update: touchups

* Added new Stage 1 notebook to create unlabelled
Vertex AI AutoML text entity extraction dataset
from collection of PDF files on Google Cloud Storage

* Linted notebook

* Removed TODOs

* Updates per PR comments

* Revered to multiple imports per line

.cloud-build/cleanup/cleanup.py

@@ -1,45 +1,49 @@
 from typing import List
+from ratemate import RateLimit
 from resource_cleanup_manager import (
-	ResourceCleanupManager,
-	DatasetResourceCleanupManager,
-	EndpointResourceCleanupManager,
-	ModelResourceCleanupManager,
+    DatasetResourceCleanupManager,
+    ModelResourceCleanupManager,
+    EndpointResourceCleanupManager,
+    ResourceCleanupManager,
 )
 
+rate_limit = RateLimit(max_count=25, per=60, greedy=False)
+
 
 def run_cleanup_managers(managers: List[ResourceCleanupManager], is_dry_run: bool):
-	for manager in managers:
-		type_name = manager.type_name
+    for manager in managers:
+        type_name = manager.type_name
 
-		print(f"Fetching {type_name}'s...")
-		resources = manager.list()
-		print(f"Found {len(resources)} {type_name}'s")
-		for resource in resources:
-			if not manager.is_deletable(resource):
-				continue
+        print(f"Fetching {type_name}'s...")
+        resources = manager.list()
+        print(f"Found {len(resources)} {type_name}'s")
+        for resource in resources:
+            try:
+                if not manager.is_deletable(resource):
+                    continue
 
-			if is_dry_run:
-				resource_name = manager.resource_name(resource)
-				print(f"Will delete '{type_name}': {resource_name}")
-			else:
-				try:
-					manager.delete(resource)
-				except Exception as exception:
-					print(exception)
+                if is_dry_run:
+                    resource_name = manager.resource_name(resource)
+                    print(f"Will delete '{type_name}': {resource_name}")
+                else:
+                    rate_limit.wait()  # wait before deleting
+                    manager.delete(resource)
+            except Exception as exception:
+                print(exception)
 
-		print("")
+        print("")
 
 
 is_dry_run = False
 
 if is_dry_run:
-	print("Starting cleanup in dry run mode...")
+    print("Starting cleanup in dry run mode...")
 
 # List of all cleanup managers
 managers = [
-	DatasetResourceCleanupManager(),
-	EndpointResourceCleanupManager(),
-	ModelResourceCleanupManager(),
+    DatasetResourceCleanupManager(),
+    EndpointResourceCleanupManager(),
+    ModelResourceCleanupManager(),  # ModelResourceCleanupManager must follow EndpointResourceCleanupManager due to deployed models blocking model deletion.
 ]
 
 run_cleanup_managers(managers=managers, is_dry_run=is_dry_run)

.cloud-build/cleanup/resource_cleanup_manager.py

@@ -1,8 +1,9 @@
 import abc
+from typing import Any, Type
+
 from google.cloud import aiplatform
-from typing import Any
-from proto.datetime_helpers import DatetimeWithNanoseconds
 from google.cloud.aiplatform import base
+from proto.datetime_helpers import DatetimeWithNanoseconds
 
 # If a resource was updated within this number of seconds, do not delete.
 RESOURCE_UPDATE_BUFFER_IN_SECONDS = 60 * 60 * 8
@@ -40,7 +41,7 @@ class ResourceCleanupManager(abc.ABC):
         # Check that it wasn't created too recently, to prevent race conditions
         if time_difference <= RESOURCE_UPDATE_BUFFER_IN_SECONDS:
             print(
-                f"Skipping '{resource}' due update_time being '{time_difference}', which is less than '{RESOURCE_UPDATE_BUFFER_IN_SECONDS}'."
+                f"Skipping '{resource}' due to update_time being '{time_difference}', which is less than '{RESOURCE_UPDATE_BUFFER_IN_SECONDS}'."
             )
             return False
 
@@ -50,7 +51,7 @@ class ResourceCleanupManager(abc.ABC):
 class VertexAIResourceCleanupManager(ResourceCleanupManager):
     @property
     @abc.abstractmethod
-    def vertex_ai_resource(self) -> base.VertexAiResourceNounWithFutureManager:
+    def vertex_ai_resource(self) -> Type[base.VertexAiResourceNounWithFutureManager]:
         pass
 
     @property
@@ -60,7 +61,9 @@ class VertexAIResourceCleanupManager(ResourceCleanupManager):
     def list(self) -> Any:
         return self.vertex_ai_resource.list()
 
-    def resource_name(self, resource: Any) -> str:
+    def resource_name(
+        self, resource: Type[base.VertexAiResourceNounWithFutureManager]
+    ) -> str:
         return resource.display_name
 
     def delete(self, resource):
@@ -74,12 +77,33 @@ class VertexAIResourceCleanupManager(ResourceCleanupManager):
 
 class DatasetResourceCleanupManager(VertexAIResourceCleanupManager):
     vertex_ai_resource = aiplatform.datasets._Dataset
+    dataset_types = [
+        aiplatform.ImageDataset,
+        aiplatform.TabularDataset,
+        aiplatform.TextDataset,
+        aiplatform.TimeSeriesDataset,
+        aiplatform.VideoDataset,
+    ]
+
+    def list(self) -> Any:
+        return [
+            dataset
+            for dataset_type in self.dataset_types
+            for dataset in dataset_type.list()
+        ]
 
 
 class EndpointResourceCleanupManager(VertexAIResourceCleanupManager):
     vertex_ai_resource = aiplatform.Endpoint
 
     def delete(self, resource):
+        # TODO: Remove this once https://github.com/googleapis/python-aiplatform/issues/1441 is fixed
+        resource._sync_gca_resource()
+        for deployed_model_id in [
+            models.id for models in resource._gca_resource.deployed_models
+        ]:
+            resource._undeploy(deployed_model_id=deployed_model_id)
+
         resource.delete(force=True)
 
 

.cloud-build/execute_changed_notebooks_cli.py

@@ -17,6 +17,7 @@
 
 import argparse
 import pathlib
+
 import execute_changed_notebooks_helper
 
 
@@ -73,6 +74,13 @@ parser.add_argument(
     help="The GCP directory for storing executed notebooks.",
     required=True,
 )
+parser.add_argument(
+    "--timeout",
+    type=int,
+    help="Timeout in seconds",
+    default=86400,
+    required=False,
+)
 parser.add_argument(
     "--private_pool_id",
     type=str,
@@ -102,6 +110,7 @@ execute_changed_notebooks_helper.process_and_execute_notebooks(
     artifacts_bucket=args.artifacts_bucket,
     variable_project_id=args.variable_project_id,
     variable_region=args.variable_region,
-    private_pool_id=args.private_pool_id if not "default" else None,
+    private_pool_id=args.private_pool_id,
     should_parallelize=args.should_parallelize,
+    timeout=args.timeout,
 )

.cloud-build/execute_changed_notebooks_helper.py

@@ -17,18 +17,24 @@ import concurrent
 import dataclasses
 import datetime
 import functools
+import git
+import operator
 import os
 import pathlib
-import nbformat
 import re
 import subprocess
 from typing import List, Optional
-from tabulate import tabulate
-import operator
 
+import execute_notebook_helper
 import execute_notebook_remote
-from utils import util, NotebookProcessors
+import nbformat
 from google.cloud.devtools.cloudbuild_v1.types import BuildOperationMetadata
+from ratemate import RateLimit
+from tabulate import tabulate
+from utils import NotebookProcessors, util
+
+# A buffer so that workers finish before the orchestrating job
+WORKER_TIMEOUT_BUFFER_IN_SECONDS: int = 60 * 60
 
 
 def format_timedelta(delta: datetime.timedelta) -> str:
@@ -103,6 +109,9 @@ def _create_tag(filepath: str) -> str:
     return tag
 
 
+rate_limit = RateLimit(max_count=50, per=60, greedy=True)
+
+
 def process_and_execute_notebook(
     container_uri: str,
     staging_bucket: str,
@@ -110,9 +119,12 @@ def process_and_execute_notebook(
     variable_project_id: str,
     variable_region: str,
     private_pool_id: Optional[str],
+    deadline: datetime,
     notebook: str,
     should_get_tail_logs: bool = False,
 ) -> NotebookExecutionResult:
+    rate_limit.wait()  # wait before creating the task
+
     print(f"Running notebook: {notebook}")
 
     # Create paths
@@ -145,14 +157,20 @@ def process_and_execute_notebook(
         # Upload the pre-processed code to a GCS bucket
         code_archive_uri = util.archive_code_and_upload(staging_bucket=staging_bucket)
 
+        # Calculate timeout in seconds
+        timeout_in_seconds = max(
+            int((deadline - datetime.datetime.now()).total_seconds()), 1
+        )
+
         operation = execute_notebook_remote.execute_notebook_remote(
             code_archive_uri=code_archive_uri,
             notebook_uri=notebook,
             notebook_output_uri=notebook_output_uri,
             container_uri=container_uri,
             tag=tag,
-            region=variable_region,
             private_pool_id=private_pool_id,
+            private_pool_region=variable_region,
+            timeout_in_seconds=timeout_in_seconds,
         )
 
         operation_metadata = BuildOperationMetadata(mapping=operation.metadata)
@@ -215,20 +233,39 @@ def get_changed_notebooks(
 
     # Find notebooks
     notebooks = []
+
+    # Instantiate GitPython objects
+    repo = git.Repo(os.getcwd())
+    index = repo.index
+
     if base_branch:
-        print(f"Looking for notebooks that changed from branch: {base_branch}")
-        notebooks = subprocess.check_output(
-            ["git", "diff", "--name-only", f"origin/{base_branch}..."] + test_paths
-        )
+        # Get the point at which this branch branches off from main
+        branching_commits = repo.merge_base("HEAD", f"origin/{base_branch}")
+
+        if len(branching_commits) > 0:
+            branching_commit = branching_commits[0]
+            print(f"Looking for notebooks that changed from branch: {branching_commit}")
+
+            notebooks = [
+                diff.b_path
+                for diff in index.diff(branching_commit, paths=test_paths)
+                if diff.b_path is not None
+            ]
+        else:
+            notebooks = []
     else:
         print(f"Looking for all notebooks.")
         notebooks = subprocess.check_output(["git", "ls-files"] + test_paths)
 
-    notebooks = notebooks.decode("utf-8").split("\n")
     notebooks = [notebook for notebook in notebooks if notebook.endswith(".ipynb")]
     notebooks = [notebook for notebook in notebooks if len(notebook) > 0]
     notebooks = [notebook for notebook in notebooks if pathlib.Path(notebook).exists()]
 
+    if len(notebooks) > 0:
+        print(f"Found {len(notebooks)} notebooks:")
+        for notebook in notebooks:
+            print(f"\t{notebook}")
+
     return notebooks
 
 
@@ -241,6 +278,7 @@ def process_and_execute_notebooks(
     variable_region: str,
     private_pool_id: Optional[str],
     should_parallelize: bool,
+    timeout: int,
 ):
     """
     Run the notebooks that exist under the folders defined in the test_paths_file.
@@ -267,17 +305,27 @@ def process_and_execute_notebooks(
             Required. The value for REGION to inject into notebooks.
         should_parallelize (bool):
             Required. Should run notebooks in parallel using a thread pool as opposed to in sequence.
+        timeout (str):
+            Required. Timeout string according to https://cloud.google.com/build/docs/build-config-file-schema#timeout.
     """
-    notebook_execution_results: List[NotebookExecutionResult] = []
 
-    if len(notebooks) > 0:
+    # Calculate deadline
+    deadline = datetime.datetime.now() + datetime.timedelta(
+        seconds=max(timeout - WORKER_TIMEOUT_BUFFER_IN_SECONDS, 0)
+    )
+
+    if len(notebooks) > 1:
+        notebook_execution_results: List[NotebookExecutionResult] = []
+
         print(f"Found {len(notebooks)} modified notebooks: {notebooks}")
 
         if should_parallelize and len(notebooks) > 1:
             print(
                 "Running notebooks in parallel, so no logs will be displayed. Please wait..."
             )
-            with concurrent.futures.ThreadPoolExecutor(max_workers=None) as executor:
+            with concurrent.futures.ThreadPoolExecutor(max_workers=100) as executor:
+                print(f"Max workers: {executor._max_workers}")
+
                 notebook_execution_results = list(
                     executor.map(
                         functools.partial(
@@ -288,6 +336,7 @@ def process_and_execute_notebooks(
                             variable_project_id,
                             variable_region,
                             private_pool_id,
+                            deadline,
                         ),
                         notebooks,
                     )
@@ -301,47 +350,69 @@ def process_and_execute_notebooks(
                     variable_project_id=variable_project_id,
                     variable_region=variable_region,
                     private_pool_id=private_pool_id,
+                    deadline=deadline,
                     notebook=notebook,
                 )
                 for notebook in notebooks
             ]
+
+        print("\n=== RESULTS ===\n")
+
+        results_sorted = sorted(
+            notebook_execution_results,
+            key=lambda result: result.is_pass,
+            reverse=True,
+        )
+
+        # Print results
+        print(
+            tabulate(
+                [
+                    [
+                        result.name,
+                        "PASSED" if result.is_pass else "FAILED",
+                        format_timedelta(result.duration),
+                        result.log_url,
+                        result.output_uri,
+                    ]
+                    for result in results_sorted
+                ],
+                headers=["build_tag", "status", "duration", "log_url", "output_url"],
+            )
+        )
+
+        print("\n=== END RESULTS===\n")
+
+        total_notebook_duration = functools.reduce(
+            operator.add,
+            [datetime.timedelta(seconds=0)]
+            + [result.duration for result in results_sorted],
+        )
+
+        print(
+            f"Cumulative notebook duration: {format_timedelta(total_notebook_duration)}"
+        )
+
+        # Raise error if any notebooks failed
+        if not all([result.is_pass for result in results_sorted]):
+            raise RuntimeError("Notebook failures detected. See logs for details")
+
+    elif len(notebooks) == 1:
+        notebook = notebooks[0]
+
+        # Pre-process notebook by substituting variable names
+        _process_notebook(
+            notebook_path=notebook,
+            variable_project_id=variable_project_id,
+            variable_region=variable_region,
+        )
+
+        execute_notebook_helper.execute_notebook(
+            notebook_source=notebook,
+            output_file_or_uri="/".join(
+                [artifacts_bucket, pathlib.Path(notebook).name]
+            ),
+            should_log_output=True,
+        )
     else:
         print("No notebooks modified in this pull request.")
-
-    print("\n=== RESULTS ===\n")
-
-    results_sorted = sorted(
-        notebook_execution_results,
-        key=lambda result: result.is_pass,
-        reverse=True,
-    )
-
-    # Print results
-    print(
-        tabulate(
-            [
-                [
-                    result.name,
-                    "PASSED" if result.is_pass else "FAILED",
-                    format_timedelta(result.duration),
-                    result.log_url,
-                ]
-                for result in results_sorted
-            ],
-            headers=["build_tag", "status", "duration", "log_url"],
-        )
-    )
-
-    print("\n=== END RESULTS===\n")
-
-    total_notebook_duration = functools.reduce(
-        operator.add,
-        [datetime.timedelta(seconds=0)]
-        + [result.duration for result in results_sorted],
-    )
-
-    print(f"Cumulative notebook duration: {format_timedelta(total_notebook_duration)}")
-
-    # Raise error if any notebooks failed
-    if not all([result.is_pass for result in results_sorted]):
-        raise RuntimeError("Notebook failures detected. See logs for details")

.cloud-build/execute_notebook_cli.py

@@ -16,6 +16,7 @@
 """A CLI to download (optional) and run a single notebook locally"""
 
 import argparse
+
 import execute_notebook_helper
 
 parser = argparse.ArgumentParser(description="Run a single notebook locally.")

.cloud-build/execute_notebook_helper.py

@@ -15,14 +15,14 @@
 
 """Methods to run a notebook locally"""
 
-import sys
-import os
 import errno
-import papermill as pm
+import os
 import shutil
+import sys
 
-from utils import util
+import papermill as pm
 from google.cloud.aiplatform import utils
+from utils import util
 
 # This script is used to execute a notebook and write out the output notebook.
 

.cloud-build/execute_notebook_remote.py

@@ -16,22 +16,18 @@
 """Methods to run a notebook on Google Cloud Build"""
 
 from re import sub
+from typing import Optional
+
+import google.auth
+import yaml
+from google.api_core import client_options, operation
+from google.cloud.aiplatform import utils
+from google.cloud.devtools import cloudbuild_v1
+from google.cloud.devtools.cloudbuild_v1.types import Source, StorageSource
 from google.protobuf import duration_pb2
 from yaml.loader import FullLoader
 
-import google.auth
-from google.cloud.devtools import cloudbuild_v1
-from google.cloud.devtools.cloudbuild_v1.types import Source, StorageSource
-
-from typing import Optional
-import yaml
-
-from google.cloud.aiplatform import utils
-from google.api_core import operation, client_options
-
-
 CLOUD_BUILD_FILEPATH = ".cloud-build/notebook-execution-test-cloudbuild-single.yaml"
-TIMEOUT_IN_SECONDS = 86400
 SERVICE_BASE_PATH = "cloudbuild.googleapis.com"
 
 
@@ -40,12 +36,14 @@ def execute_notebook_remote(
     notebook_uri: str,
     notebook_output_uri: str,
     container_uri: str,
-    region: str,
     private_pool_id: Optional[str],
+    private_pool_region: Optional[str],
     tag: Optional[str],
+    timeout_in_seconds: Optional[int] = None,
 ) -> operation.Operation:
     """Create and execute a single notebook on Google Cloud Build"""
     # Load build steps from YAML
+
     cloudbuild_config = yaml.load(open(CLOUD_BUILD_FILEPATH), Loader=FullLoader)
 
     substitutions = {
@@ -57,13 +55,14 @@ def execute_notebook_remote(
     build = cloudbuild_v1.Build()
 
     options: Optional[client_options.ClientOptions] = None
-    if private_pool_id:
-        substitutions["_PRIVATE_POOL_NAME"] = private_pool_id
-        build.options = cloudbuild_config["options"]
+    if private_pool_id and private_pool_region:
+        # substitutions["_PRIVATE_POOL_NAME"] = private_pool_id
+        build.options = cloudbuild_config.get("options")
+        build.options.pool = {"name": private_pool_id}
 
         # Switch to the regional endpoint of the pool
         options = client_options.ClientOptions(
-            api_endpoint=f"{region}-{SERVICE_BASE_PATH}"
+            api_endpoint=f"{private_pool_region}-{SERVICE_BASE_PATH}"
         )
 
     # Authorize the client with Google defaults
@@ -85,8 +84,8 @@ def execute_notebook_remote(
 
     build.steps = cloudbuild_config["steps"]
     build.substitutions = substitutions
-    build.timeout = duration_pb2.Duration(seconds=TIMEOUT_IN_SECONDS)
-    build.queue_ttl = duration_pb2.Duration(seconds=TIMEOUT_IN_SECONDS)
+    build.timeout = duration_pb2.Duration(seconds=timeout_in_seconds)
+    build.queue_ttl = duration_pb2.Duration(seconds=timeout_in_seconds)
 
     if tag:
         build.tags = [tag]

.cloud-build/notebook-execution-test-cloudbuild-single.yaml

@@ -25,7 +25,4 @@ steps:
     - 'python3 -m pip install -U pip && python3 -m pip freeze && python3 .cloud-build/execute_notebook_cli.py --notebook_source "${_NOTEBOOK_GCS_URI}" --output_file_or_uri "${_NOTEBOOK_OUTPUT_GCS_URI}"'
     env:
     - 'IS_TESTING=1'
-timeout: 86400s
-options:
-  pool:
-    name: ${_PRIVATE_POOL_NAME}
+timeout: 86400s

.cloud-build/notebook-execution-test-cloudbuild.yaml

@@ -11,12 +11,9 @@ steps:
     args:
     - -c
     - 'python3 .cloud-build/CheckPythonVersion.py'
-  # Fetch base branch if required
-  - name: ${_PYTHON_IMAGE}
-    entrypoint: /bin/sh
-    args:
-    - -c
-    - 'if [ -n "${_BASE_BRANCH}" ]; then git fetch origin "${_BASE_BRANCH}":refs/remotes/origin/"${_BASE_BRANCH}"; else echo "Skipping fetch."; fi'
+  # Fetch full repo for diff purposes
+  - name: gcr.io/cloud-builders/git
+    args: [fetch, --unshallow]
   # Install Python dependencies
   - name: ${_PYTHON_IMAGE}
     entrypoint: /bin/sh

.cloud-build/requirements.txt

@@ -9,4 +9,5 @@ tabulate
 google-cloud-aiplatform
 google-cloud-storage
 google-cloud-build
-gcloud
+ratemate
+GitPython

.cloud-build/test_folders.txt

@@ -1,3 +1,2 @@
 notebooks/official
 notebooks/notebook_template.ipynb
-notebooks/community/ml_ops

.cloud-build/utils/NotebookProcessors.py

@@ -13,8 +13,10 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-from nbconvert.preprocessors import Preprocessor
 from typing import Dict
+
+from nbconvert.preprocessors import Preprocessor
+
 from . import UpdateNotebookVariables as update_notebook_variables
 
 
@@ -60,4 +62,4 @@ class UpdateVariablesPreprocessor(Preprocessor):
 
             executable_cells.append(cell)
         notebook.cells = executable_cells
-        return notebook, resources
+        return notebook, resources

.cloud-build/utils/UpdateNotebookVariables.py

@@ -78,4 +78,4 @@ def test_region():
         variable_name="REGION",
         variable_value="us-central1",
     )
-    assert new_content == 'REGION = "us-central1"  # @param {type:"string"}'
+    assert new_content == 'REGION = "us-central1"  # @param {type:"string"}'

.cloud-build/utils/util.py

@@ -1,13 +1,13 @@
-from datetime import datetime
-from typing import Optional
-from google.cloud import storage
-from google.cloud.aiplatform import utils
-from google.auth import credentials as auth_credentials
 import os
-
 import subprocess
 import tarfile
 import uuid
+from datetime import datetime
+from typing import Optional
+
+from google.auth import credentials as auth_credentials
+from google.cloud import storage
+from google.cloud.aiplatform import utils
 
 
 def download_file(bucket_name: str, blob_name: str, destination_file: str) -> str:
@@ -57,4 +57,4 @@ def archive_code_and_upload(staging_bucket: str):
 
     print(f"Uploaded source code archive to {source_archived_file_gcs}")
 
-    return source_archived_file_gcs
+    return source_archived_file_gcs

.github/PULL_REQUEST_TEMPLATE.md

@@ -2,17 +2,17 @@ If you are opening a PR for `Official Notebooks` under the [notebooks/official](
 - [ ] Use the [notebook template](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/notebook_template.ipynb) as a starting point.
 - [ ] Follow the style and grammar rules outlined in the above notebook template.
 - [ ] Verify the notebook runs successfully in Colab since the automated tests cannot guarantee this even when it passes.
-- [ ] Passes all the required automated checks. You can locally test for formatting and linting with these [instructions](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/docs/contributing.md#code-quality-checks).
+- [ ] Passes all the required automated checks. You can locally test for formatting and linting with these [instructions](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/CONTRIBUTING.md#code-quality-checks).
 - [ ] You have consulted with a tech writer to see if tech writer review is necessary. If so, the notebook has been reviewed by a tech writer, and they have approved it.
-- [ ] This notebook has been added to the [CODEOWNERS](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/docs/CODEOWNERS) file under `# Official Notebooks` section, pointing to the author or the author's team.
+- [ ] This notebook has been added to the [CODEOWNERS](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/CODEOWNERS) file under the `Official Notebooks` section, pointing to the author or the author's team.
 - [ ] The Jupyter notebook cleans up any artifacts it has created (datasets, ML models, endpoints, etc) so as not to eat up unnecessary resources.
 
 
 If you are opening a PR for `Community Notebooks` under the [notebooks/community](https://github.com/GoogleCloudPlatform/vertex-ai-samples/tree/main/notebooks/community) folder:
-- [ ] This notebook has been added to the [CODEOWNERS](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/docs/CODEOWNERS) file under the `# Community Notebooks` section, pointing to the author or the author's team.
-- [ ] Passes all the required formatting and linting checks. You can locally test with these [instructions](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/docs/contributing.md#code-quality-checks).
+- [ ] This notebook has been added to the [CODEOWNERS](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/CODEOWNERS) file under the `Community Notebooks` section, pointing to the author or the author's team.
+- [ ] Passes all the required formatting and linting checks. You can locally test with these [instructions](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/CONTRIBUTING.md#code-quality-checks).
 
 If you are opening a PR for `Community Content` under the [community-content](https://github.com/GoogleCloudPlatform/vertex-ai-samples/tree/main/community-content) folder:
 - [ ] Make sure your main `Content Directory Name` is descriptive, informative, and includes some of the key products and attributes of your content, so that it is differentiable from other content
-- [ ] The main content directory has been added to the [CODEOWNERS](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/docs/CODEOWNERS) file under the `# Community Content` section, pointing to the author or the author's team.
-- [ ] Passes all the required formatting and linting checks. You can locally test with these [instructions](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/docs/contributing.md#code-quality-checks).
+- [ ] The main content directory has been added to the [CODEOWNERS](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/community-content/CODEOWNERS) file under the `Community Content` section, pointing to the author or the author's team.
+- [ ] Passes all the required formatting and linting checks. You can locally test with these [instructions](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/CONTRIBUTING.md#code-quality-checks).

.github/workflows/ci.yaml

@@ -7,7 +7,9 @@ jobs:
     runs-on: ubuntu-latest
     steps:
     - name: Set up Python
-      uses: actions/setup-python@v3
+      uses: actions/setup-python@v4
+      with:
+        python-version: '3.x'      
     - name: Fetch pull request branch
       uses: actions/checkout@v3
       with:

.github/workflows/linter/requirements.txt

@@ -3,7 +3,8 @@ ipython
 jupyter
 nbconvert
 black==22.3.0
-pyupgrade==2.31.1
+pyupgrade==2.34.0
 isort==5.10.1
 flake8==4.0.1
 nbqa==1.3.1
+

CONTRIBUTING.md

@@ -48,8 +48,8 @@ then you will need to manually address them before submitting your PR.
 nbqa black "$notebook"
 nbqa pyupgrade "$notebook"
 nbqa isort "$notebook"
-python3 -m tensorflow_docs.tools.nbfmt --remove_outputs "$notebook"
 nbqa flake8 "$notebook" --extend-ignore=W391,E501,F821,E402,F404,W503,E203,E722,W293,W291
+python3 -m tensorflow_docs.tools.nbfmt --remove_outputs "$notebook"
 ```
 
 ## Code Reviews

community-content/tf_agents_bandits_movie_recommendation_with_kfp_and_vertex_sdk/mlops_pipeline_tf_agents_bandits_movie_recommendation/src/logger/requirements.txt

@@ -1,4 +1,4 @@
 google-cloud-bigquery==2.20.0
-tensorflow==2.5.3
+tensorflow==2.7.2
 pillow==9.0.1
 tf-agents==0.8.0

community-content/tf_agents_bandits_movie_recommendation_with_kfp_and_vertex_sdk/mlops_pipeline_tf_agents_bandits_movie_recommendation/src/prediction_container/requirements.txt

@@ -1,4 +1,4 @@
 google-cloud-pubsub==2.5.0
 pillow==9.0.1
 tf-agents==0.8.0
-tensorflow==2.5.3
+tensorflow==2.7.2

community-content/tf_agents_bandits_movie_recommendation_with_kfp_and_vertex_sdk/mlops_pipeline_tf_agents_bandits_movie_recommendation/src/simulator/requirements.txt

@@ -1,5 +1,5 @@
 dataclasses==0.6
 google-cloud-aiplatform==1.8.1
-tensorflow==2.5.3
+tensorflow==2.7.2
 pillow==9.0.1
 tf-agents==0.8.0

community-content/tf_keras_image_classification_distributed_multi_worker_with_vertex_sdk/trainer/requirements.txt

@@ -1 +1 @@
-tensorflow==2.5.3
+tensorflow==2.7.2

community-content/tf_keras_text_classification_distributed_single_worker_gpus_with_gcloud_local_run_and_vertex_sdk/trainer/requirements.txt

@@ -1 +1 @@
-tensorflow==2.5.3
+tensorflow==2.7.2

notebooks/README.md

@@ -1,5 +1,5 @@
-The [official](https://github.com/GoogleCloudPlatform/vertex-ai-samples/tree/main/notebooks/official) folder contains notebooks organized by Google Cloud product.
+The [official](https://github.com/GoogleCloudPlatform/vertex-ai-samples/tree/main/notebooks/official) folder contains notebooks organized by Google Cloud product. These are tested weekly and maintained by Google.
 
-The [community](https://github.com/GoogleCloudPlatform/vertex-ai-samples/tree/main/notebooks/community) folder contains notebooks that aren't officially supported by Google.
+The [community](https://github.com/GoogleCloudPlatform/vertex-ai-samples/tree/main/notebooks/community) folder contains notebooks that may be created by Google or external contributors. They are not necessary maintained.
 
 Contributions to the repo should use the [notebook template](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/notebook_template.ipynb) as a starting point.

notebooks/community/CODEOWNERS

@@ -12,6 +12,7 @@
 /managed_notebooks/
 /sdk/SDK_FBProphet_Forecasting_Online.ipynb @brianchunkang
 /pipelines/google_cloud_pipeline_components_TPU_model_train_upload_deploy.ipynb @brianchunkang
+/explainable_ai/SDK_Custom_Container_XAI.ipynb @brianchunkang
 /matching_engine/sdk_matching_engine_for_indexing.ipynb @ivanmkc
 /matching_engine/matching_engine_for_indexing.ipynb @yinghsienwu
 /sdk/pytorch_lightning_custom_container_training.ipynb @brianchunkang
@@ -19,3 +20,7 @@
 /feature_store @nayaknishant @morgandu
 /vertex_endpoints/tf_hub_obj_detection/deploy_tfhub_object_detection_on_vertex_endpoints.ipynb @entrpn
 /vertex_endpoints/nvidia-triton/nvidia-triton-custom-container-prediction.ipynb @RajeshThallam
+/vertex_endpoints/optimized_tensorflow_runtime @vlasenkoalexey
+/notebooks/community/ml_ops/stage2/get_started_with_visionapi_and_automl.ipynb @mansari
+/notebooks/community/neo4j/graph_paysim.ipynb @benofben @laeg
+/notebooks/community/ml_ops/stage1/get_started_with_visionapi_and_vertex_datasets.ipynb @mansari

notebooks/community/matching_engine/sdk_matching_engine_for_indexing.ipynb

@@ -98,10 +98,10 @@
         "## Before you begin\n",
         "\n",
         "* **Prepare a VPC network**.  To reduce any network overhead that might lead to unnecessary increase in overhead latency, it is best to call the ANN endpoints from your VPC via a direct [VPC Peering](https://cloud.google.com/vertex-ai/docs/general/vpc-peering) connection. The following section describes how to setup a VPC Peering connection if you don't have one. This is a one-time initial setup task. You can also reuse existing VPC network and skip this section.\n",
-        "* **WARNING:** The match service gRPC API (to create online queries against your deployed index) has to be executed in a Google Cloud Notebook instance that is created with the following requirements:\n",
+        "* **WARNING:** The MatchingIndexEndpoint.match method (to create online queries against your deployed index) has to be executed in a Vertex AI Workbench notebook instance that is created with the following requirements:\n",
         "  * **In the same region as where your ANN service is deployed** (for example, if you set `REGION = \"us-central1\"` as same as the tutorial, the notebook instance has to be in `us-central1`).\n",
         "  * **Make sure you select the VPC network you created for ANN service** (instead of using the \"default\" one). That is, you will have to create the VPC network below and then create a new notebook instance that uses that VPC.  \n",
-        "  * If you run it in the colab or a Google Cloud Notebook instance in a different VPC network or region, the gRPC API will fail to peer the network (InactiveRPCError)."
+        "  * If you run it in the colab or a Vertex AI Workbench notebook instance in a different VPC network or region, the gRPC API will fail to peer the network (InactiveRPCError)."
       ]
     },
     {
@@ -114,9 +114,9 @@
       "source": [
         "PROJECT_ID = \"<your_project_id>\"  # @param {type:\"string\"}\n",
         "\n",
-        "NETWORK_NAME = \"ucaip-haystack-vpc-network\"  # @param {type:\"string\"}\n",
+        "NETWORK_NAME = \"my-vpc-network\"  # @param {type:\"string\"}\n",
         "\n",
-        "PEERING_RANGE_NAME = \"ucaip-haystack-range\""
+        "PEERING_RANGE_NAME = \"my-haystack-range\""
       ]
     },
     {
@@ -140,7 +140,7 @@
         "! gcloud compute firewall-rules create {NETWORK_NAME}-allow-ssh --network {NETWORK_NAME} --priority 65534 --project {PROJECT_ID} --allow tcp:22\n",
         "\n",
         "# Reserve IP range\n",
-        "! gcloud compute addresses create {PEERING_RANGE_NAME} --global --prefix-length=16 --network={NETWORK_NAME} --purpose=VPC_PEERING --project={PROJECT_ID} --description=\"peering range for uCAIP Haystack.\"\n",
+        "! gcloud compute addresses create {PEERING_RANGE_NAME} --global --prefix-length=16 --network={NETWORK_NAME} --purpose=VPC_PEERING --project={PROJECT_ID} --description=\"peering range\"\n",
         "\n",
         "# Set up peering with service networking\n",
         "! gcloud services vpc-peerings connect --service=servicenetworking.googleapis.com --network={NETWORK_NAME} --ranges={PEERING_RANGE_NAME} --project={PROJECT_ID}"
@@ -152,7 +152,7 @@
         "id": "d3uj8x73nDX_"
       },
       "source": [
-        "* Authentication: `$ gcloud auth login` rerun this in Google Cloud Notebook terminal when you are logged out and need the credential again."
+        "* Authentication: Rerun the `gcloud auth login` command in the Vertex AI Workbench notebook terminal when you are logged out and need the credential again."
       ]
     },
     {
@@ -163,7 +163,7 @@
       "source": [
         "### Installation\n",
         "\n",
-        "Download and install the latest (preview) version of the Vertex SDK for Python."
+        "Download and install the latest version of the Vertex SDK for Python."
       ]
     },
     {
@@ -174,7 +174,7 @@
       },
       "outputs": [],
       "source": [
-        "! pip install -U git+https://github.com/ivanmkc/python-aiplatform.git@imkc--matching-engine"
+        "! pip install -U google-cloud-aiplatform"
       ]
     },
     {
@@ -333,7 +333,7 @@
       "source": [
         "### Authenticate your Google Cloud account\n",
         "\n",
-        "**If you are using Google Cloud Notebooks**, your environment is already\n",
+        "**If you are using a Vertex AI Workbench notebook**, your environment is already\n",
         "authenticated. Skip this step."
       ]
     },
@@ -383,11 +383,13 @@
         "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
         "# requests.\n",
         "\n",
-        "# The Google Cloud Notebook product has specific requirements\n",
-        "IS_GOOGLE_CLOUD_NOTEBOOK = os.path.exists(\"/opt/deeplearning/metadata/env_version\")\n",
+        "# The Vertex AI Workbench notebook product has specific requirements\n",
+        "IS_VERTEX_AI_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
         "\n",
-        "# If on Google Cloud Notebooks, then don't execute this code\n",
-        "if not IS_GOOGLE_CLOUD_NOTEBOOK:\n",
+        "# If on a Vertex AI Workbench notebook, then don't execute this code\n",
+        "if not IS_VERTEX_AI_WORKBENCH_NOTEBOOK:\n",
         "    if \"google.colab\" in sys.modules:\n",
         "        from google.colab import auth as google_auth\n",
         "\n",
@@ -539,12 +541,12 @@
         "id": "lR6Wwv-hCCN-"
       },
       "source": [
-        "## Prepare the Data\n",
+        "## Prepare the data\n",
         "\n",
         "The GloVe dataset consists of a set of pre-trained embeddings. The embeddings are split into a \"train\" split, and a \"test\" split.\n",
         "We will create a vector search index from the \"train\" split, and use the embedding vectors in the \"test\" split as query vectors to test the vector search index.\n",
         "\n",
-        "NOTE: While the data split uses the term \"train\", these are pre-trained embeddings and thus are ready to be indexed for search. The terms \"train\" and \"test\" split are used just to be consistent with usual machine learning terminology.\n",
+        "**Note:** While the data split uses the term \"train\", these are pre-trained embeddings and therefore are ready to be indexed for search. The terms \"train\" and \"test\" split are used just to be consistent with machine learning terminology.\n",
         "\n",
         "Download the GloVe dataset.\n"
       ]

notebooks/community/ml_metadata/sdk-metric-parameter-tracking-for-locally-trained-models.ipynb

@@ -1,877 +0,0 @@
-{
-  "cells": [
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "ur8xi4C7S06n"
-      },
-      "outputs": [],
-      "source": [
-        "# Copyright 2021 Google LLC\n",
-        "#\n",
-        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
-        "# you may not use this file except in compliance with the License.\n",
-        "# You may obtain a copy of the License at\n",
-        "#\n",
-        "#     https://www.apache.org/licenses/LICENSE-2.0\n",
-        "#\n",
-        "# Unless required by applicable law or agreed to in writing, software\n",
-        "# distributed under the License is distributed on an \"AS IS\" BASIS,\n",
-        "# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
-        "# See the License for the specific language governing permissions and\n",
-        "# limitations under the License."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "JAPoU8Sm5E6e"
-      },
-      "source": [
-        "<table align=\"left\">\n",
-        "\n",
-        "  <td>\n",
-        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/master/notebooks/community/ml_metadata/sdk-metric-parameter-tracking-for-locally-trained-models.ipynb\">\n",
-        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
-        "    </a>\n",
-        "  </td>\n",
-        "  <td>\n",
-        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/master/notebooks/community/ml_metadata/sdk-metric-parameter-tracking-for-locally-trained-models.ipynb\">\n",
-        "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
-        "      View on GitHub\n",
-        "    </a>\n",
-        "  </td>\n",
-        "</table>"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "WBFL9LagqmwT"
-      },
-      "source": [
-        "#Vertex AI: Track parameters and metrics for locally trained models"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "tvgnzT1CKxrO"
-      },
-      "source": [
-        "## Overview\n",
-        "\n",
-        "This notebook demonstrates how to track metrics and parameters for ML training jobs and analyze this metadata using Vertex SDK for Python.\n",
-        "\n",
-        "### Dataset\n",
-        "\n",
-        "In this notebook, we will train a simple distributed neural network (DNN) model to predict automobile's miles per gallon (MPG) based on automobile information in the [auto-mpg dataset](https://www.kaggle.com/devanshbesain/exploration-and-analysis-auto-mpg).\n",
-        "\n",
-        "### Objective\n",
-        "\n",
-        "In this notebook, you will learn how to use Vertex SDK for Python to:\n",
-        "\n",
-        "    * Track parameters and metrics for a locally trainined model.\n",
-        "    * Extract and perform analysis for all parameters and metrics within an Experiment.\n",
-        "\n",
-        "### Costs \n",
-        "\n",
-        "\n",
-        "This tutorial uses billable components of Google Cloud:\n",
-        "\n",
-        "* Vertex AI\n",
-        "* Cloud Storage\n",
-        "\n",
-        "\n",
-        "Learn about [Vertex AI\n",
-        "pricing](https://cloud.google.com/vertex-ai/pricing) and [Cloud Storage\n",
-        "pricing](https://cloud.google.com/storage/pricing), and use the [Pricing\n",
-        "Calculator](https://cloud.google.com/products/calculator/)\n",
-        "to generate a cost estimate based on your projected usage."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "ze4-nDLfK4pw"
-      },
-      "source": [
-        "### Set up your local development environment\n",
-        "\n",
-        "**If you are using Colab or Google Cloud Notebooks**, your environment already meets\n",
-        "all the requirements to run this notebook. You can skip this step."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "gCuSR8GkAgzl"
-      },
-      "source": [
-        "**Otherwise**, make sure your environment meets this notebook's requirements.\n",
-        "You need the following:\n",
-        "\n",
-        "* The Google Cloud SDK\n",
-        "* Git\n",
-        "* Python 3\n",
-        "* virtualenv\n",
-        "* Jupyter notebook running in a virtual environment with Python 3\n",
-        "\n",
-        "The Google Cloud guide to [Setting up a Python development\n",
-        "environment](https://cloud.google.com/python/setup) and the [Jupyter\n",
-        "installation guide](https://jupyter.org/install) provide detailed instructions\n",
-        "for meeting these requirements. The following steps provide a condensed set of\n",
-        "instructions:\n",
-        "\n",
-        "1. [Install and initialize the Cloud SDK.](https://cloud.google.com/sdk/docs/)\n",
-        "\n",
-        "1. [Install Python 3.](https://cloud.google.com/python/setup#installing_python)\n",
-        "\n",
-        "1. [Install\n",
-        "   virtualenv](https://cloud.google.com/python/setup#installing_and_using_virtualenv)\n",
-        "   and create a virtual environment that uses Python 3. Activate the virtual environment.\n",
-        "\n",
-        "1. To install Jupyter, run `pip install jupyter` on the\n",
-        "command-line in a terminal shell.\n",
-        "\n",
-        "1. To launch Jupyter, run `jupyter notebook` on the command-line in a terminal shell.\n",
-        "\n",
-        "1. Open this notebook in the Jupyter Notebook Dashboard."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "i7EUnXsZhAGF"
-      },
-      "source": [
-        "### Install additional packages\n",
-        "\n",
-        "Run the following commands to install the Vertex SDK for Python."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "IaYsrh0Tc17L"
-      },
-      "outputs": [],
-      "source": [
-        "import sys\n",
-        "\n",
-        "if \"google.colab\" in sys.modules:\n",
-        "    USER_FLAG = \"\"\n",
-        "else:\n",
-        "    USER_FLAG = \"--user\""
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "wyy5Lbnzg5fi"
-      },
-      "outputs": [],
-      "source": [
-        "!python3 -m pip install {USER_FLAG} google-cloud-aiplatform --upgrade"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "hhq5zEbGg0XX"
-      },
-      "source": [
-        "### Restart the kernel\n",
-        "\n",
-        "After you install the additional packages, you need to restart the notebook kernel so it can find the packages."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "EzrelQZ22IZj"
-      },
-      "outputs": [],
-      "source": [
-        "# Automatically restart kernel after installs\n",
-        "import os\n",
-        "\n",
-        "if not os.getenv(\"IS_TESTING\"):\n",
-        "    # Automatically restart kernel after installs\n",
-        "    import IPython\n",
-        "\n",
-        "    app = IPython.Application.instance()\n",
-        "    app.kernel.do_shutdown(True)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "lWEdiXsJg0XY"
-      },
-      "source": [
-        "## Before you begin\n",
-        "\n",
-        "### Select a GPU runtime\n",
-        "\n",
-        "**Make sure you're running this notebook in a GPU runtime if you have that option. In Colab, select \"Runtime --> Change runtime type > GPU\"**"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "BF1j6f9HApxa"
-      },
-      "source": [
-        "### Set up your Google Cloud project\n",
-        "\n",
-        "**The following steps are required, regardless of your notebook environment.**\n",
-        "\n",
-        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
-        "\n",
-        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
-        "\n",
-        "1. [Enable the Vertex AI API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com).\n",
-        "\n",
-        "1. If you are running this notebook locally, you will need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
-        "\n",
-        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
-        "Cloud SDK uses the right project for all the commands in this notebook.\n",
-        "\n",
-        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "WReHDGG5g0XY"
-      },
-      "source": [
-        "#### Set your project ID\n",
-        "\n",
-        "**If you don't know your project ID**, you may be able to get your project ID using `gcloud`."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "oM1iC_MfAts1"
-      },
-      "outputs": [],
-      "source": [
-        "import os\n",
-        "\n",
-        "PROJECT_ID = \"\"\n",
-        "\n",
-        "# Get your Google Cloud project ID from gcloud\n",
-        "if not os.getenv(\"IS_TESTING\"):\n",
-        "    shell_output=!gcloud config list --format 'value(core.project)' 2>/dev/null\n",
-        "    PROJECT_ID = shell_output[0]\n",
-        "    print(\"Project ID: \", PROJECT_ID)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "qJYoRfYng0XZ"
-      },
-      "source": [
-        "Otherwise, set your project ID here."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "riG_qUokg0XZ"
-      },
-      "outputs": [],
-      "source": [
-        "if PROJECT_ID == \"\" or PROJECT_ID is None:\n",
-        "    PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "06571eb4063b"
-      },
-      "source": [
-        "#### Timestamp\n",
-        "\n",
-        "If you are in a live tutorial session, you might be using a shared test account or project. To avoid name collisions between users on resources created, you create a timestamp for each instance session, and append it onto the name of resources you create in this tutorial."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "697568e92bd6"
-      },
-      "outputs": [],
-      "source": [
-        "from datetime import datetime\n",
-        "\n",
-        "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "dr--iN2kAylZ"
-      },
-      "source": [
-        "### Authenticate your Google Cloud account\n",
-        "\n",
-        "**If you are using Google Cloud Notebooks**, your environment is already\n",
-        "authenticated. Skip this step."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "sBCra4QMA2wR"
-      },
-      "source": [
-        "**If you are using Colab**, run the cell below and follow the instructions\n",
-        "when prompted to authenticate your account via oAuth.\n",
-        "\n",
-        "**Otherwise**, follow these steps:\n",
-        "\n",
-        "1. In the Cloud Console, go to the [**Create service account key**\n",
-        "   page](https://console.cloud.google.com/apis/credentials/serviceaccountkey).\n",
-        "\n",
-        "2. Click **Create service account**.\n",
-        "\n",
-        "3. In the **Service account name** field, enter a name, and\n",
-        "   click **Create**.\n",
-        "\n",
-        "4. In the **Grant this service account access to project** section, click the **Role** drop-down list. Type \"Vertex AI\"\n",
-        "into the filter box, and select\n",
-        "   **Vertex AI Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
-        "\n",
-        "5. Click *Create*. A JSON file that contains your key downloads to your\n",
-        "local environment.\n",
-        "\n",
-        "6. Enter the path to your service account key as the\n",
-        "`GOOGLE_APPLICATION_CREDENTIALS` variable in the cell below and run the cell."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "PyQmSRbKA8r-"
-      },
-      "outputs": [],
-      "source": [
-        "import os\n",
-        "import sys\n",
-        "\n",
-        "# If you are running this notebook in Colab, run this cell and follow the\n",
-        "# instructions to authenticate your GCP account. This provides access to your\n",
-        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
-        "# requests.\n",
-        "\n",
-        "# If on Google Cloud Notebooks, then don't execute this code\n",
-        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\"):\n",
-        "    if \"google.colab\" in sys.modules:\n",
-        "        from google.colab import auth as google_auth\n",
-        "\n",
-        "        google_auth.authenticate_user()\n",
-        "\n",
-        "    # If you are running this notebook locally, replace the string below with the\n",
-        "    # path to your service account key and run this cell to authenticate your GCP\n",
-        "    # account.\n",
-        "    elif not os.getenv(\"IS_TESTING\"):\n",
-        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "XoEqT2Y4DJmf"
-      },
-      "source": [
-        "### Import libraries and define constants"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "Y9Uo3tifg1kx"
-      },
-      "source": [
-        "Import required libraries."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "pRUOFELefqf1"
-      },
-      "outputs": [],
-      "source": [
-        "import matplotlib.pyplot as plt\n",
-        "import pandas as pd\n",
-        "from google.cloud import aiplatform\n",
-        "from tensorflow.python.keras import Sequential, layers\n",
-        "from tensorflow.python.keras.utils import data_utils"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "xtXZWmYqJ1bh"
-      },
-      "source": [
-        "Define some constants"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "JIOrI-hoJ46P"
-      },
-      "outputs": [],
-      "source": [
-        "EXPERIMENT_NAME = \"\"  # @param {type:\"string\"}\n",
-        "REGION = \"[your-region]\"  # @param {type:\"string\"}"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "jWQLXXNVN4Lv"
-      },
-      "source": [
-        "If EXEPERIMENT_NAME is not set, set a default one below:"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "Q1QInYWOKsmo"
-      },
-      "outputs": [],
-      "source": [
-        "if EXPERIMENT_NAME == \"\" or EXPERIMENT_NAME is None:\n",
-        "    EXPERIMENT_NAME = \"my-experiment-\" + TIMESTAMP"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "Xuny18aMcWDb"
-      },
-      "source": [
-        "## Concepts\n",
-        "\n",
-        "To better understanding how parameters and metrics are stored and organized, we'd like to introduce the following concepts:\n"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "NThDci5bp0Uw"
-      },
-      "source": [
-        "### Experiment\n",
-        "Experiments describe a context that groups your runs and the artifacts you create into a logical session. For example, in this notebook you create an Experiment and log data to that experiment."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "SAyRR3Ydp4X5"
-      },
-      "source": [
-        "### Run\n",
-        "A run represents a single path/avenue that you executed while performing an experiment. A run includes artifacts that you used as inputs or outputs, and parameters that you used in this execution. An Experiment can contain multiple runs. "
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "l1YW2pgyegFP"
-      },
-      "source": [
-        "## Getting started tracking parameters and metrics\n",
-        "\n",
-        "You can use the Vertex SDK for Python to track metrics and parameters for models trained locally. \n",
-        "\n",
-        "In the following example, you train a simple distributed neural network (DNN) model to predict automobile's miles per gallon (MPG) based on automobile information in the [auto-mpg dataset](https://www.kaggle.com/devanshbesain/exploration-and-analysis-auto-mpg)."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "KPY41M9_AhZU"
-      },
-      "source": [
-        "### Load and process the training dataset"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "bfMQSmRuUuX-"
-      },
-      "source": [
-        "Download and process the dataset."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "RiQuMv4bmpuV"
-      },
-      "outputs": [],
-      "source": [
-        "def read_data(uri):\n",
-        "    dataset_path = data_utils.get_file(\"auto-mpg.data\", uri)\n",
-        "    column_names = [\n",
-        "        \"MPG\",\n",
-        "        \"Cylinders\",\n",
-        "        \"Displacement\",\n",
-        "        \"Horsepower\",\n",
-        "        \"Weight\",\n",
-        "        \"Acceleration\",\n",
-        "        \"Model Year\",\n",
-        "        \"Origin\",\n",
-        "    ]\n",
-        "    raw_dataset = pd.read_csv(\n",
-        "        dataset_path,\n",
-        "        names=column_names,\n",
-        "        na_values=\"?\",\n",
-        "        comment=\"\\t\",\n",
-        "        sep=\" \",\n",
-        "        skipinitialspace=True,\n",
-        "    )\n",
-        "    dataset = raw_dataset.dropna()\n",
-        "    dataset[\"Origin\"] = dataset[\"Origin\"].map(\n",
-        "        lambda x: {1: \"USA\", 2: \"Europe\", 3: \"Japan\"}.get(x)\n",
-        "    )\n",
-        "    dataset = pd.get_dummies(dataset, prefix=\"\", prefix_sep=\"\")\n",
-        "    return dataset\n",
-        "\n",
-        "\n",
-        "dataset = read_data(\n",
-        "    \"http://archive.ics.uci.edu/ml/machine-learning-databases/auto-mpg/auto-mpg.data\"\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "Y06J7A7yU21t"
-      },
-      "source": [
-        "Split dataset for training and testing."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "p5JBCBKyH-NC"
-      },
-      "outputs": [],
-      "source": [
-        "def train_test_split(dataset, split_frac=0.8, random_state=0):\n",
-        "    train_dataset = dataset.sample(frac=split_frac, random_state=random_state)\n",
-        "    test_dataset = dataset.drop(train_dataset.index)\n",
-        "    train_labels = train_dataset.pop(\"MPG\")\n",
-        "    test_labels = test_dataset.pop(\"MPG\")\n",
-        "\n",
-        "    return train_dataset, test_dataset, train_labels, test_labels\n",
-        "\n",
-        "\n",
-        "train_dataset, test_dataset, train_labels, test_labels = train_test_split(dataset)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "gaNNTFPaU7KT"
-      },
-      "source": [
-        "Normalize the features in the dataset for better model performance."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "VGq5QCoyIEWJ"
-      },
-      "outputs": [],
-      "source": [
-        "def normalize_dataset(train_dataset, test_dataset):\n",
-        "    train_stats = train_dataset.describe()\n",
-        "    train_stats = train_stats.transpose()\n",
-        "\n",
-        "    def norm(x):\n",
-        "        return (x - train_stats[\"mean\"]) / train_stats[\"std\"]\n",
-        "\n",
-        "    normed_train_data = norm(train_dataset)\n",
-        "    normed_test_data = norm(test_dataset)\n",
-        "\n",
-        "    return normed_train_data, normed_test_data\n",
-        "\n",
-        "\n",
-        "normed_train_data, normed_test_data = normalize_dataset(train_dataset, test_dataset)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "UBXUgxgqA_GB"
-      },
-      "source": [
-        "### Define ML model and training function"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "66odBYKrIN4q"
-      },
-      "outputs": [],
-      "source": [
-        "def train(\n",
-        "    train_data,\n",
-        "    train_labels,\n",
-        "    num_units=64,\n",
-        "    activation=\"relu\",\n",
-        "    dropout_rate=0.0,\n",
-        "    validation_split=0.2,\n",
-        "    epochs=1000,\n",
-        "):\n",
-        "\n",
-        "    model = Sequential(\n",
-        "        [\n",
-        "            layers.Dense(\n",
-        "                num_units,\n",
-        "                activation=activation,\n",
-        "                input_shape=[len(train_dataset.keys())],\n",
-        "            ),\n",
-        "            layers.Dropout(rate=dropout_rate),\n",
-        "            layers.Dense(num_units, activation=activation),\n",
-        "            layers.Dense(1),\n",
-        "        ]\n",
-        "    )\n",
-        "\n",
-        "    model.compile(loss=\"mse\", optimizer=\"adam\", metrics=[\"mae\", \"mse\"])\n",
-        "    print(model.summary())\n",
-        "\n",
-        "    history = model.fit(\n",
-        "        train_data, train_labels, epochs=epochs, validation_split=validation_split\n",
-        "    )\n",
-        "\n",
-        "    return model, history"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "O8XJZB3gR8eL"
-      },
-      "source": [
-        "### Initialize the Vertex AI SDK for Python and create an Experiment\n",
-        "\n",
-        "Initialize the *client* for Vertex AI and create an experiment."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "o_wnT10RJ7-W"
-      },
-      "outputs": [],
-      "source": [
-        "aiplatform.init(project=PROJECT_ID, location=REGION, experiment=EXPERIMENT_NAME)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "u-iTnzt3B6Z_"
-      },
-      "source": [
-        "### Start several model training runs\n",
-        "\n",
-        "Training parameters and metrics are logged for each run."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "i2wnpu8_7JfV"
-      },
-      "outputs": [],
-      "source": [
-        "parameters = [\n",
-        "    {\"num_units\": 16, \"epochs\": 3, \"dropout_rate\": 0.1},\n",
-        "    {\"num_units\": 16, \"epochs\": 10, \"dropout_rate\": 0.1},\n",
-        "    {\"num_units\": 16, \"epochs\": 10, \"dropout_rate\": 0.2},\n",
-        "    {\"num_units\": 32, \"epochs\": 10, \"dropout_rate\": 0.1},\n",
-        "    {\"num_units\": 32, \"epochs\": 10, \"dropout_rate\": 0.2},\n",
-        "]\n",
-        "\n",
-        "for i, params in enumerate(parameters):\n",
-        "    aiplatform.start_run(run=f\"auto-mpg-local-run-{i}\")\n",
-        "    aiplatform.log_params(params)\n",
-        "    model, history = train(\n",
-        "        normed_train_data,\n",
-        "        train_labels,\n",
-        "        num_units=params[\"num_units\"],\n",
-        "        activation=\"relu\",\n",
-        "        epochs=params[\"epochs\"],\n",
-        "        dropout_rate=params[\"dropout_rate\"],\n",
-        "    )\n",
-        "    aiplatform.log_metrics(\n",
-        "        {metric: values[-1] for metric, values in history.history.items()}\n",
-        "    )\n",
-        "\n",
-        "    loss, mae, mse = model.evaluate(normed_test_data, test_labels, verbose=2)\n",
-        "    aiplatform.log_metrics({\"eval_loss\": loss, \"eval_mae\": mae, \"eval_mse\": mse})"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "jZLrJZTfL7tE"
-      },
-      "source": [
-        "### Extract parameters and metrics into a dataframe for analysis"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "A1PqKxlpOZa2"
-      },
-      "source": [
-        "We can also extract all parameters and metrics associated with any Experiment into a dataframe for further analysis."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "jbRf1WoH_vbY"
-      },
-      "outputs": [],
-      "source": [
-        "experiment_df = aiplatform.get_experiment_df()\n",
-        "experiment_df"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "EYuYgqVCMKU1"
-      },
-      "source": [
-        "### Visualizing an experiment's parameters and metrics"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "r8orCj8iJuO1"
-      },
-      "outputs": [],
-      "source": [
-        "plt.rcParams[\"figure.figsize\"] = [15, 5]\n",
-        "\n",
-        "ax = pd.plotting.parallel_coordinates(\n",
-        "    experiment_df.reset_index(level=0),\n",
-        "    \"run_name\",\n",
-        "    cols=[\n",
-        "        \"param.num_units\",\n",
-        "        \"param.dropout_rate\",\n",
-        "        \"param.epochs\",\n",
-        "        \"metric.loss\",\n",
-        "        \"metric.val_loss\",\n",
-        "        \"metric.eval_loss\",\n",
-        "    ],\n",
-        "    color=[\"blue\", \"green\", \"pink\", \"red\"],\n",
-        ")\n",
-        "ax.set_yscale(\"symlog\")\n",
-        "ax.legend(bbox_to_anchor=(1.0, 0.5))"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "WTHvPMweMlP1"
-      },
-      "source": [
-        "## Visualizing experiments in Cloud Console"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "F19_5lw0MqXv"
-      },
-      "source": [
-        "Run the following to get the URL of Vertex AI Experiments for your project.\n"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "GmN9vE9pqqzt"
-      },
-      "outputs": [],
-      "source": [
-        "print(\"Vertex AI Experiments:\")\n",
-        "print(\n",
-        "    f\"https://console.cloud.google.com/ai/platform/experiments/experiments?folder=&organizationId=&project={PROJECT_ID}\"\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "TpV-iwP9qw9c"
-      },
-      "source": [
-        "## Cleaning up\n",
-        "\n",
-        "To clean up all Google Cloud resources used in this project, you can [delete the Google Cloud\n",
-        "project](https://cloud.google.com/resource-manager/docs/creating-managing-projects#shutting_down_projects) you used for the tutorial."
-      ]
-    }
-  ],
-  "metadata": {
-    "colab": {
-      "collapsed_sections": [],
-      "name": "sdk-metric-parameter-tracking-for-locally-trained-models.ipynb",
-      "toc_visible": true
-    },
-    "kernelspec": {
-      "display_name": "Python 3",
-      "name": "python3"
-    }
-  },
-  "nbformat": 4,
-  "nbformat_minor": 0
-}

notebooks/community/ml_ops/stage1/README.md

@@ -22,7 +22,7 @@ The first stage in MLOps is the collection and preparation for the purpose of de
 - Data is preprocessed for training and evaluation using Dataflow.
 - Data augmentation is performed on-the-fly and is coupled with model feeding.
 
-<img src='stage1.jpg'>
+<img src='stage1v2.png'>
 
 ## Notebooks
 
@@ -76,7 +76,7 @@ The steps performed include:
     - image data
 ```
 
-[Get Started with Data Labeling](get_started_data_labeling.ipynb)
+[Get Started with Data Labeling](get_started_with_data_labeling.ipynb)
 
 ```
 The steps performed include:

notebooks/community/ml_ops/stage1/get_started_bq_datasets.ipynb

@@ -34,12 +34,16 @@
         "<table align=\"left\">\n",
         "  <td>\n",
         "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage1/get_started_bq_datasets.ipynb\">\n",
-        "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"GitHub logo\">\n",
         "      View on GitHub\n",
         "    </a>\n",
+        "  <td>\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage1/get_started_bq_datasets.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage1/get_started_bq_datasets.ipynb\">\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/ml_ops/stage1/get_started_bq_datasets.ipynb\">\n",
         "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
         "      Open in Vertex AI Workbench\n",
         "    </a>\n",
@@ -169,20 +173,24 @@
       "source": [
         "import os\n",
         "\n",
-        "# The Google Cloud Notebook product has specific requirements\n",
-        "IS_GOOGLE_CLOUD_NOTEBOOK = os.path.exists(\"/opt/deeplearning/metadata/env_version\")\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\") and not os.getenv(\"VIRTUAL_ENV\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
         "\n",
-        "# Google Cloud Notebook requires dependencies to be installed with '--user'\n",
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
         "USER_FLAG = \"\"\n",
-        "if IS_GOOGLE_CLOUD_NOTEBOOK:\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
         "    USER_FLAG = \"--user\"\n",
         "\n",
         "# Install the packages\n",
-        "! pip3 install --upgrade pyarrow $USER_FLAG\n",
-        "! pip3 install --upgrade google-cloud-bigquery $USER_FLAG\n",
-        "! pip3 install --upgrade google-cloud-aiplatform[tensorboard] $USER_FLAG\n",
-        "! pip3 install -U xgboost $USER_FLAG\n",
-        "! pip3 install -U tensorflow-io==0.18 $USER_FLAG"
+        "! pip3 install --upgrade pyarrow $USER_FLAG -q\n",
+        "! pip3 install --upgrade google-cloud-bigquery $USER_FLAG -q\n",
+        "! pip3 install --upgrade google-cloud-aiplatform $USER_FLAG -q\n",
+        "! pip3 install -U xgboost $USER_FLAG -q\n",
+        "! pip3 install -U tensorflow $USER_FLAG -q\n",
+        "! pip3 install -U tensorflow-io==0.18 $USER_FLAG -q"
       ]
     },
     {
@@ -214,21 +222,14 @@
         "    app.kernel.do_shutdown(True)"
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "a47846030fef"
-      },
-      "source": [
-        "## Before you begin"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
         "id": "84cd83853240"
       },
       "source": [
+        "## Before you begin\n",
+        "\n",
         "### Set up your Google Cloud project\n",
         "\n",
         "**The following steps are required, regardless of your notebook environment.**\n",
@@ -237,7 +238,7 @@
         "\n",
         "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
         "\n",
-        "1. [Enable the Vertex AI API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com). {TODO: Update the APIs needed for your tutorial. Edit the API names, and update the link to append the API IDs, separating each one with a comma. For example, container.googleapis.com,cloudbuild.googleapis.com}\n",
+        "1. [Enable the Vertex AI, BigQuery, Compute Engine and Cloud Storage APIs](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,bigquery,compute_component,storage_component).\n",
         "\n",
         "1. If you are running this notebook locally, you need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
         "\n",
@@ -353,6 +354,67 @@
         "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "77c385f0db59"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already authenticated. Skip this step.\n",
+        "\n",
+        "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\n",
+        "\n",
+        "1. **Click Create service account**.\n",
+        "\n",
+        "2. In the **Service account name** field, enter a name, and click **Create**.\n",
+        "\n",
+        "3. In the **Grant this service account access to project** section, click the Role drop-down list. Type \"Vertex AI\" into the filter box, and select **Vertex AI Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "4. Click Create. A JSON file that contains your key downloads to your local environment.\n",
+        "\n",
+        "5. Enter the path to your service account key as the GOOGLE_APPLICATION_CREDENTIALS variable in the cell below and run the cell."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "535223fa4b84"
+      },
+      "outputs": [],
+      "source": [
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
+        "IS_COLAB = False\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
+        "    \"DL_ANACONDA_HOME\"\n",
+        "):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        IS_COLAB = True\n",
+        "        from google.colab import auth as google_auth\n",
+        "\n",
+        "        google_auth.authenticate_user()\n",
+        "\n",
+        "    # If you are running this notebook locally, replace the string below with the\n",
+        "    # path to your service account key and run this cell to authenticate your GCP\n",
+        "    # account.\n",
+        "    elif not os.getenv(\"IS_TESTING\"):\n",
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -376,7 +438,8 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_URI = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
+        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
+        "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
       ]
     },
     {
@@ -388,7 +451,8 @@
       "outputs": [],
       "source": [
         "if BUCKET_URI == \"\" or BUCKET_URI is None or BUCKET_URI == \"gs://[your-bucket-name]\":\n",
-        "    BUCKET_URI = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
+        "    BUCKET_NAME = PROJECT_ID + \"aip-\" + TIMESTAMP\n",
+        "    BUCKET_URI = \"gs://\" + BUCKET_NAME"
       ]
     },
     {
@@ -1068,7 +1132,7 @@
       "source": [
         "dataframe[\"station_number\"] = pd.to_numeric(dataframe[\"station_number\"])\n",
         "labels = dataframe[\"mean_temp\"]\n",
-        "data = dataframe.drop(4)\n",
+        "data = dataframe.drop([\"mean_temp\"], axis=1)\n",
         "\n",
         "dtrain = xgb.DMatrix(data, label=labels)"
       ]
@@ -1112,7 +1176,9 @@
         "\n",
         "- Vertex AI Dataset resource\n",
         "- Cloud Storage Bucket\n",
-        "- BigQuery Dataset"
+        "- BigQuery Dataset\n",
+        "\n",
+        "Set `delete_storage` to _True_ to delete the storage resources used in this notebook."
       ]
     },
     {
@@ -1128,12 +1194,15 @@
         "# Delete the dataset using the Vertex dataset object\n",
         "dataset.delete()\n",
         "\n",
-        "if os.getenv(\"IS_TESTING\"):\n",
+        "# Delete the temporary BigQuery dataset\n",
+        "! bq rm -r -f $PROJECT_ID:$DATASET_ID\n",
+        "\n",
+        "delete_storage = False\n",
+        "if delete_storage or os.getenv(\"IS_TESTING\"):\n",
         "    # Delete the created GCS bucket\n",
         "    ! gsutil rm -r $BUCKET_URI\n",
         "    # Delete the created BigQuery datasets\n",
-        "    ! bq rm -r -f $PROJECT_ID:$BQ_MY_DATASET\n",
-        "    ! bq rm -r -f $PROJECT_ID:$DATASET_ID"
+        "    ! bq rm -r -f $PROJECT_ID:$BQ_MY_DATASET"
       ]
     }
   ],

notebooks/community/ml_ops/stage1/get_started_dataflow.ipynb

@@ -39,8 +39,14 @@
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://console.cloud.google.com/ai/platform/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage1/get_started_dataflow.ipynb\">\n",
-        "      Open in Google Cloud Notebooks\n",
+        "        <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage1/get_started_dataflow.ipynb\">\n",
+        "        <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\\\" alt=\"Colab logo\"> Run in Colab\n",
+        "        </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage1/get_started_dataflow.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "      Open in Vertex AI Workbench\n",
         "    </a>\n",
         "  </td>\n",
         "</table>\n",
@@ -139,7 +145,7 @@
       "source": [
         "## Installations\n",
         "\n",
-        "Install *one time* the packages for executing the MLOps notebooks."
+        "Install the following packages to execute this notebook."
       ]
     },
     {
@@ -150,20 +156,26 @@
       },
       "outputs": [],
       "source": [
-        "ONCE_ONLY = False\n",
-        "if ONCE_ONLY:\n",
-        "    ! pip3 install -U tensorflow==2.5 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-data-validation==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-transform==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-io==0.18 $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-aiplatform[tensorboard] $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-pipeline-components $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-bigquery $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-logging $USER_FLAG\n",
-        "    ! pip3 install --upgrade apache-beam[gcp] $USER_FLAG\n",
-        "    ! pip3 install --upgrade pyarrow $USER_FLAG\n",
-        "    ! pip3 install --upgrade cloudml-hypertune $USER_FLAG\n",
-        "    ! pip3 install --upgrade kfp $USER_FLAG"
+        "import os\n",
+        "\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\") and not os.getenv(\"VIRTUAL_ENV\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
+        "\n",
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
+        "USER_FLAG = \"\"\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "\n",
+        "! pip3 install -U tensorflow==2.5 $USER_FLAG -q\n",
+        "! pip3 install -U tensorflow-data-validation==1.2 $USER_FLAG -q\n",
+        "! pip3 install -U tensorflow-transform==1.2 $USER_FLAG -q\n",
+        "! pip3 install -U tensorflow-io==0.18 $USER_FLAG -q\n",
+        "! pip3 install --upgrade google-cloud-aiplatform $USER_FLAG -q\n",
+        "! pip3 install --upgrade google-cloud-bigquery $USER_FLAG -q\n",
+        "! pip3 install --upgrade apache-beam[gcp] $USER_FLAG -q"
       ]
     },
     {
@@ -195,6 +207,32 @@
         "    app.kernel.do_shutdown(True)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "84cd83853240"
+      },
+      "source": [
+        "## Before you begin\n",
+        "\n",
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI, BigQuery, Compute Engine and Cloud Storage APIs](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,bigquery,compute_component,storage_component).\n",
+        "\n",
+        "1. If you are running this notebook locally, you need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+        "\n",
+        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -271,7 +309,10 @@
       },
       "outputs": [],
       "source": [
-        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
+        "\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
       ]
     },
     {
@@ -298,6 +339,67 @@
         "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "77c385f0db59"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already authenticated. Skip this step.\n",
+        "\n",
+        "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\n",
+        "\n",
+        "1. **Click Create service account**.\n",
+        "\n",
+        "2. In the **Service account name** field, enter a name, and click **Create**.\n",
+        "\n",
+        "3. In the **Grant this service account access to project** section, click the Role drop-down list. Type \"Vertex AI\" into the filter box, and select **Vertex AI Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "4. Click Create. A JSON file that contains your key downloads to your local environment.\n",
+        "\n",
+        "5. Enter the path to your service account key as the GOOGLE_APPLICATION_CREDENTIALS variable in the cell below and run the cell."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "535223fa4b84"
+      },
+      "outputs": [],
+      "source": [
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
+        "IS_COLAB = False\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
+        "    \"DL_ANACONDA_HOME\"\n",
+        "):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        IS_COLAB = True\n",
+        "        from google.colab import auth as google_auth\n",
+        "\n",
+        "        google_auth.authenticate_user()\n",
+        "\n",
+        "    # If you are running this notebook locally, replace the string below with the\n",
+        "    # path to your service account key and run this cell to authenticate your GCP\n",
+        "    # account.\n",
+        "    elif not os.getenv(\"IS_TESTING\"):\n",
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -326,7 +428,8 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
+        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
+        "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
       ]
     },
     {
@@ -337,8 +440,9 @@
       },
       "outputs": [],
       "source": [
-        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"gs://[your-bucket-name]\":\n",
-        "    BUCKET_NAME = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
+        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"[your-bucket-name]\":\n",
+        "    BUCKET_NAME = PROJECT_ID + \"aip-\" + TIMESTAMP\n",
+        "    BUCKET_URI = \"gs://\" + BUCKET_NAME"
       ]
     },
     {
@@ -358,7 +462,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION $BUCKET_NAME"
+        "! gsutil mb -l $REGION $BUCKET_URI"
       ]
     },
     {
@@ -378,7 +482,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil ls -al $BUCKET_NAME"
+        "! gsutil ls -al $BUCKET_URI"
       ]
     },
     {
@@ -401,7 +505,7 @@
       },
       "outputs": [],
       "source": [
-        "import google.cloud.aiplatform as aip"
+        "import google.cloud.aiplatform as aiplatform"
       ]
     },
     {
@@ -555,7 +659,7 @@
       },
       "outputs": [],
       "source": [
-        "aip.init(project=PROJECT_ID, location=REGION)"
+        "aiplatform.init(project=PROJECT_ID, location=REGION)"
       ]
     },
     {
@@ -1004,7 +1108,7 @@
       },
       "outputs": [],
       "source": [
-        "SCHEMA_LOCATION = BUCKET_NAME + \"/schema.txt\"\n",
+        "SCHEMA_LOCATION = BUCKET_URI + \"/schema.txt\"\n",
         "\n",
         "# When running Apache Beam directly (file is directly accessed)\n",
         "tfdv.write_schema_text(output_path=SCHEMA_LOCATION, schema=schema)\n",
@@ -1149,7 +1253,7 @@
         "            )\n",
         "\n",
         "\n",
-        "EXPORTED_DATA_PREFIX = os.path.join(BUCKET_NAME, \"exported_data\")\n",
+        "EXPORTED_DATA_PREFIX = os.path.join(BUCKET_URI, \"exported_data\")\n",
         "\n",
         "QUERY_STRING = \"SELECT {},{} FROM {} LIMIT 500\".format(\n",
         "    \"CAST(station_number as STRING) AS station_number,year,month,day\",\n",
@@ -1162,7 +1266,7 @@
         "    \"runner\": RUNNER,\n",
         "    \"raw_data_query\": QUERY_STRING,\n",
         "    \"exported_data_prefix\": EXPORTED_DATA_PREFIX,\n",
-        "    \"temp_location\": os.path.join(BUCKET_NAME, \"temp\"),\n",
+        "    \"temp_location\": os.path.join(BUCKET_URI, \"temp\"),\n",
         "    \"project\": PROJECT_ID,\n",
         "    \"region\": REGION,\n",
         "    \"setup_file\": \"./setup.py\",\n",
@@ -1187,17 +1291,7 @@
         "To clean up all Google Cloud resources used in this project, you can [delete the Google Cloud\n",
         "project](https://cloud.google.com/resource-manager/docs/creating-managing-projects#shutting_down_projects) you used for the tutorial.\n",
         "\n",
-        "Otherwise, you can delete the individual resources you created in this tutorial:\n",
-        "\n",
-        "- Dataset\n",
-        "- Pipeline\n",
-        "- Model\n",
-        "- Endpoint\n",
-        "- AutoML Training Job\n",
-        "- Batch Job\n",
-        "- Custom Job\n",
-        "- Hyperparameter Tuning Job\n",
-        "- Cloud Storage Bucket"
+        "Otherwise, you can delete the individual resources you created in this tutorial."
       ]
     },
     {
@@ -1208,61 +1302,11 @@
       },
       "outputs": [],
       "source": [
-        "delete_all = True\n",
+        "delete_storage = True\n",
         "\n",
-        "if delete_all:\n",
-        "    # Delete the dataset using the Vertex dataset object\n",
-        "    try:\n",
-        "        if \"dataset\" in globals():\n",
-        "            dataset.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the model using the Vertex model object\n",
-        "    try:\n",
-        "        if \"model\" in globals():\n",
-        "            model.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the endpoint using the Vertex endpoint object\n",
-        "    try:\n",
-        "        if \"endpoint\" in globals():\n",
-        "            endpoint.undeploy_all()\n",
-        "            endpoint.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the AutoML or Pipeline training job\n",
-        "    try:\n",
-        "        if \"dag\" in globals():\n",
-        "            dag.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the custom training job\n",
-        "    try:\n",
-        "        if \"job\" in globals():\n",
-        "            job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the batch prediction job using the Vertex batch prediction object\n",
-        "    try:\n",
-        "        if \"batch_predict_job\" in globals():\n",
-        "            batch_predict_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the hyperparameter tuning job using the Vertex hyperparameter tuning object\n",
-        "    try:\n",
-        "        if \"hpt_job\" in globals():\n",
-        "            hpt_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    if \"BUCKET_NAME\" in globals():\n",
-        "        ! gsutil rm -r $BUCKET_NAME"
+        "if delete_storage or os.getenv(\"IS_TESTING\"):\n",
+        "    if \"BUCKET_URI\" in globals():\n",
+        "        ! gsutil rm -r $BUCKET_URI"
       ]
     }
   ],

notebooks/community/ml_ops/stage1/get_started_vertex_datasets.ipynb

@@ -8,7 +8,7 @@
       },
       "outputs": [],
       "source": [
-        "# Copyright 2021 Google LLC\n",
+        "# Copyright 2022 Google LLC\n",
         "#\n",
         "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
         "# you may not use this file except in compliance with the License.\n",
@@ -34,15 +34,21 @@
         "<table align=\"left\">\n",
         "  <td>\n",
         "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage1/get_started_vertex_datasets.ipynb\">\n",
-        "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
-        "      View on GitHub\n",
+        "     <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
         "    <a href=\"https://console.cloud.google.com/ai/platform/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage1/get_started_vertex_datasets.ipynb\">\n",
-        "      Open in Google Cloud Notebooks\n",
+        "<img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
+        "      View on GitHub\n",
         "    </a>\n",
         "  </td>\n",
+        "   <td>\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/ml_ops/stage1/get_started_vertex_datasets.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "      Open in Vertex AI Workbench\n",
+        "    </a>\n",
+        "  </td>   \n",
         "</table>\n",
         "<br/><br/><br/>"
       ]
@@ -130,7 +136,17 @@
         "            - Create a tf.data.Dataset generator from the CSV index file.\n",
         "        - If text strings are in text files:\n",
         "            - Using the JSON index file, convert the text files and labels to TFRecords.\n",
-        "            - Create a tf.data.Dataset from the TFRecords."
+        "            - Create a tf.data.Dataset from the TFRecords.\n",
+        "\n",
+        "    \n",
+        "### Costs\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "- Vertex AI\n",
+        "- Cloud Storage\n",
+        "- BigQuery\n",
+        "\n",
+        "Learn about [Vertex AI pricing](https://cloud.google.com/vertex-ai/pricing), [Cloud Storage pricing](https://cloud.google.com/storage/pricing) and [BigQuery pricing](https://cloud.google.com/bigquery/pricing) and use the [Pricing Calculator](https://cloud.google.com/products/calculator/) to generate a cost estimate based on your projected usage."
       ]
     },
     {
@@ -141,7 +157,7 @@
       "source": [
         "## Installations\n",
         "\n",
-        "Install *one time* the packages for executing the MLOps notebooks."
+        "Install the packages required for executing this notebook."
       ]
     },
     {
@@ -152,20 +168,27 @@
       },
       "outputs": [],
       "source": [
-        "ONCE_ONLY = False\n",
-        "if ONCE_ONLY:\n",
-        "    ! pip3 install -U tensorflow==2.5 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-data-validation==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-transform==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-io==0.18 $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-aiplatform[tensorboard] $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-pipeline-components $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-bigquery $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-logging $USER_FLAG\n",
-        "    ! pip3 install --upgrade apache-beam[gcp] $USER_FLAG\n",
-        "    ! pip3 install --upgrade pyarrow $USER_FLAG\n",
-        "    ! pip3 install --upgrade cloudml-hypertune $USER_FLAG\n",
-        "    ! pip3 install --upgrade kfp $USER_FLAG"
+        "import os\n",
+        "\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\") and not os.getenv(\"VIRTUAL_ENV\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
+        "\n",
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
+        "USER_FLAG = \"\"\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "\n",
+        "! pip3 install -U tensorflow $USER_FLAG -q\n",
+        "! pip3 install -U tensorflow-data-validation $USER_FLAG -q\n",
+        "! pip3 install -U tensorflow-transform $USER_FLAG -q\n",
+        "! pip3 install -U tensorflow-io $USER_FLAG -q\n",
+        "! pip3 install --upgrade google-cloud-aiplatform $USER_FLAG -q\n",
+        "! pip3 install --upgrade google-cloud-bigquery $USER_FLAG -q\n",
+        "! pip3 install -U tensorflow-io==0.18 $USER_FLAG -q\n",
+        "! pip3 install --upgrade db-dtypes $USER_FLAG -q! pip3 install --upgrade future $USER_FLAG -q"
       ]
     },
     {
@@ -197,6 +220,30 @@
         "    app.kernel.do_shutdown(True)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "cb082379ed5b"
+      },
+      "source": [
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com). \n",
+        "\n",
+        "1. If you are running this notebook locally, you need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+        "\n",
+        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -216,7 +263,24 @@
       },
       "outputs": [],
       "source": [
-        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
+        "import os\n",
+        "\n",
+        "PROJECT_ID = \"\"\n",
+        "\n",
+        "if not os.getenv(\"IS_TESTING\"):\n",
+        "    # Get your Google Cloud project ID from gcloud\n",
+        "    shell_output = !gcloud config list --format 'value(core.project)' 2>/dev/null\n",
+        "    PROJECT_ID = shell_output[0]\n",
+        "    print(\"Project ID: \", PROJECT_ID)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "37c0a68ff20d"
+      },
+      "source": [
+        "Otherwise, set your project ID here."
       ]
     },
     {
@@ -227,18 +291,15 @@
       },
       "outputs": [],
       "source": [
-        "if PROJECT_ID == \"\" or PROJECT_ID is None or PROJECT_ID == \"[your-project-id]\":\n",
-        "    # Get your GCP project id from gcloud\n",
-        "    shell_output = ! gcloud config list --format 'value(core.project)' 2>/dev/null\n",
-        "    PROJECT_ID = shell_output[0]\n",
-        "    print(\"Project ID:\", PROJECT_ID)"
+        "if PROJECT_ID == \"\" or PROJECT_ID is None:\n",
+        "    PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "set_gcloud_project_id"
+        "id": "c021ca495967"
       },
       "outputs": [],
       "source": [
@@ -273,7 +334,10 @@
       },
       "outputs": [],
       "source": [
-        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
+        "\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
       ]
     },
     {
@@ -300,6 +364,66 @@
         "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "927085b84a07"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already authenticated. Skip this step.\n",
+        "\n",
+        "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\n",
+        "\n",
+        "**Click Create service account**.\n",
+        "\n",
+        "In the **Service account name** field, enter a name, and click **Create**.\n",
+        "\n",
+        "In the **Grant this service account access to project** section, click the Role drop-down list. Type \"Vertex\" into the filter box, and select **Vertex Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "Click Create. A JSON file that contains your key downloads to your local environment.\n",
+        "\n",
+        "Enter the path to your service account key as the GOOGLE_APPLICATION_CREDENTIALS variable in the cell below and run the cell."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "89788a802687"
+      },
+      "outputs": [],
+      "source": [
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
+        "IS_COLAB = \"google.colab\" in sys.modules\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
+        "    \"DL_ANACONDA_HOME\"\n",
+        "):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        from google.colab import auth as google_auth\n",
+        "\n",
+        "        google_auth.authenticate_user()\n",
+        "\n",
+        "    # If you are running this notebook locally, replace the string below with the\n",
+        "    # path to your service account key and run this cell to authenticate your GCP\n",
+        "    # account.\n",
+        "    elif not os.getenv(\"IS_TESTING\"):\n",
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -328,7 +452,7 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
+        "BUCKET_URI = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
       ]
     },
     {
@@ -339,8 +463,8 @@
       },
       "outputs": [],
       "source": [
-        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"gs://[your-bucket-name]\":\n",
-        "    BUCKET_NAME = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
+        "if BUCKET_URI == \"\" or BUCKET_URI is None or BUCKET_URI == \"gs://[your-bucket-name]\":\n",
+        "    BUCKET_URI = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
       ]
     },
     {
@@ -360,7 +484,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION $BUCKET_NAME"
+        "! gsutil mb -l $REGION $BUCKET_URI"
       ]
     },
     {
@@ -380,7 +504,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil ls -al $BUCKET_NAME"
+        "! gsutil ls -al $BUCKET_URI"
       ]
     },
     {
@@ -392,7 +516,11 @@
         "### Set up variables\n",
         "\n",
         "Next, set up some variables used throughout the tutorial.\n",
-        "### Import libraries and define constants"
+        "### Import libraries and define constants\n",
+        "\n",
+        "Import the BigQuery package, TensorFlow Data Validation (TFDV) package and TensorFlow Data Validation package into your Python environment. \n",
+        "\n",
+        "Import TensorFlow Transform (TFT) package and pandas into your Python environment."
       ]
     },
     {
@@ -403,97 +531,13 @@
       },
       "outputs": [],
       "source": [
-        "import google.cloud.aiplatform as aip"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "import_bq"
-      },
-      "source": [
-        "#### Import BigQuery\n",
-        "\n",
-        "Import the BigQuery package into your Python environment."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "import_bq"
-      },
-      "outputs": [],
-      "source": [
+        "import google.cloud.aiplatform as aip\n",
+        "import pandas as pd\n",
+        "import tensorflow_data_validation as tfdv\n",
+        "import tensorflow_transform as tft\n",
         "from google.cloud import bigquery"
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "import_tfdv"
-      },
-      "source": [
-        "#### Import TensorFlow Data Validation\n",
-        "\n",
-        "Import the TensorFlow Data Validation (TFDV) package into your Python environment."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "import_tfdv"
-      },
-      "outputs": [],
-      "source": [
-        "import tensorflow_data_validation as tfdv"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "import_tft"
-      },
-      "source": [
-        "#### Import TensorFlow Transform\n",
-        "\n",
-        "Import the TensorFlow Transform (TFT) package into your Python environment."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "import_tft"
-      },
-      "outputs": [],
-      "source": [
-        "import tensorflow_transform as tft"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "import_pandas"
-      },
-      "source": [
-        "#### Import pandas\n",
-        "\n",
-        "Import the pandas package into your Python environment."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "import_pandas"
-      },
-      "outputs": [],
-      "source": [
-        "import pandas as pd"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -513,7 +557,7 @@
       },
       "outputs": [],
       "source": [
-        "aip.init(project=PROJECT_ID, location=REGION)"
+        "aip.init(project=PROJECT_ID, location=REGION, staging_bucket=BUCKET_URI)"
       ]
     },
     {
@@ -567,26 +611,13 @@
         "Learn more about [All dataset documentation](https://cloud.google.com/vertex-ai/docs/datasets/datasets)"
       ]
     },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "import_file:flowers,csv,icn"
-      },
-      "outputs": [],
-      "source": [
-        "IMPORT_FILE = (\n",
-        "    \"gs://cloud-samples-data/vision/automl_classification/flowers/all_data_v2.csv\"\n",
-        ")"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
         "id": "create_dataset:image,icn"
       },
       "source": [
-        "### Create the Dataset\n",
+        "### Create an Image Dataset\n",
         "\n",
         "Next, create the `Dataset` resource using the `create` method for the `ImageDataset` class, which takes the following parameters:\n",
         "\n",
@@ -601,6 +632,19 @@
         "Learn more about [ImageDataset](https://cloud.google.com/vertex-ai/docs/datasets/prepare-image)."
       ]
     },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "import_file:flowers,csv,icn"
+      },
+      "outputs": [],
+      "source": [
+        "IMPORT_FILE = (\n",
+        "    \"gs://cloud-samples-data/vision/automl_classification/flowers/all_data_v2.csv\"\n",
+        ")"
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -618,24 +662,13 @@
         "print(dataset.resource_name)"
       ]
     },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "import_file:hmdb,csv,vcn"
-      },
-      "outputs": [],
-      "source": [
-        "IMPORT_FILE = \"gs://automl-video-demo-data/hmdb_split1_5classes_train_inf.csv\""
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
         "id": "create_dataset:video,vcn"
       },
       "source": [
-        "### Create the Dataset\n",
+        "### Create a Video Dataset\n",
         "\n",
         "Next, create the `Dataset` resource using the `create` method for the `VideoDataset` class, which takes the following parameters:\n",
         "\n",
@@ -649,6 +682,17 @@
         "Learn more about [VideoDataset](https://cloud.google.com/vertex-ai/docs/datasets/prepare-video)."
       ]
     },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "import_file:hmdb,csv,vcn"
+      },
+      "outputs": [],
+      "source": [
+        "IMPORT_FILE = \"gs://automl-video-demo-data/hmdb_split1_5classes_train_inf.csv\""
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -666,24 +710,13 @@
         "print(dataset.resource_name)"
       ]
     },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "import_file:happydb,csv,tcn"
-      },
-      "outputs": [],
-      "source": [
-        "IMPORT_FILE = \"gs://cloud-ml-data/NL-classification/happiness.csv\""
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
         "id": "create_dataset:text,tcn"
       },
       "source": [
-        "### Create the Dataset\n",
+        "### Create a Text Dataset\n",
         "\n",
         "Next, create the `Dataset` resource using the `create` method for the `TextDataset` class, which takes the following parameters:\n",
         "\n",
@@ -698,6 +731,17 @@
         "Learn more about [TextDataset](https://cloud.google.com/vertex-ai/docs/datasets/prepare-text)."
       ]
     },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "import_file:happydb,csv,tcn"
+      },
+      "outputs": [],
+      "source": [
+        "IMPORT_FILE = \"gs://cloud-ml-data/NL-classification/happiness.csv\""
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -715,6 +759,24 @@
         "print(dataset.resource_name)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "create_dataset:tabular,bq,lrg,v2"
+      },
+      "source": [
+        "### Create a Tabular Dataset\n",
+        "\n",
+        "#### CSV input data\n",
+        "\n",
+        "Next, create the `Dataset` resource using the `create` method for the `TabularDataset` class for CSV input data, which takes the following parameters:\n",
+        "\n",
+        "- `display_name`: The human readable name for the `Dataset` resource.\n",
+        "- `gcs_source`: A list of one or more dataset index files to import the data items into the `Dataset` resource.\n",
+        "\n",
+        "Learn more about [TabularDataset from CSV files](https://cloud.google.com/vertex-ai/docs/datasets/create-dataset-api#aiplatform_create_dataset_tabular_gcs_sample-python)"
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -723,27 +785,50 @@
       },
       "outputs": [],
       "source": [
-        "IMPORT_FILE = \"bq://bigquery-public-data.samples.gsod\"\n",
-        "BQ_TABLE = \"bigquery-public-data.samples.gsod\""
+        "IMPORT_FILE = \"gs://cloud-samples-data/tables/iris_1000.csv\""
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "create_dataset:tabular,bq,lrg,v2"
+      },
+      "outputs": [],
+      "source": [
+        "dataset = aip.TabularDataset.create(\n",
+        "    display_name=\"example\" + \"_\" + TIMESTAMP, gcs_source=[IMPORT_FILE]\n",
+        ")\n",
+        "\n",
+        "print(dataset.resource_name)"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "create_dataset:tabular,bq,lrg,v2"
+        "id": "854dd1e0195c"
       },
       "source": [
-        "### Create the Dataset\n",
+        "#### BigQuery input data\n",
         "\n",
-        "#### CSV input data\n",
-        "\n",
-        "Next, create the `Dataset` resource using the `create` method for the `TabularDataset` class, which takes the following parameters:\n",
+        "Next, create the `Dataset` resource using the `create` method for the `TabularDataset` class for BigQuery table input, which takes the following parameters:\n",
         "\n",
         "- `display_name`: The human readable name for the `Dataset` resource.\n",
-        "- `gcs_source`: A list of one or more dataset index files to import the data items into the `Dataset` resource.\n",
-        "- `labels`: User defined metadata. In this example, you store the location of the Cloud Storage bucket containing the user defined data.\n",
+        "- `bq_source`: A list of one or more BigQuery tables to import the data items into the `Dataset` resource.\n",
         "\n",
-        "Learn more about [TabularDataset from CSV files](https://cloud.google.com/vertex-ai/docs/datasets/create-dataset-api#aiplatform_create_dataset_tabular_gcs_sample-python)"
+        "Learn more about [TabularDataset from BigQuery table](https://cloud.google.com/vertex-ai/docs/datasets/create-dataset-api#aiplatform_create_dataset_tabular_bigquery_sample-pythonn)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "86343c146300"
+      },
+      "outputs": [],
+      "source": [
+        "IMPORT_FILE = \"bq://bigquery-public-data.samples.gsod\"\n",
+        "BQ_TABLE = \"bigquery-public-data.samples.gsod\""
       ]
     },
     {
@@ -761,15 +846,63 @@
         "print(dataset.resource_name)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "82e9fe20ce71"
+      },
+      "source": [
+        "#### Dataframe input data\n",
+        "\n",
+        "Next, create the `Dataset` resource using the `create_from_dataframe` method for the `TabularDataset` class for pandas dataframe input, which takes the following parameters:\n",
+        "\n",
+        "- `display_name`: The human readable name for the `Dataset` resource.\n",
+        "- `df_source`: The pandas dataframe to import the data items into the `Dataset` resource.\n",
+        "- `staging_path`: The BigQuery table to store the imported data."
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "import_file:covid,csv,forecast"
+        "id": "3805f945ffdd"
       },
       "outputs": [],
       "source": [
-        "IMPORT_FILE = \"gs://cloud-samples-data/ai-platform/covid/bigquery-public-covid-nyt-us-counties-train.csv\""
+        "# Download the table.\n",
+        "table = bigquery.TableReference.from_string(BQ_TABLE)\n",
+        "\n",
+        "rows = bqclient.list_rows(\n",
+        "    table,\n",
+        "    max_results=10000,\n",
+        "    selected_fields=[\n",
+        "        bigquery.SchemaField(\"station_number\", \"STRING\"),\n",
+        "        bigquery.SchemaField(\"year\", \"INTEGER\"),\n",
+        "        bigquery.SchemaField(\"month\", \"INTEGER\"),\n",
+        "        bigquery.SchemaField(\"day\", \"INTEGER\"),\n",
+        "        bigquery.SchemaField(\"mean_temp\", \"FLOAT\"),\n",
+        "    ],\n",
+        ")\n",
+        "\n",
+        "dataframe = rows.to_dataframe()\n",
+        "print(dataframe.head())"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "create_dataset:tabular,bq,lrg,v2"
+      },
+      "outputs": [],
+      "source": [
+        "dataset = aip.TabularDataset.create_from_dataframe(\n",
+        "    display_name=\"example\" + \"_\" + TIMESTAMP,\n",
+        "    df_source=dataframe,\n",
+        "    staging_path=f\"bq://{PROJECT_ID}.samples.gsod\",\n",
+        ")\n",
+        "\n",
+        "print(dataset.resource_name)"
       ]
     },
     {
@@ -778,7 +911,7 @@
         "id": "create_dataset:tabular,forecast,v2"
       },
       "source": [
-        "### Create the Dataset\n",
+        "### Create a Time Series Dataset\n",
         "\n",
         "Next, create the `Dataset` resource using the `create` method for the `TimeSeriesDataset` class, which takes the following parameters:\n",
         "\n",
@@ -789,6 +922,17 @@
         "Learn more about [TimeSeriesDataset](https://cloud.google.com/vertex-ai/docs/datasets/prepare-tabular)."
       ]
     },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "import_file:covid,csv,forecast"
+      },
+      "outputs": [],
+      "source": [
+        "IMPORT_FILE = \"gs://cloud-samples-data/ai-platform/covid/bigquery-public-covid-nyt-us-counties-train.csv\""
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -1149,9 +1293,9 @@
         "comps = BQ_TABLE.split(\".\")\n",
         "BQ_PROJECT_DATASET_TABLE = comps[0] + \":\" + comps[1] + \".\" + comps[2]\n",
         "\n",
-        "! bq --location=us extract --destination_format CSV $BQ_PROJECT_DATASET_TABLE $BUCKET_NAME/mydata*.csv\n",
+        "! bq --location=us extract --destination_format CSV $BQ_PROJECT_DATASET_TABLE $BUCKET_URI/mydata*.csv\n",
         "\n",
-        "IMPORT_FILES = ! gsutil ls $BUCKET_NAME/mydata*.csv\n",
+        "IMPORT_FILES = ! gsutil ls $BUCKET_URI/mydata*.csv\n",
         "\n",
         "print(IMPORT_FILES)\n",
         "\n",
@@ -1209,6 +1353,38 @@
         "To create a dataframe from multiple CSV sources, you read each CSV file and concatenate the dataframes together."
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "bcd2e4e0703b"
+      },
+      "source": [
+        "If you are running this notebook on Colab, run the following cell to install packages fsspec and gcsfs."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "927bd3f92268"
+      },
+      "outputs": [],
+      "source": [
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If on Workbench AI Notebook, then don't execute this code\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\"):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        ! pip3 install fsspec\n",
+        "        ! pip3 install gcsfs"
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -1269,7 +1445,7 @@
       },
       "outputs": [],
       "source": [
-        "EXPORTED_DIR = f\"{BUCKET_NAME}/exported\"\n",
+        "EXPORTED_DIR = f\"{BUCKET_URI}/exported\"\n",
         "exported_files = dataset.export_data(output_dir=EXPORTED_DIR)\n",
         "\n",
         "! gsutil ls $EXPORTED_DIR"
@@ -1498,7 +1674,7 @@
         "    data = f.readlines()\n",
         "\n",
         "# The path to the TFRecord cached file.\n",
-        "GCS_TFRECORD_URI = BUCKET_NAME + \"/flowers.tfrecord\"\n",
+        "GCS_TFRECORD_URI = BUCKET_URI + \"/flowers.tfrecord\"\n",
         "\n",
         "# Create the TFRecord cached file\n",
         "with tf.io.TFRecordWriter(GCS_TFRECORD_URI) as writer:\n",
@@ -1532,14 +1708,7 @@
         "Otherwise, you can delete the individual resources you created in this tutorial:\n",
         "\n",
         "- Dataset\n",
-        "- Pipeline\n",
-        "- Model\n",
-        "- Endpoint\n",
-        "- AutoML Training Job\n",
-        "- Batch Job\n",
-        "- Custom Job\n",
-        "- Hyperparameter Tuning Job\n",
-        "- Cloud Storage Bucket"
+        "- Bucket"
       ]
     },
     {
@@ -1550,61 +1719,16 @@
       },
       "outputs": [],
       "source": [
-        "delete_all = True\n",
+        "delete_bucket = False\n",
         "\n",
-        "if delete_all:\n",
-        "    # Delete the dataset using the Vertex dataset object\n",
-        "    try:\n",
-        "        if \"dataset\" in globals():\n",
-        "            dataset.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
+        "# Delete the dataset using the Vertex dataset object\n",
+        "datasets = aip.TabularDataset.list(filter=f'display_name=\"example_{TIMESTAMP}\"')\n",
+        "for dataset in datasets:\n",
+        "    dataset.delete()\n",
         "\n",
-        "    # Delete the model using the Vertex model object\n",
-        "    try:\n",
-        "        if \"model\" in globals():\n",
-        "            model.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the endpoint using the Vertex endpoint object\n",
-        "    try:\n",
-        "        if \"endpoint\" in globals():\n",
-        "            endpoint.undeploy_all()\n",
-        "            endpoint.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the AutoML or Pipeline training job\n",
-        "    try:\n",
-        "        if \"dag\" in globals():\n",
-        "            dag.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the custom training job\n",
-        "    try:\n",
-        "        if \"job\" in globals():\n",
-        "            job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the batch prediction job using the Vertex batch prediction object\n",
-        "    try:\n",
-        "        if \"batch_predict_job\" in globals():\n",
-        "            batch_predict_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the hyperparameter tuning job using the Vertex hyperparameter tuning object\n",
-        "    try:\n",
-        "        if \"hpt_job\" in globals():\n",
-        "            hpt_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    if \"BUCKET_NAME\" in globals():\n",
-        "        ! gsutil rm -r $BUCKET_NAME"
+        "# Delete the bucket\n",
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil rm -r $BUCKET_URI"
       ]
     }
   ],

notebooks/community/ml_ops/stage1/get_started_with_data_labeling.ipynb

@@ -33,13 +33,19 @@
         "\n",
         "<table align=\"left\">\n",
         "  <td>\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage1/get_started_with_data_labeling.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
         "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage1/get_started_with_data_labeling.ipynb\">\n",
         "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
         "      View on GitHub\n",
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://console.cloud.google.com/ai/platform/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage3/get_started_with_data_labeling.ipynb\">\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/ml_ops/stage1/get_started_with_data_labeling.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
         "      Open in Vertex AI Workbench\n",
         "    </a>\n",
         "  </td>\n",
@@ -96,6 +102,28 @@
         "Learn more about [Request a Vertex AI Data Labeling job](https://cloud.google.com/vertex-ai/docs/datasets/data-labeling-job)."
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0c997d8d92ce"
+      },
+      "source": [
+        "### Costs \n",
+        "\n",
+        "\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "* Vertex AI\n",
+        "* Cloud Storage\n",
+        "\n",
+        "\n",
+        "Learn about [Vertex AI\n",
+        "pricing](https://cloud.google.com/vertex-ai/pricing) and [Cloud Storage\n",
+        "pricing](https://cloud.google.com/storage/pricing), and use the [Pricing\n",
+        "Calculator](https://cloud.google.com/products/calculator/)\n",
+        "to generate a cost estimate based on your projected usage."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -117,17 +145,20 @@
       "source": [
         "import os\n",
         "\n",
-        "# The Google Cloud Notebook product has specific requirements\n",
-        "IS_GOOGLE_CLOUD_NOTEBOOK = os.path.exists(\"/opt/deeplearning/metadata/env_version\")\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\") and not os.getenv(\"VIRTUAL_ENV\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
         "\n",
-        "# Google Cloud Notebook requires dependencies to be installed with '--user'\n",
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
         "USER_FLAG = \"\"\n",
-        "if IS_GOOGLE_CLOUD_NOTEBOOK:\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
         "    USER_FLAG = \"--user\"\n",
         "\n",
         "# Install the packages\n",
-        "! pip3 install --upgrade google-cloud-aiplatform $USER_FLAG\n",
-        "! pip3 install --upgrade google-cloud-storage"
+        "! pip3 install --upgrade google-cloud-aiplatform $USER_FLAG -q\n",
+        "! pip3 install --upgrade google-cloud-storage $USER_FLAG -q"
       ]
     },
     {
@@ -138,7 +169,7 @@
       "source": [
         "### Restart the Kernel\n",
         "\n",
-        "Once you've installed the Vertex SDK and Google *cloud-storage*, you need to restart the notebook kernel so it can find the packages.\n"
+        "Once you've installed the Vertex AI SDK and Google *cloud-storage*, you need to restart the notebook kernel so it can find the packages.\n"
       ]
     },
     {
@@ -179,7 +210,7 @@
         "\n",
         "2. [Make sure that billing is enabled for your project.](https://cloud.google.com/billing/docs/how-to/modify-project)\n",
         "\n",
-        "3. [Enable the Vertex APIs and Compute Engine APIs.](https://console.cloud.google.com/flows/enableapi?apiid=ml.googleapis.com,compute_component)\n",
+        "3. [Enable the Vertex AI APIs and Compute Engine APIs.](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,compute_component)\n",
         "\n",
         "4. [Google Cloud SDK](https://cloud.google.com/sdk) is already installed in Google Cloud Notebooks.\n",
         "\n",
@@ -318,7 +349,7 @@
       "source": [
         "if EMAIL == \"[your-email-address]\":\n",
         "    shell_output = ! gcloud auth list 2>/dev/null\n",
-        "    EMAIL = shell_output[3].replace(\"*\", \"\").strip()\n",
+        "    EMAIL = shell_output[2].replace(\"*\", \"\").strip()\n",
         "\n",
         "print(EMAIL)"
       ]
@@ -329,12 +360,40 @@
         "id": "gcp_authenticate"
       },
       "source": [
-        "### Authenticate your GCP account\n",
+        "### Authenticate your Google Cloud account\n",
         "\n",
-        "**If you are using Google Cloud Notebooks**, your environment is already\n",
-        "authenticated. Skip this step.\n",
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already\n",
+        "authenticated. Skip this step."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "32e1cd21a5d5"
+      },
+      "source": [
+        "**If you are using Colab**, run the cell below and follow the instructions\n",
+        "when prompted to authenticate your account via oAuth.\n",
         "\n",
-        "*Note: If you are on an Vertex AI Workbench notebook and run the cell, the cell knows to skip executing the authentication steps.*\n"
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "1. In the Cloud Console, go to the [**Create service account key**\n",
+        "   page](https://console.cloud.google.com/apis/credentials/serviceaccountkey).\n",
+        "\n",
+        "2. Click **Create service account**.\n",
+        "\n",
+        "3. In the **Service account name** field, enter a name, and\n",
+        "   click **Create**.\n",
+        "\n",
+        "4. In the **Grant this service account access to project** section, click the **Role** drop-down list. Type \"Vertex AI\"\n",
+        "into the filter box, and select\n",
+        "   **Vertex AI Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "5. Click *Create*. A JSON file that contains your key downloads to your\n",
+        "local environment.\n",
+        "\n",
+        "6. Enter the path to your service account key as the\n",
+        "`GOOGLE_APPLICATION_CREDENTIALS` variable in the cell below and run the cell."
       ]
     },
     {
@@ -345,29 +404,30 @@
       },
       "outputs": [],
       "source": [
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
         "import os\n",
         "import sys\n",
         "\n",
-        "# If you are running this notebook in Colab, run this cell and follow the\n",
-        "# instructions to authenticate your Google Cloud account. This provides access\n",
-        "# to your Cloud Storage bucket and lets you submit training jobs and prediction\n",
-        "# requests.\n",
-        "\n",
-        "# If on Vertex, then don't execute this code\n",
-        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\"):\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
+        "IS_COLAB = False\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
+        "    \"DL_ANACONDA_HOME\"\n",
+        "):\n",
         "    if \"google.colab\" in sys.modules:\n",
+        "        IS_COLAB = True\n",
         "        from google.colab import auth as google_auth\n",
         "\n",
         "        google_auth.authenticate_user()\n",
         "\n",
-        "    # If you are running this tutorial in a notebook locally, replace the string\n",
-        "    # below with the path to your service account key and run this cell to\n",
-        "    # authenticate your Google Cloud account.\n",
-        "    else:\n",
-        "        %env GOOGLE_APPLICATION_CREDENTIALS your_path_to_credentials.json\n",
-        "\n",
-        "    # Log in to your account on Google Cloud\n",
-        "    ! gcloud auth login"
+        "    # If you are running this notebook locally, replace the string below with the\n",
+        "    # path to your service account key and run this cell to authenticate your GCP\n",
+        "    # account.\n",
+        "    elif not os.getenv(\"IS_TESTING\"):\n",
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
       ]
     },
     {
@@ -406,7 +466,8 @@
       "outputs": [],
       "source": [
         "if BUCKET_URI == \"\" or BUCKET_URI is None or BUCKET_URI == \"gs://[your-bucket-name]\":\n",
-        "    BUCKET_URI = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
+        "    BUCKET_NAME = PROJECT_ID + \"aip-\" + TIMESTAMP\n",
+        "    BUCKET_URI = \"gs://\" + BUCKET_NAME"
       ]
     },
     {
@@ -485,11 +546,34 @@
         "import time\n",
         "\n",
         "import google.cloud.aiplatform as aip\n",
+        "from google.cloud import storage\n",
         "from google.cloud.aiplatform import gapic\n",
         "from google.protobuf.json_format import ParseDict\n",
         "from google.protobuf.struct_pb2 import Value"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "750d53e37094"
+      },
+      "source": [
+        "### Initialize Vertex AI SDK for Python\n",
+        "\n",
+        "Initialize the Vertex AI SDK for Python for your project and corresponding bucket."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "adcc964aaaa1"
+      },
+      "outputs": [],
+      "source": [
+        "aip.init(project=PROJECT_ID, location=REGION)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -604,18 +688,29 @@
       },
       "outputs": [],
       "source": [
-        "import tensorflow as tf\n",
-        "\n",
+        "test_filename = \"labeling.csv\"\n",
         "LABELING_FILES = [\n",
         "    \"gs://cloud-samples-data/vision/automl_classification/flowers/daisy/100080576_f52e8ee070_n.jpg\",\n",
         "    \"gs://cloud-samples-data/vision/automl_classification/flowers/daisy/102841525_bd6628ae3c.jpg\",\n",
         "]\n",
         "\n",
         "IMPORT_FILE = BUCKET_URI + \"/labeling.csv\"\n",
-        "with tf.io.gfile.GFile(IMPORT_FILE, \"w\") as f:\n",
-        "    for lf in LABELING_FILES:\n",
-        "        f.write(lf + \"\\n\")\n",
         "\n",
+        "bucket = storage.Client(project=PROJECT_ID).bucket(BUCKET_URI.replace(\"gs://\", \"\"))\n",
+        "\n",
+        "# creating a blob\n",
+        "blob = bucket.blob(blob_name=test_filename)\n",
+        "\n",
+        "# creating data variable\n",
+        "data = LABELING_FILES[0] + \"\\n\" + LABELING_FILES[1] + \"\\n\"\n",
+        "\n",
+        "# uploading data variable content to bucket\n",
+        "blob.upload_from_string(data, content_type=\"text/csv\")\n",
+        "\n",
+        "# printing path of uploaded file\n",
+        "print(IMPORT_FILE)\n",
+        "\n",
+        "# printing content of uploaded file\n",
         "! gsutil cat $IMPORT_FILE"
       ]
     },
@@ -675,7 +770,7 @@
       "source": [
         "## Create a new data specialist pool\n",
         "\n",
-        "You data labeling job will be sent to a data specialist pool. You may have one or more multiple specialist pools. \n",
+        "Your data labeling job will be sent to a data specialist pool. You may have one or more multiple specialist pools. \n",
         "\n",
         "In this next step, you create a new specialist pool with the method `create_specialist_pool()`. The request includes the parameters:\n",
         "\n",
@@ -882,34 +977,20 @@
       },
       "outputs": [],
       "source": [
-        "delete_dataset = True\n",
-        "delete_job = True\n",
-        "delete_specialist_pool = True\n",
-        "delete_bucket = True\n",
+        "# Set this to true only if you'd like to delete your bucket\n",
+        "delete_bucket = False\n",
         "\n",
         "# Delete the dataset using the Vertex AI fully qualified identifier for the dataset\n",
-        "try:\n",
-        "    if delete_dataset:\n",
-        "        dataset.delete()\n",
-        "except Exception as e:\n",
-        "    print(e)\n",
+        "dataset.delete()\n",
         "\n",
         "# Delete the labeling job using the Vertex AI fully qualified identifier for the dataset\n",
-        "try:\n",
-        "    if delete_job:\n",
-        "        request = clients[\"job\"].delete_data_labeling_job(name=labeling_task_name)\n",
-        "except Exception as e:\n",
-        "    print(e)\n",
+        "request = clients[\"job\"].delete_data_labeling_job(name=labeling_task_name)\n",
         "\n",
         "# Delete the specialist pool using the Vertex AI fully qualified identifier for the dataset\n",
-        "try:\n",
-        "    if delete_specialist_pool:\n",
-        "        clients[\"specialist_pool\"].delete_specialist_pool(name=specialist_name)\n",
-        "except Exception as e:\n",
-        "    print(e)\n",
+        "clients[\"specialist_pool\"].delete_specialist_pool(name=specialist_name)\n",
         "\n",
-        "\n",
-        "if delete_bucket and \"BUCKET_URI\" in globals():\n",
+        "# Delete the bucket created\n",
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
         "    ! gsutil rm -r $BUCKET_URI"
       ]
     }

notebooks/community/ml_ops/stage1/get_started_with_visionapi_and_vertex_datasets.ipynb

@@ -0,0 +1,994 @@
+{
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "copyright"
+      },
+      "outputs": [],
+      "source": [
+        "# Copyright 2022 Google LLC\n",
+        "#\n",
+        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
+        "# you may not use this file except in compliance with the License.\n",
+        "# You may obtain a copy of the License at\n",
+        "#\n",
+        "#     https://www.apache.org/licenses/LICENSE-2.0\n",
+        "#\n",
+        "# Unless required by applicable law or agreed to in writing, software\n",
+        "# distributed under the License is distributed on an \"AS IS\" BASIS,\n",
+        "# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
+        "# See the License for the specific language governing permissions and\n",
+        "# limitations under the License."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "4JIDiHvGasba"
+      },
+      "source": [
+        "This notebook was contributed by [Mohammad Al-Ansari](https://github.com/Mansari)."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "2xDiUNIZINWp"
+      },
+      "source": [
+        "# E2E ML on GCP: MLOps stage 1 : data management: create an unlabelled Vertex AI AutoML text entity extraction dataset from PDFs using Vision API\n",
+        "\n",
+        "<table align=\"left\">\n",
+        "  <td>\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage1/get_started_with_visionapi_and_vertex_datasets.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage1/get_started_with_visionapi_and_vertex_datasets.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
+        "      View on GitHub\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage1/get_started_with_visionapi_and_vertex_datasets.ipynb\">\n",
+        "     <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "      Open in Vertex AI Workbench\n",
+        "    </a>\n",
+        "  </td>\n",
+        "</table>\n",
+        "<br/><br/><br/>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "H0alLPo_A-LK"
+      },
+      "source": [
+        "## Overview\n",
+        "\n",
+        "This notebook will create an unlabelled `Vertex AI AutoML` text entity extraction dataset based on a collection of PDF files stored in a Cloud Storage bucket. \n",
+        "\n",
+        "The notebook can be modified to create different types of text datasets including sentiment analysis and classification."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "W4IBLTKOA5nl"
+      },
+      "source": [
+        "### Dataset\n",
+        "\n",
+        "The dataset used for this tutorial is the [Patent PDF Samples with Extracted Structured Data](https://console.cloud.google.com/marketplace/product/global-patents/labeled-patents) from Google Public Data Sets. \n",
+        "\n",
+        "This dataset includes data extracted from over 300 patent documents issued in the US and EU. The dataset includes links to Cloud Storage blobs for the first page of each patent, in addition to a number of extracted entities. \n",
+        "\n",
+        "The data is published as a [public dataset](https://cloud.google.com/bigquery/public-data) on `BigQuery`."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "3f8c2f702ccd"
+      },
+      "source": [
+        "### Objective\n",
+        "\n",
+        "In this tutorial, you learn to use `Vision API` to extract text from PDF files stored on a Cloud Storage bucket. You will then process the results and create an unlabelled `Vertex AI Dataset`, compatible with `AutoML`, for text entity extraction.\n",
+        "\n",
+        "You can then either use Google Cloud console to annotate / label the dataset, or create a labelling job as demonstrated in [this notebook](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage1/get_started_with_data_labeling.ipynb).\n",
+        "\n",
+        "This tutorial uses the following Google Cloud services:\n",
+        "\n",
+        "- `Vision AI`\n",
+        "- `Vertex AI AutoML`\n",
+        "\n",
+        "The steps performed include:\n",
+        "\n",
+        "1. Using `Vision API` to perform Optical Character Recognition (OCR) to extract text from PDF files.\n",
+        "2. Processing the results and saving them to text files.\n",
+        "3. Generating a `Vertex AI Dataset` import file.\n",
+        "4. Creating a new unlabelled text entity extraction `Vertex AI Dataset` resource in `Vertex AI`."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "CgLDJ419LPJs"
+      },
+      "source": [
+        "### Costs\n",
+        "\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "* Vision API\n",
+        "* Vertex AI\n",
+        "* Cloud Storage\n",
+        "\n",
+        "Learn about [Vertex AI\n",
+        "pricing](https://cloud.google.com/vertex-ai/pricing), [Vision API pricing](https://cloud.google.com/vision/pricing), [Cloud Storage\n",
+        "pricing](https://cloud.google.com/storage/pricing), and use the [Pricing\n",
+        "Calculator](https://cloud.google.com/products/calculator/)\n",
+        "to generate a cost estimate based on your projected usage."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "va2g7m9wLTjA"
+      },
+      "source": [
+        "### Set up your local development environment\n",
+        "\n",
+        "If you are using Colab or Vertex AI Workbench Notebooks, your environment already meets all the requirements to run this notebook. You can skip this step.\n",
+        "\n",
+        "Otherwise, make sure your environment meets this notebook's requirements. You need the following:\n",
+        "\n",
+        "- The Vision API SDK\n",
+        "- The Vertex AI SDK\n",
+        "- The Cloud Storage SDK\n",
+        "- Git\n",
+        "- Python 3\n",
+        "- virtualenv\n",
+        "- Jupyter notebook running in a virtual environment with Python 3\n",
+        "\n",
+        "The Cloud Storage guide to [Setting up a Python development environment](https://cloud.google.com/python/setup) and the [Jupyter installation guide](https://jupyter.org/install) provide detailed instructions for meeting these requirements. The following steps provide a condensed set of instructions:\n",
+        "\n",
+        "1. [Install and initialize the SDKs](https://cloud.google.com/sdk/docs/).\n",
+        "\n",
+        "2. [Install Python 3](https://cloud.google.com/python/setup#installing_python).\n",
+        "\n",
+        "3. [Install virtualenv](https://cloud.google.com/python/setup#installing_and_using_virtualenv) and create a virtual environment that uses Python 3.  Activate the virtual environment.\n",
+        "\n",
+        "4. To install Jupyter, run `pip3 install jupyter` on the command-line in a terminal shell.\n",
+        "\n",
+        "5. To launch Jupyter, run `jupyter notebook` on the command-line in a terminal shell.\n",
+        "\n",
+        "6. Open this notebook in the Jupyter Notebook Dashboard.\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "X2tZAmugAe6h"
+      },
+      "source": [
+        "## Installation\n",
+        "\n",
+        "Install the packages required for executing this notebook. You can ignore errors for the `pip` dependecy resolver as they do not impact this notebook."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "BQOsJ1hZAZu0"
+      },
+      "outputs": [],
+      "source": [
+        "import os\n",
+        "\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
+        "\n",
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
+        "USER_FLAG = \"\"\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "\n",
+        "! pip3 install --upgrade google-cloud-storage google-cloud-vision google-cloud-aiplatform $USER_FLAG -q"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "yzvvcmCuAon3"
+      },
+      "source": [
+        "### Restart the kernel\n",
+        "\n",
+        "Once you've installed the additional packages, you need to restart the notebook kernel so it can find the packages."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "6qEonzbuAoI_"
+      },
+      "outputs": [],
+      "source": [
+        "import os\n",
+        "\n",
+        "if not os.getenv(\"IS_TESTING\"):\n",
+        "    # Automatically restart kernel after installs\n",
+        "    import IPython\n",
+        "\n",
+        "    app = IPython.Application.instance()\n",
+        "    app.kernel.do_shutdown(True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "pGbbyN7rAuRM"
+      },
+      "source": [
+        "## Before you begin\n",
+        "\n",
+        "### GPU runtime\n",
+        "\n",
+        "*Make sure you're running this notebook in a GPU runtime if you have that option. In Colab, select* **Runtime > Change Runtime Type > GPU**\n",
+        "\n",
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "2. [Make sure that billing is enabled for your project.](https://cloud.google.com/billing/docs/how-to/modify-project)\n",
+        "\n",
+        "3. [Enable the following APIs: Vision API, Vertex AI APIs, Compute Engine APIs, and Cloud Storage.](https://console.cloud.google.com/flows/enableapi?apiid=vision.googleapis.com,aiplatform.googleapis.com,compute_component,storage-component.googleapis.com)\n",
+        "\n",
+        "4. If you are running this notebook locally, you will need to install the [Cloud SDK]((https://cloud.google.com/sdk)).\n",
+        "\n",
+        "5. Enter your project ID in the cell below. Then run the  cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$`."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "AE97adtnAzrr"
+      },
+      "outputs": [],
+      "source": [
+        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "nWlzLu5ELxWd"
+      },
+      "outputs": [],
+      "source": [
+        "if PROJECT_ID == \"\" or PROJECT_ID is None or PROJECT_ID == \"[your-project-id]\":\n",
+        "    # Get your GCP project id from gcloud\n",
+        "    shell_output = ! gcloud config list --format 'value(core.project)' 2>/dev/null\n",
+        "    PROJECT_ID = shell_output[0]\n",
+        "    print(\"Project ID:\", PROJECT_ID)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "GB5b27r0LxqE"
+      },
+      "outputs": [],
+      "source": [
+        "! gcloud config set project $PROJECT_ID"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "pMJdU1K5xG7D"
+      },
+      "source": [
+        "### Regions\n",
+        "\n",
+        "#### Vision AI\n",
+        "\n",
+        "You can now specify continent-level data storage and Optical Character Regonition (OCR) processing by setting the `VISION_AI_REGION` variable. You can select one of the following options:\n",
+        "\n",
+        "* USA country only: `us`\n",
+        "* The European Union: `eu`\n",
+        "\n",
+        "Learn more about [Vision AI regions for OCR](https://cloud.google.com/vision/docs/pdf#regionalization)\n",
+        "\n",
+        "#### Vertex AI\n",
+        "\n",
+        "You can also change the `VERTEX_AI_REGION` variable, which is used for operations throughout the rest of this notebook.  Below are regions supported for Vertex AI. We recommend that you choose the region closest to you.\n",
+        "\n",
+        "- Americas: `us-central1`\n",
+        "- Europe: `europe-west4`\n",
+        "- Asia Pacific: `asia-east1`\n",
+        "\n",
+        "You may not use a multi-regional bucket for training with Vertex AI. Not all regions provide support for all Vertex AI services.\n",
+        "\n",
+        "Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "5EhEAOK5xIKc"
+      },
+      "outputs": [],
+      "source": [
+        "VISION_AI_REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
+        "\n",
+        "if VISION_AI_REGION == \"[your-region]\":\n",
+        "    VISION_AI_REGION = \"us\"\n",
+        "\n",
+        "VERTEX_AI_REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
+        "\n",
+        "if VERTEX_AI_REGION == \"[your-region]\":\n",
+        "    VERTEX_AI_REGION = \"us-central1\""
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "xkgvWoXkxM1r"
+      },
+      "source": [
+        "### Timestamp\n",
+        "\n",
+        "If you are in a live tutorial session, you might be using a shared test account or project. To avoid name collisions between users on resources created, you create a timestamp for each instance session, and append onto the name of resources which will be created in this tutorial."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "gr0HTpQZxNy4"
+      },
+      "outputs": [],
+      "source": [
+        "from datetime import datetime\n",
+        "\n",
+        "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "AA-ns5CcBA9U"
+      },
+      "source": [
+        "### Vertex AI dataset import schema\n",
+        "\n",
+        "This constant tells Vertex AI the schema for importing the dataset. In this tutorial you are going to use the value for text extraction, but you can also change it to any of the values below for other use cases:\n",
+        "\n",
+        "- \n",
+        "`aiplatform.schema.dataset.ioformat.text.single_label_classification`\n",
+        "\n",
+        "- \n",
+        "`aiplatform.schema.dataset.ioformat.text.multi_label_classification`\n",
+        "\n",
+        "- \n",
+        "`aiplatform.schema.dataset.ioformat.text.extraction`\n",
+        "\n",
+        "- \n",
+        "`aiplatform.schema.dataset.ioformat.text.sentiment`\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "jnOb6Pp-4w5P"
+      },
+      "outputs": [],
+      "source": [
+        "from google.cloud import aiplatform\n",
+        "\n",
+        "DATASET_IMPORT_SCHEMA = aiplatform.schema.dataset.ioformat.text.extraction"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "ekbg-G7UA-bK"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "**If you are using Vertex AI Workbench**, your environment is already authenticated. Skip this step. If you receive errors still, you may have to grant the service account that is your Workbench notebook is running under access to the services listed below.\n",
+        "\n",
+        "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\n",
+        "\n",
+        "**Click Create service account**.\n",
+        "\n",
+        "In the **Service account name** field, enter a name, and click **Create**.\n",
+        "\n",
+        "In the **Grant this service account access to project** section, click the Role drop-down list. Type \"Vertex\" into the filter box, and select **Vertex AI Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "Click Create. A JSON file that contains your key downloads to your local environment.\n",
+        "\n",
+        "Enter the path to your service account key as the GOOGLE_APPLICATION_CREDENTIALS variable in the cell below and run the cell."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "lCRrULxKBAfa"
+      },
+      "outputs": [],
+      "source": [
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
+        "IS_COLAB = \"google.colab\" in sys.modules\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
+        "    \"DL_ANACONDA_HOME\"\n",
+        "):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        from google.colab import auth as google_auth\n",
+        "\n",
+        "        google_auth.authenticate_user()\n",
+        "\n",
+        "    # If you are running this notebook locally, replace the string below with the\n",
+        "    # path to your service account key and run this cell to authenticate your GCP\n",
+        "    # account.\n",
+        "    elif not os.getenv(\"IS_TESTING\"):\n",
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "rHB6fbonMMbI"
+      },
+      "source": [
+        "### Create a Cloud Storage bucket\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "When you initialize the Vertex AI SDK for Python, you specify a Cloud Storage staging bucket. The staging bucket is where all the data associated with your dataset and model resources are retained across sessions. This bucket will be also used to store the output of the Vision API SDK PDF-to-text conversion process.\n",
+        "\n",
+        "Set the name of your Cloud Storage bucket below. Bucket names must be globally unique across all Google Cloud projects, including those outside of your organization."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "ZSM5j0nfMOVK"
+      },
+      "outputs": [],
+      "source": [
+        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
+        "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "i6H2iQX2MP-s"
+      },
+      "outputs": [],
+      "source": [
+        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"[your-bucket-name]\":\n",
+        "    BUCKET_NAME = PROJECT_ID + \"aip-\" + TIMESTAMP\n",
+        "    BUCKET_URI = \"gs://\" + BUCKET_NAME"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "AOsnYE5cMQX4"
+      },
+      "source": [
+        "**Only if your bucket doesn't already exist**: Run the following cell to create your Cloud Storage bucket."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "33RgSjhyMR6C"
+      },
+      "outputs": [],
+      "source": [
+        "! gsutil mb -l $VERTEX_AI_REGION -p $PROJECT_ID $BUCKET_URI"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "UpKfi0VfMTwe"
+      },
+      "source": [
+        "Finally, validate access to your Cloud Storage bucket by examining its contents:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "G9dMjMnkMVNt"
+      },
+      "outputs": [],
+      "source": [
+        "! gsutil ls -al $BUCKET_URI"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "k2qH7YCI0vnG"
+      },
+      "source": [
+        "### Set up variables\n",
+        "\n",
+        "Next, set up some variables used throughout the tutorial.\n",
+        "\n",
+        "### Import libraries and define constants"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "TB5-_2Xh01NH"
+      },
+      "outputs": [],
+      "source": [
+        "import os\n",
+        "\n",
+        "from google.cloud import aiplatform, storage, vision"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "-v7gY_KABIn8"
+      },
+      "source": [
+        "### Initialize Vision API SDK for Python\n",
+        "\n",
+        "Initialize the `Vision AI` SDK for Python for your project and region."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "DRbf--kWBLpx"
+      },
+      "outputs": [],
+      "source": [
+        "vision_client_options = {\n",
+        "    \"quota_project_id\": PROJECT_ID,\n",
+        "    \"api_endpoint\": f\"{VISION_AI_REGION}-vision.googleapis.com\",\n",
+        "}\n",
+        "vision_client = vision.ImageAnnotatorClient(client_options=vision_client_options)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "CA4nNVbBZ25d"
+      },
+      "source": [
+        "### Initialize Vertex AI SDK for Python\n",
+        "\n",
+        "Initialize the `Vertex AI` SDK for Python for your project, region and corresponding bucket."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "awWpNW1vZ6uV"
+      },
+      "outputs": [],
+      "source": [
+        "aiplatform.init(\n",
+        "    project=PROJECT_ID, location=VERTEX_AI_REGION, staging_bucket=BUCKET_URI\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "debBBljMDqkM"
+      },
+      "source": [
+        "### Initialize Cloud Storage SDK for Python\n",
+        "\n",
+        "Initialize the `Cloud Storage` SDK for Python for your project."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "ZtzmI9tpDr4e"
+      },
+      "outputs": [],
+      "source": [
+        "storage_client = storage.Client(project=PROJECT_ID)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "mvD0BxVXMtJe"
+      },
+      "source": [
+        "## Tutorial\n",
+        "\n",
+        "Now you are ready to start creating an unlabelled `Vertex AI Dataset` text entity extraction dataset from PDF files."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "EurEFM3GBap9"
+      },
+      "source": [
+        "### Convert PDF files to text using Vision API\n",
+        "\n",
+        "First, you make a `Vision API` request to OCR to text the PDFs from the Patent samples stored in the Cloud Storage bucket.\n",
+        "\n",
+        "*Note:* `Visions API` only allows batches of 100 document submissions at a time."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "uXVPOvjTBeK3"
+      },
+      "outputs": [],
+      "source": [
+        "ORIGIN_BUCKET_NAME = \"gcs-public-data--labeled-patents\"\n",
+        "# You can add a path if needed\n",
+        "ORIGIN_BUCKET_PATH = \"\"\n",
+        "\n",
+        "DESTINATION_BUCKET_NAME = BUCKET_NAME\n",
+        "DESTINATION_BUCKET_PATH = \"ocr-output\"\n",
+        "\n",
+        "gcs_destination_uri = f\"gs://{DESTINATION_BUCKET_NAME}/{DESTINATION_BUCKET_PATH}\"\n",
+        "\n",
+        "# Specify the feature for the Vision API processor\n",
+        "feature = vision.Feature(type_=vision.Feature.Type.DOCUMENT_TEXT_DETECTION)\n",
+        "\n",
+        "# Retrieve a list of all files in the bucket and path\n",
+        "blobs = storage_client.list_blobs(\n",
+        "    ORIGIN_BUCKET_NAME, prefix=ORIGIN_BUCKET_PATH, delimiter=\"/\"\n",
+        ")\n",
+        "\n",
+        "# Create a collection of requests. The SDK requires a separate request per each\n",
+        "# file that we want to extract text from\n",
+        "async_requests = []\n",
+        "\n",
+        "# Visions API only supports processing up to 100 documents at a time\n",
+        "# so we will process the first 100 elements only\n",
+        "sliced_blob_list = list(blobs)[:100]\n",
+        "\n",
+        "# Loop through the source bucket and create a request for each file there\n",
+        "for blob in sliced_blob_list:\n",
+        "    # Build input_config\n",
+        "    # Ensure we are only processing PDF files\n",
+        "    if blob.name.endswith(\".pdf\"):\n",
+        "        gcs_source = vision.GcsSource(uri=f\"gs://{ORIGIN_BUCKET_NAME}/{blob.name}\")\n",
+        "        input_config = vision.InputConfig(\n",
+        "            gcs_source=gcs_source, mime_type=\"application/pdf\"\n",
+        "        )\n",
+        "\n",
+        "        # Build output config\n",
+        "        # Get file name\n",
+        "        file_name = os.path.splitext(os.path.basename(blob.name))[0]\n",
+        "        gcs_destination = vision.GcsDestination(\n",
+        "            uri=f\"{gcs_destination_uri}/{file_name}-\"\n",
+        "        )\n",
+        "        output_config = vision.OutputConfig(gcs_destination=gcs_destination)\n",
+        "\n",
+        "        # Build request object and add to the collection\n",
+        "        async_request = vision.AsyncAnnotateFileRequest(\n",
+        "            features=[feature], input_config=input_config, output_config=output_config\n",
+        "        )\n",
+        "\n",
+        "        async_requests.append(async_request)\n",
+        "\n",
+        "print(f\"Created {len(async_requests)} requests\")\n",
+        "\n",
+        "# Submit the batch OCR job\n",
+        "\n",
+        "operation = vision_client.async_batch_annotate_files(requests=async_requests)\n",
+        "print(\"Submitting the batch OCR job\")\n",
+        "\n",
+        "print(\"Waiting for the operation to finish... this will take a short while\")\n",
+        "\n",
+        "response = operation.result(timeout=420)\n",
+        "\n",
+        "print(\"Completed!\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "7b15473e1937"
+      },
+      "source": [
+        "#### Quick peek at extracted annotated JSON files\n",
+        "\n",
+        "Next, you take a peek at the contents of one of the extracted JSON annotated files."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "4366442c1373"
+      },
+      "outputs": [],
+      "source": [
+        "json_files = ! gsutil ls {gcs_destination_uri}\n",
+        "\n",
+        "example = json_files[0]\n",
+        "! gsutil cat {example} | head -n 1"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "QWmeHWPIHako"
+      },
+      "source": [
+        "### Process results and build the import file\n",
+        "\n",
+        "The `Vision API` output is in JSON format, and contains detailed text extraction data. You only need the full text output, so you will processs the JSON results, extract the text output, and save it in new text files to be used later in the tutorial."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "WDLtiejKHug6"
+      },
+      "outputs": [],
+      "source": [
+        "import json\n",
+        "\n",
+        "print(\"Extracting text from Vision API output and saving it to text files\")\n",
+        "\n",
+        "ocr_blobs = storage_client.list_blobs(\n",
+        "    DESTINATION_BUCKET_NAME, prefix=DESTINATION_BUCKET_PATH\n",
+        ")\n",
+        "\n",
+        "output_bucket = storage_client.bucket(DESTINATION_BUCKET_NAME)\n",
+        "\n",
+        "# begin building the import file content\n",
+        "import_file_entries = []\n",
+        "\n",
+        "for ocr_blob in ocr_blobs:\n",
+        "    # Only process .json files, in case we previously processed files and had .txt files\n",
+        "    if ocr_blob.name.endswith(\".json\"):\n",
+        "        print(f\"Extracting text from {ocr_blob.name}\")\n",
+        "        # read each blob into a stream\n",
+        "        contents = ocr_blob.download_as_string()\n",
+        "        # load as JSON\n",
+        "        json_object = json.loads(contents)\n",
+        "        # extract text\n",
+        "        full_text = \"\"\n",
+        "        for response in json_object[\"responses\"]:\n",
+        "            if response[\"fullTextAnnotation\"]:\n",
+        "                full_text += response[\"fullTextAnnotation\"][\"text\"] + \"\\r\\n\"\n",
+        "\n",
+        "        # save as a blob\n",
+        "        output_blob_name = f\"{ocr_blob.name}.txt\"\n",
+        "        import_file_blob = output_bucket.blob(output_blob_name)\n",
+        "        import_file_blob.upload_from_string(full_text)\n",
+        "\n",
+        "        # create import file listing\n",
+        "        import_file_entry = {\n",
+        "            \"textGcsUri\": f\"gs://{DESTINATION_BUCKET_NAME}/{output_blob_name}\"\n",
+        "        }\n",
+        "\n",
+        "        import_file_entries.append(import_file_entry)\n",
+        "\n",
+        "print(\"Extraction completed!\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0a5aae0eab44"
+      },
+      "source": [
+        "#### Quick peek at extracted text files\n",
+        "\n",
+        "Next, you take a peek at the contents of one of the extracted text files."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "76ce5f57b1ae"
+      },
+      "outputs": [],
+      "source": [
+        "example = import_file_entries[0][\"textGcsUri\"]\n",
+        "\n",
+        "! gsutil cat {example}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "hqTLS_AmLWQP"
+      },
+      "source": [
+        "### Generate and save import file to be used in `Vertex AI Dataset` resource\n",
+        "\n",
+        "You will now build the import file that will be used to create the `Vertex AI Dataset` resource."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "_xFvOdQ_LWne"
+      },
+      "outputs": [],
+      "source": [
+        "IMPORT_FILE_PATH = \"import_file\"\n",
+        "\n",
+        "# Convert import file entries to JSON Lines format\n",
+        "import_file_content = \"\"\n",
+        "for entry in import_file_entries:\n",
+        "    import_file_content += json.dumps(entry) + \"\\n\"\n",
+        "\n",
+        "print(f\"Created import file based on {len(import_file_entries)} annotations\")\n",
+        "\n",
+        "# Upload content to GCS to be used in our next step\n",
+        "gcs_annotation_file_name = f\"{IMPORT_FILE_PATH}/import_file_{TIMESTAMP}.jsonl\"\n",
+        "import_file_blob = output_bucket.blob(gcs_annotation_file_name)\n",
+        "import_file_blob.upload_from_string(import_file_content)\n",
+        "\n",
+        "print(f\"Uploaded import file to {output_bucket.name}/{gcs_annotation_file_name}\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "6dVjFftOaKdw"
+      },
+      "source": [
+        "### Create an unlabelled `Vertex AI Dataset` resource\n",
+        "\n",
+        "Next, you create the `Dataset` resource using the `create` method for the `TextDataset` class, which takes the following parameters:\n",
+        "\n",
+        "- `display_name`: The human readable name for the `Dataset` resource.\n",
+        "- `gcs_source`: A list of one or more dataset index files to import the data items into the `Dataset` resource.\n",
+        "- `import_schema_uri`: The data labeling schema for the data items.\n",
+        "\n",
+        "This operation may take ten to twenty minutes."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "ciM9HLGCaOTJ"
+      },
+      "outputs": [],
+      "source": [
+        "print(\"Creating dataset ...\")\n",
+        "\n",
+        "dataset = aiplatform.TextDataset.create(\n",
+        "    display_name=\"Text Dataset \" + TIMESTAMP,\n",
+        "    gcs_source=[f\"gs://{output_bucket.name}/{gcs_annotation_file_name}\"],\n",
+        "    import_schema_uri=DATASET_IMPORT_SCHEMA,\n",
+        ")\n",
+        "\n",
+        "print(\"Completed!\")\n",
+        "\n",
+        "print(dataset.resource_name)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "2vagHf5T6Jd4"
+      },
+      "source": [
+        "**Congratulations, your dataset is now ready for annotations!**\n",
+        "\n",
+        "You have two options:\n",
+        "\n",
+        "*   Use Google Cloud Console to manually annotate the dataset in `Vertex AI`. Checkout [this link](https://cloud.google.com/vertex-ai/docs/datasets/label-using-console#entity-extraction) for more details on how to do so.\n",
+        "*   Create a labelling job to request data labelling. Check out [this link](https://cloud.google.com/vertex-ai/docs/datasets/data-labeling-job) and [this notebook](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage1/get_started_with_data_labeling.ipynb) for more details and examples.\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "cleanup:migration,new"
+      },
+      "source": [
+        "# Cleaning up\n",
+        "\n",
+        "To clean up all GCP resources used in this project, you can [delete the GCP\n",
+        "project](https://cloud.google.com/resource-manager/docs/creating-managing-projects#shutting_down_projects) you used for the tutorial.\n",
+        "\n",
+        "Otherwise, you can delete the individual resources you created in this tutorial.\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "aoJ18d8Y_jAy"
+      },
+      "outputs": [],
+      "source": [
+        "# Set this to true only if you'd like to delete your bucket\n",
+        "delete_bucket = False\n",
+        "\n",
+        "# Delete the dataset using the Vertex AI fully qualified identifier for the dataset\n",
+        "dataset.delete()\n",
+        "\n",
+        "# Delete the bucket created\n",
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil rm -r $BUCKET_URI"
+      ]
+    }
+  ],
+  "metadata": {
+    "accelerator": "GPU",
+    "colab": {
+      "collapsed_sections": [],
+      "name": "get_started_with_visionapi_and_vertex_datasets.ipynb",
+      "toc_visible": true
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

notebooks/community/ml_ops/stage1/mlops_data_management.ipynb

@@ -39,8 +39,14 @@
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://console.cloud.google.com/ai/platform/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage1/mlops_data_management.ipynb\">\n",
-        "      Open in Google Cloud Notebooks\n",
+        "        <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage1/mlops_data_management.ipynb\">\n",
+        "        <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\\\" alt=\"Colab logo\"> Run in Colab\n",
+        "        </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/ml_ops/stage1/mlops_data_management.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "      Open in Vertex AI Workbench\n",
         "    </a>\n",
         "  </td>\n",
         "</table>\n",
@@ -133,7 +139,20 @@
       },
       "outputs": [],
       "source": [
-        "ONCE_ONLY = False\n",
+        "import os\n",
+        "\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\") and not os.getenv(\"VIRTUAL_ENV\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
+        "\n",
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
+        "USER_FLAG = \"\"\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "\n",
+        "ONCE_ONLY = True\n",
         "if ONCE_ONLY:\n",
         "    ! pip3 install -U tensorflow==2.5 $USER_FLAG\n",
         "    ! pip3 install -U tensorflow-data-validation==1.2 $USER_FLAG\n",
@@ -178,6 +197,32 @@
         "    app.kernel.do_shutdown(True)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "84cd83853240"
+      },
+      "source": [
+        "## Before you begin\n",
+        "\n",
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI, BigQuery, Compute Engine and Cloud Storage APIs](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,bigquery,compute_component,storage_component).\n",
+        "\n",
+        "1. If you are running this notebook locally, you need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+        "\n",
+        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -254,7 +299,10 @@
       },
       "outputs": [],
       "source": [
-        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
+        "\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
       ]
     },
     {
@@ -281,6 +329,67 @@
         "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "77c385f0db59"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already authenticated. Skip this step.\n",
+        "\n",
+        "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\n",
+        "\n",
+        "1. **Click Create service account**.\n",
+        "\n",
+        "2. In the **Service account name** field, enter a name, and click **Create**.\n",
+        "\n",
+        "3. In the **Grant this service account access to project** section, click the Role drop-down list. Type \"Vertex AI\" into the filter box, and select **Vertex AI Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "4. Click Create. A JSON file that contains your key downloads to your local environment.\n",
+        "\n",
+        "5. Enter the path to your service account key as the GOOGLE_APPLICATION_CREDENTIALS variable in the cell below and run the cell."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "535223fa4b84"
+      },
+      "outputs": [],
+      "source": [
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
+        "IS_COLAB = False\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
+        "    \"DL_ANACONDA_HOME\"\n",
+        "):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        IS_COLAB = True\n",
+        "        from google.colab import auth as google_auth\n",
+        "\n",
+        "        google_auth.authenticate_user()\n",
+        "\n",
+        "    # If you are running this notebook locally, replace the string below with the\n",
+        "    # path to your service account key and run this cell to authenticate your GCP\n",
+        "    # account.\n",
+        "    elif not os.getenv(\"IS_TESTING\"):\n",
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -309,7 +418,8 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
+        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
+        "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
       ]
     },
     {
@@ -320,8 +430,9 @@
       },
       "outputs": [],
       "source": [
-        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"gs://[your-bucket-name]\":\n",
-        "    BUCKET_NAME = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
+        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"[your-bucket-name]\":\n",
+        "    BUCKET_NAME = PROJECT_ID + \"aip-\" + TIMESTAMP\n",
+        "    BUCKET_URI = \"gs://\" + BUCKET_NAME"
       ]
     },
     {
@@ -341,7 +452,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION $BUCKET_NAME"
+        "! gsutil mb -l $REGION $BUCKET_URI"
       ]
     },
     {
@@ -361,7 +472,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil ls -al $BUCKET_NAME"
+        "! gsutil ls -al $BUCKET_URI"
       ]
     },
     {
@@ -516,7 +627,7 @@
       },
       "outputs": [],
       "source": [
-        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_NAME)"
+        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_URI)"
       ]
     },
     {
@@ -757,7 +868,7 @@
         "dataset = aip.TabularDataset.create(\n",
         "    display_name=\"Chicago Taxi\" + \"_\" + TIMESTAMP,\n",
         "    bq_source=[IMPORT_FILE],\n",
-        "    labels={\"user_metadata\": BUCKET_NAME[5:]},\n",
+        "    labels={\"user_metadata\": BUCKET_NAME},\n",
         ")\n",
         "\n",
         "label_column = \"tip_bin\"\n",
@@ -949,9 +1060,9 @@
       },
       "outputs": [],
       "source": [
-        "STATISTICS_SCHEMA = BUCKET_NAME + \"/statistics.jsonl\"\n",
+        "STATISTICS_SCHEMA = BUCKET_URI + \"/statistics.jsonl\"\n",
         "\n",
-        "tfdv.write_stats_text(stats, BUCKET_NAME + \"/statistics.jsonl\")\n",
+        "tfdv.write_stats_text(stats, BUCKET_URI + \"/statistics.jsonl\")\n",
         "\n",
         "with tf.io.gfile.GFile(\n",
         "    \"gs://\" + dataset.labels[\"user_metadata\"] + \"/metadata.jsonl\", \"r\"\n",
@@ -964,7 +1075,7 @@
         ") as f:\n",
         "    json.dump(metadata, f)\n",
         "\n",
-        "!gsutil cat $BUCKET_NAME/metadata.jsonl"
+        "! gsutil cat $BUCKET_URI/metadata.jsonl"
       ]
     },
     {
@@ -1011,7 +1122,7 @@
       },
       "outputs": [],
       "source": [
-        "SCHEMA_LOCATION = BUCKET_NAME + \"/schema.txt\"\n",
+        "SCHEMA_LOCATION = BUCKET_URI + \"/schema.txt\"\n",
         "\n",
         "# When running Apache Beam directly (file is directly accessed)\n",
         "tfdv.write_schema_text(output_path=SCHEMA_LOCATION, schema=schema)\n",
@@ -1049,7 +1160,7 @@
         ") as f:\n",
         "    json.dump(metadata, f)\n",
         "\n",
-        "!gsutil cat $BUCKET_NAME/metadata.jsonl"
+        "! gsutil cat $BUCKET_URI/metadata.jsonl"
       ]
     },
     {
@@ -1372,10 +1483,10 @@
         "            )\n",
         "\n",
         "\n",
-        "EXPORTED_JSONL_PREFIX = os.path.join(BUCKET_NAME, \"exported_data/jsonl\")\n",
-        "EXPORTED_TFREC_PREFIX = os.path.join(BUCKET_NAME, \"exported_data/tfrec\")\n",
-        "TRANSFORMED_DATA_PREFIX = os.path.join(BUCKET_NAME, \"transformed_data\")\n",
-        "TRANSFORM_ARTIFACTS_DIR = os.path.join(BUCKET_NAME, \"transformed_artifacts\")\n",
+        "EXPORTED_JSONL_PREFIX = os.path.join(BUCKET_URI, \"exported_data/jsonl\")\n",
+        "EXPORTED_TFREC_PREFIX = os.path.join(BUCKET_URI, \"exported_data/tfrec\")\n",
+        "TRANSFORMED_DATA_PREFIX = os.path.join(BUCKET_URI, \"transformed_data\")\n",
+        "TRANSFORM_ARTIFACTS_DIR = os.path.join(BUCKET_URI, \"transformed_artifacts\")\n",
         "\n",
         "QUERY_STRING = \"SELECT * FROM {} LIMIT 300000\".format(BQ_TABLE)\n",
         "JOB_NAME = \"chicago\" + TIMESTAMP\n",
@@ -1388,7 +1499,7 @@
         "    \"transform_artifact_dir\": TRANSFORM_ARTIFACTS_DIR,\n",
         "    \"exported_jsonl_prefix\": EXPORTED_JSONL_PREFIX,\n",
         "    \"exported_tfrec_prefix\": EXPORTED_TFREC_PREFIX,\n",
-        "    \"temp_location\": os.path.join(BUCKET_NAME, \"temp\"),\n",
+        "    \"temp_location\": os.path.join(BUCKET_URI, \"temp\"),\n",
         "    \"project\": PROJECT_ID,\n",
         "    \"region\": REGION,\n",
         "    \"setup_file\": \"./setup.py\",\n",
@@ -1459,7 +1570,7 @@
         ") as f:\n",
         "    json.dump(metadata, f)\n",
         "\n",
-        "!gsutil cat $BUCKET_NAME/metadata.jsonl"
+        "! gsutil cat $BUCKET_URI/metadata.jsonl"
       ]
     },
     {
@@ -1473,17 +1584,9 @@
         "To clean up all Google Cloud resources used in this project, you can [delete the Google Cloud\n",
         "project](https://cloud.google.com/resource-manager/docs/creating-managing-projects#shutting_down_projects) you used for the tutorial.\n",
         "\n",
-        "Otherwise, you can delete the individual resources you created in this tutorial:\n",
+        "Otherwise, you can delete the individual resources you created in this tutorial.\n",
         "\n",
-        "- Dataset\n",
-        "- Pipeline\n",
-        "- Model\n",
-        "- Endpoint\n",
-        "- AutoML Training Job\n",
-        "- Batch Job\n",
-        "- Custom Job\n",
-        "- Hyperparameter Tuning Job\n",
-        "- Cloud Storage Bucket"
+        "*Note:* stage2/mlops_experimentation is dependent on the resources created by this stage1 notebook."
       ]
     },
     {
@@ -1504,8 +1607,8 @@
         "    except Exception as e:\n",
         "        print(e)\n",
         "\n",
-        "    if \"BUCKET_NAME\" in globals():\n",
-        "        ! gsutil rm -r $BUCKET_NAME"
+        "    if \"BUCKET_URI\" in globals():\n",
+        "        ! gsutil rm -r $BUCKET_URI"
       ]
     }
   ],

notebooks/community/ml_ops/stage2/README.md

@@ -25,7 +25,11 @@ The second stage in MLOps is experimenting in developing one or more baseline mo
 - Use the What-if-Tool (WIT) to explore how the trained model would make predictions in different scenarios.
 
 
-<img src='stage2.png'>
+<img src='stage2v3.png'>
+<br/>
+<br/>
+<br/>
+<img src='stage2.2v1.png'>
 
 ## Notebooks
 
@@ -115,6 +119,32 @@ The steps performed include:
 - Train a R model using `Vertex AI Trainingh` service with the R-to-Python training package.
 ```
 
+[Get Started with Custom Training Packages (R) and Deployment in R environment](get_started_vertex_training_r_using_r_kernel.ipynb)
+```
+The steps performed include:
+
+- Create a custom R training script
+- Create a custom R serving script
+- Create a custom R deployment (serving) container.
+- Train the model using `Vertex AI` custom training.
+- Create an `Endpoint` resource.
+- Deploy the `Model` resource (trained R model) to the `Endpoint` resource.
+- Make an online prediction.
+```
+
+[Get Started with Custom Training Packages (LightGBM)](get_started_vertex_training_lightgbm.ipynb)
+
+```
+The steps performed include:
+
+- Training using a Python package.
+- Save the model artifacts to Cloud Storage using GCSFuse.
+- Construct a FastAPI prediction server.
+- Construct a Dockerfile deployment image.
+- Test the deployment image locally.
+- Create a `Vertex AI Model` resource.
+```
+
 [Get Started with Distributed Training](get_started_vertex_distributed_training.ipynb)
 
 ```
@@ -153,12 +183,13 @@ The steps performed include:
 ```
 The steps performed include:
 
-- Create a local BQ table in your project.
-- Train a BQML model.
-- Evaluate the BQML model.
-- Export the BQML model as a cloud model.
-- Upload the exported model as a Vertex AI Model resource.
-- Hyperparameter tune a BQML model with Vertex AI Vizier.
+- Create a local BigQuery table in your project
+- Train a BQML model
+- Evaluate the BQML model
+- Export the BQML model as a cloud model
+- Upload the exported model as a `Vertex AI Model` resource
+- Hyperparameter tune a BQML model with `Vertex AI Vizier`
+- Automatically register a BQML model to `Vertex AI Model Registry`
 ```
 
 [Get Started with Vertex Feature Store](get_started_vertex_feature_store.ipynb)
@@ -200,6 +231,34 @@ The steps performed include:
     - Save model artifacts and upload as Vertex AI Model resource.
 ```
 
+[Get Started with Vertex AI TabNet builtin algorithm](get_started_with_tabnet.ipynb)
+```
+The steps performed include:
+
+- Get the training data.
+- Configure training parameters for the Vertex AI TabNet container.
+- Train the model using Vertex AI Training using CSV data.
+- Upload the model as a Vertex AI Model resource.
+- Deploy the Vertex AI Model resource to a Vertex AI Endpoint resource.
+- Make a prediction with the deployed model.
+- Hyperparameter tuning the Vertex AI TabNet model.
+- Train the model using Vertex AI Training using BigQuery table.
+```
+
+[Get Started with Vision API and AutoML](get_started_with_visionapi_and_automl.ipynb)
+```
+The steps performed include:
+
+- Preprocess training files using `Vision AI` APIs to extract the text from PDF files.
+- Create a custom import file that includes annotation data based on the sample `BigQuery` dataset.
+- Create a `Vertex AI Dataset` resource.
+- Train the model.
+- View the model evaluation.
+- Deploy the `Vertex AI Model` resource to a serving `Endpoint` resource.
+- Make a prediction.
+- Undeploy the `Model`.
+```
+
 
 ### E2E Stage Example
 

notebooks/community/ml_ops/stage2/get_started_automl_training.ipynb

@@ -8,7 +8,7 @@
       },
       "outputs": [],
       "source": [
-        "# Copyright 2021 Google LLC\n",
+        "# Copyright 2022 Google LLC\n",
         "#\n",
         "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
         "# you may not use this file except in compliance with the License.\n",
@@ -39,8 +39,14 @@
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://console.cloud.google.com/ai/platform/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_automl_training.ipynb\">\n",
-        "      Open in Google Cloud Notebooks\n",
+        "        <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_automl_training.ipynb\">\n",
+        "        <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "        </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/ml_ops/stage2/get_started_automl_training.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "      Open in Vertex AI Workbench\n",
         "    </a>\n",
         "  </td>\n",
         "</table>\n",
@@ -69,7 +75,7 @@
         "\n",
         "#### Image\n",
         "\n",
-        "The image dataset used for this tutorial is the [Flowers dataset](https://www.tensorflow.org/datasets/catalog/tf_flowers) from [TensorFlow Datasets](https://www.tensorflow.org/datasets/catalog/overview). The version of the dataset you will use in this tutorial is stored in a public Cloud Storage bucket. The trained model predicts the type of flower an image is from a class of five flowers: daisy, dandelion, rose, sunflower, or tulip."
+        "The image dataset used for this tutorial is the [Flowers dataset](https://www.tensorflow.org/datasets/catalog/tf_flowers) from [TensorFlow Datasets](https://www.tensorflow.org/datasets/catalog/overview). The version of the dataset you will use in this tutorial is stored in a public Cloud Storage bucket. The trained model predicts the type of flower in a given image from a class of five flowers: daisy, dandelion, rose, sunflower, or tulip."
       ]
     },
     {
@@ -102,7 +108,7 @@
       "source": [
         "#### Video\n",
         "\n",
-        "The video dataset used for this tutorial is the golf swing recognition portion of the [Human Motion dataset](https://todo) from [MIT](http://cbcl.mit.edu/publications/ps/Kuehne_etal_iccv11.pdf). The version of the dataset you will use in this tutorial is stored in a public #(GCS) bucket. The trained model will predict the start frame where a golf swing begins."
+        "The video dataset used for this tutorial is the golf swing recognition portion of the [Human Motion dataset](https://todo) from [MIT](http://cbcl.mit.edu/publications/ps/Kuehne_etal_iccv11.pdf). The version of the dataset you will use in this tutorial is stored in a public Cloud Storage bucket. The trained model will predict the start frame where a golf swing begins."
       ]
     },
     {
@@ -121,12 +127,12 @@
         "\n",
         "The steps performed include:\n",
         "\n",
-        "- Train an image model.\n",
-        "- Export the image model as an edge model.\n",
-        "- Train a tabular model.\n",
-        "- Export the tabular model as a cloud model.\n",
-        "- Train a text model.\n",
-        "- Train a video model."
+        "- Train an image model\n",
+        "- Export the image model as an edge model\n",
+        "- Train a tabular model\n",
+        "- Export the tabular model as a cloud model\n",
+        "- Train a text model\n",
+        "- Train a video model"
       ]
     },
     {
@@ -139,9 +145,24 @@
         "\n",
         "When doing E2E MLOps on Google Cloud, the following are best practices for when to use AutoML:\n",
         "\n",
-        "**You have a limited amount of training data**\n",
+        "* **You have a limited amount of training data**\n",
         "\n",
-        "**You want to establish a baseline metric before experimenting with a custom model**"
+        "* **You want to establish a baseline metric before experimenting with a custom model**"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "fb3451ce8e47"
+      },
+      "source": [
+        "### Costs\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "- Vertex AI\n",
+        "- Cloud Storage\n",
+        "\n",
+        "Learn about [Vertex AI pricing](https://cloud.google.com/vertex-ai/pricing) and [Cloud Storage pricing](https://cloud.google.com/storage/pricing) and use the [Pricing Calculator](https://cloud.google.com/products/calculator/) to generate a cost estimate based on your projected usage."
       ]
     },
     {
@@ -152,7 +173,7 @@
       "source": [
         "## Installations\n",
         "\n",
-        "Install *one time* the packages for executing the MLOps notebooks."
+        "Install the packages required for executing this notebook."
       ]
     },
     {
@@ -163,24 +184,23 @@
       },
       "outputs": [],
       "source": [
-        "ONCE_ONLY = False\n",
-        "if ONCE_ONLY:\n",
-        "    ! pip3 install -U tensorflow==2.5 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-data-validation==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-transform==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-io==0.18 $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-aiplatform[tensorboard] $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-pipeline-components $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-bigquery $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-logging $USER_FLAG\n",
-        "    ! pip3 install --upgrade apache-beam[gcp] $USER_FLAG\n",
-        "    ! pip3 install --upgrade pyarrow $USER_FLAG\n",
-        "    ! pip3 install --upgrade cloudml-hypertune $USER_FLAG\n",
-        "    ! pip3 install --upgrade kfp $USER_FLAG\n",
-        "    ! pip3 install --upgrade torchvision $USER_FLAG\n",
-        "    ! pip3 install --upgrade rpy2 $USER_FLAG\n",
-        "    ! pip3 install --upgrade python-tabulate $USER_FLAG\n",
-        "    ! pip3 install -U opencv-python-headless==4.5.2.52 $USER_FLAG"
+        "import os\n",
+        "\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\") and not os.getenv(\"VIRTUAL_ENV\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
+        "\n",
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
+        "USER_FLAG = \"\"\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "\n",
+        "# Install the packages\n",
+        "\n",
+        "! pip3 install --upgrade google-cloud-aiplatform $USER_FLAG -q\n",
+        "! pip3 install --upgrade google-cloud-storage $USER_FLAG -q"
       ]
     },
     {
@@ -218,6 +238,23 @@
         "id": "project_id"
       },
       "source": [
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI, Compute Engine and Cloud Storage APIs](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,compute_component,storage_component).\n",
+        "\n",
+        "1. If you are running this notebook locally, you need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+        "\n",
+        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands.\n",
+        "\n",
         "#### Set your project ID\n",
         "\n",
         "**If you don't know your project ID**, you may be able to get your project ID using `gcloud`."
@@ -288,7 +325,10 @@
       },
       "outputs": [],
       "source": [
-        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
+        "\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
       ]
     },
     {
@@ -315,6 +355,67 @@
         "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "3ffa6b6c7cdb"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already authenticated. Skip this step.\n",
+        "\n",
+        "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\n",
+        "\n",
+        "1. **Click Create service account**.\n",
+        "\n",
+        "2. In the **Service account name** field, enter a name, and click **Create**.\n",
+        "\n",
+        "3. In the **Grant this service account access to project** section, click the Role drop-down list. Type \"Vertex AI\" into the filter box, and select **Vertex AI Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "4. Click Create. A JSON file that contains your key downloads to your local environment.\n",
+        "\n",
+        "5. Enter the path to your service account key as the GOOGLE_APPLICATION_CREDENTIALS variable in the cell below and run the cell."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "2b72272258fc"
+      },
+      "outputs": [],
+      "source": [
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
+        "IS_COLAB = False\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
+        "    \"DL_ANACONDA_HOME\"\n",
+        "):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        IS_COLAB = True\n",
+        "        from google.colab import auth as google_auth\n",
+        "\n",
+        "        google_auth.authenticate_user()\n",
+        "\n",
+        "    # If you are running this notebook locally, replace the string below with the\n",
+        "    # path to your service account key and run this cell to authenticate your GCP\n",
+        "    # account.\n",
+        "    elif not os.getenv(\"IS_TESTING\"):\n",
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -415,7 +516,7 @@
       },
       "outputs": [],
       "source": [
-        "import google.cloud.aiplatform as aip"
+        "import google.cloud.aiplatform as aiplatform"
       ]
     },
     {
@@ -437,7 +538,7 @@
       },
       "outputs": [],
       "source": [
-        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_URI)"
+        "aiplatform.init(project=PROJECT_ID, staging_bucket=BUCKET_URI)"
       ]
     },
     {
@@ -468,7 +569,7 @@
       "source": [
         "## AutoML image models\n",
         "\n",
-        "AutoML can train the following types of models:\n",
+        "AutoML can train the following types of image models:\n",
         "\n",
         "- classification\n",
         "- objection detection\n",
@@ -524,10 +625,7 @@
       },
       "outputs": [],
       "source": [
-        "if \"IMPORT_FILES\" in globals():\n",
-        "    FILE = IMPORT_FILES[0]\n",
-        "else:\n",
-        "    FILE = IMPORT_FILE\n",
+        "FILE = IMPORT_FILE\n",
         "\n",
         "count = ! gsutil cat $FILE | wc -l\n",
         "print(\"Number of Examples\", int(count[0]))\n",
@@ -565,10 +663,10 @@
       },
       "outputs": [],
       "source": [
-        "dataset = aip.ImageDataset.create(\n",
+        "dataset = aiplatform.ImageDataset.create(\n",
         "    display_name=\"flowers_\" + TIMESTAMP,\n",
         "    gcs_source=[IMPORT_FILE],\n",
-        "    import_schema_uri=aip.schema.dataset.ioformat.image.single_label_classification,\n",
+        "    import_schema_uri=aiplatform.schema.dataset.ioformat.image.single_label_classification,\n",
         ")\n",
         "\n",
         "print(dataset.resource_name)"
@@ -613,7 +711,7 @@
       },
       "outputs": [],
       "source": [
-        "dag = aip.AutoMLImageTrainingJob(\n",
+        "dag = aiplatform.AutoMLImageTrainingJob(\n",
         "    display_name=\"flowers_\" + TIMESTAMP,\n",
         "    prediction_type=\"classification\",\n",
         "    multi_label=False,\n",
@@ -632,14 +730,14 @@
       "source": [
         "#### Run the training pipeline\n",
         "\n",
-        "Next, you run the DAG to start the training job by invoking the method `run`, with the following parameters:\n",
+        "Next, you run the created DAG to start the training job by invoking the method `run`, with the following parameters:\n",
         "\n",
         "- `dataset`: The `Dataset` resource to train the model.\n",
         "- `model_display_name`: The human readable name for the trained model.\n",
         "- `training_fraction_split`: The percentage of the dataset to use for training.\n",
         "- `test_fraction_split`: The percentage of the dataset to use for test (holdout data).\n",
         "- `validation_fraction_split`: The percentage of the dataset to use for validation.\n",
-        "- `budget_milli_node_hours`: (optional) Maximum training time specified in unit of millihours (1000 = hour).\n",
+        "- `budget_milli_node_hours`: (optional) Maximum training time specified in unit of milli node-hours (1000 = node-hour).\n",
         "- `disable_early_stopping`: If `True`, training maybe completed before using the entire budget if the service believes it cannot further improve on the model objective measurements.\n",
         "\n",
         "The `run` method when completed returns the `Model` resource.\n",
@@ -673,9 +771,8 @@
       },
       "source": [
         "## Review model evaluation scores\n",
-        "After your model has finished training, you can review the evaluation scores for it.\n",
         "\n",
-        "First, you need to get a reference to the new model. As with datasets, you can either use the reference to the model variable you created when you deployed the model or you can list all of the models in your project."
+        "After your model training has finished, you can review the evaluation scores for it using the `list_model_evaluations()` method. This method will return an iterator for each evaluation slice."
       ]
     },
     {
@@ -686,18 +783,10 @@
       },
       "outputs": [],
       "source": [
-        "# Get model resource ID\n",
-        "models = aip.Model.list(filter=\"display_name=flowers_\" + TIMESTAMP)\n",
+        "model_evaluations = model.list_model_evaluations()\n",
         "\n",
-        "# Get a reference to the Model Service client\n",
-        "client_options = {\"api_endpoint\": f\"{REGION}-aiplatform.googleapis.com\"}\n",
-        "model_service_client = aip.gapic.ModelServiceClient(client_options=client_options)\n",
-        "\n",
-        "model_evaluations = model_service_client.list_model_evaluations(\n",
-        "    parent=models[0].resource_name\n",
-        ")\n",
-        "model_evaluation = list(model_evaluations)[0]\n",
-        "print(model_evaluation)"
+        "for model_evaluation in model_evaluations:\n",
+        "    print(model_evaluation.to_dict())"
       ]
     },
     {
@@ -741,7 +830,7 @@
       "source": [
         "### Get test item\n",
         "\n",
-        "You will use an arbitrary example out of the dataset as a test item. Don't be concerned that the example was likely used in training the model -- we just want to demonstrate how to make a prediction."
+        "You will use an arbitrary example out of the dataset as a test item. Don't be concerned that the example was likely used in training the model. You are just looking at how to make a prediction."
       ]
     },
     {
@@ -773,7 +862,7 @@
         "\n",
         "#### Request\n",
         "\n",
-        "Since in this example your test item is in a Cloud Storage bucket, you open and read the contents of the image using `tf.io.gfile.Gfile()`. To pass the test data to the prediction service, you encode the bytes into base64 -- which makes the content safe from modification while transmitting binary data over the network.\n",
+        "Since your test item is in a public Cloud Storage bucket in this example, you copy it to your bucket and read the contents of the image using `Cloud Storage SDK`. To pass the test data to the prediction service, you encode the bytes into base64 which makes the content safe from modification while transmitting binary data over the network.\n",
         "\n",
         "The format of each instance is:\n",
         "\n",
@@ -795,14 +884,46 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "predict_request:mbsdk,icn"
+        "id": "1c1d53e89beb"
       },
       "outputs": [],
       "source": [
         "import base64\n",
         "\n",
+        "from google.cloud import storage\n",
+        "\n",
+        "# Copy the test image to the Cloud storage bucket as \"test.jpg\"\n",
+        "test_image_local = \"{}/test.jpg\".format(BUCKET_URI)\n",
+        "! gsutil cp $test_item $test_image_local\n",
+        "\n",
+        "# Download the test image in bytes format\n",
+        "storage_client = storage.Client(project=PROJECT_ID)\n",
+        "bucket = storage_client.bucket(bucket_name=BUCKET_NAME)\n",
+        "test_content = bucket.get_blob(\"test.jpg\").download_as_bytes()\n",
+        "\n",
+        "# The format of each instance should conform to the deployed model's prediction input schema.\n",
+        "instances = [{\"content\": base64.b64encode(test_content).decode(\"utf-8\")}]\n",
+        "\n",
+        "prediction = endpoint.predict(instances=instances)\n",
+        "\n",
+        "print(prediction)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "3b1b67898533"
+      },
+      "source": [
+        "#### Alternate method using [GFile](https://www.tensorflow.org/api_docs/python/tf/io/gfile/GFile)\n",
+        "\n",
+        "Alternatively, [GFile](https://www.tensorflow.org/api_docs/python/tf/io/gfile/GFile) method from tensorflow-io library can be used to read the data from Cloud storage directly. The following code snippet does the same :\n",
+        "\n",
+        "```\n",
+        "import base64\n",
         "import tensorflow as tf\n",
         "\n",
+        "# Read the test file using GFile\n",
         "with tf.io.gfile.GFile(test_item, \"rb\") as f:\n",
         "    content = f.read()\n",
         "\n",
@@ -811,7 +932,9 @@
         "\n",
         "prediction = endpoint.predict(instances=instances)\n",
         "\n",
-        "print(prediction)"
+        "print(prediction)\n",
+        "```\n",
+        "Nevertheless, `tf.io.gfile.GFile` supports multiple file system implementations, including local files, Google Cloud Storage (using a gs:// prefix), and HDFS (using an hdfs:// prefix)."
       ]
     },
     {
@@ -1007,7 +1130,7 @@
       },
       "outputs": [],
       "source": [
-        "dataset = aip.TabularDataset.create(\n",
+        "dataset = aiplatform.TabularDataset.create(\n",
         "    display_name=\"gsod_\" + TIMESTAMP,\n",
         "    bq_source=[IMPORT_FILE],\n",
         "    labels={\"user_metadata\": BUCKET_NAME},\n",
@@ -1066,9 +1189,7 @@
         "  - regression:\n",
         "    - `minimize-rmse`\n",
         "    - `minimize-mae`\n",
-        "    - `minimize-rmsle`\n",
-        "\n",
-        "The instantiated object is the DAG (directed acyclic graph) for the training pipeline."
+        "    - `minimize-rmsle`"
       ]
     },
     {
@@ -1079,7 +1200,7 @@
       },
       "outputs": [],
       "source": [
-        "dag = aip.AutoMLTabularTrainingJob(\n",
+        "dag = aiplatform.AutoMLTabularTrainingJob(\n",
         "    display_name=\"gsod_\" + TIMESTAMP,\n",
         "    optimization_prediction_type=\"regression\",\n",
         "    optimization_objective=\"minimize-rmse\",\n",
@@ -1097,7 +1218,7 @@
       "source": [
         "#### Run the training pipeline\n",
         "\n",
-        "Next, you run the DAG to start the training job by invoking the method `run`, with the following parameters:\n",
+        "Next, you run the created DAG to start the training job by invoking the method `run`, with the following parameters:\n",
         "\n",
         "- `dataset`: The `Dataset` resource to train the model.\n",
         "- `model_display_name`: The human readable name for the trained model.\n",
@@ -1140,9 +1261,8 @@
       },
       "source": [
         "## Review model evaluation scores\n",
-        "After your model has finished training, you can review the evaluation scores for it.\n",
         "\n",
-        "First, you need to get a reference to the new model. As with datasets, you can either use the reference to the model variable you created when you deployed the model or you can list all of the models in your project."
+        "After your model training has finished, you can review the evaluation scores for it using the `list_model_evaluations()` method. This method will return an iterator for each evaluation slice."
       ]
     },
     {
@@ -1153,18 +1273,10 @@
       },
       "outputs": [],
       "source": [
-        "# Get model resource ID\n",
-        "models = aip.Model.list(filter=\"display_name=gsod_\" + TIMESTAMP)\n",
+        "model_evaluations = model.list_model_evaluations()\n",
         "\n",
-        "# Get a reference to the Model Service client\n",
-        "client_options = {\"api_endpoint\": f\"{REGION}-aiplatform.googleapis.com\"}\n",
-        "model_service_client = aip.gapic.ModelServiceClient(client_options=client_options)\n",
-        "\n",
-        "model_evaluations = model_service_client.list_model_evaluations(\n",
-        "    parent=models[0].resource_name\n",
-        ")\n",
-        "model_evaluation = list(model_evaluations)[0]\n",
-        "print(model_evaluation)"
+        "for model_evaluation in model_evaluations:\n",
+        "    print(model_evaluation.to_dict())"
       ]
     },
     {
@@ -1370,10 +1482,7 @@
       },
       "outputs": [],
       "source": [
-        "if \"IMPORT_FILES\" in globals():\n",
-        "    FILE = IMPORT_FILES[0]\n",
-        "else:\n",
-        "    FILE = IMPORT_FILE\n",
+        "FILE = IMPORT_FILE\n",
         "\n",
         "count = ! gsutil cat $FILE | wc -l\n",
         "print(\"Number of Examples\", int(count[0]))\n",
@@ -1411,10 +1520,10 @@
       },
       "outputs": [],
       "source": [
-        "dataset = aip.TextDataset.create(\n",
+        "dataset = aiplatform.TextDataset.create(\n",
         "    display_name=\"happydb_\" + TIMESTAMP,\n",
         "    gcs_source=[IMPORT_FILE],\n",
-        "    import_schema_uri=aip.schema.dataset.ioformat.text.single_label_classification,\n",
+        "    import_schema_uri=aiplatform.schema.dataset.ioformat.text.single_label_classification,\n",
         ")\n",
         "\n",
         "print(dataset.resource_name)"
@@ -1440,9 +1549,7 @@
         "  - `sentiment`: A text sentiment analysis model.\n",
         "  - `extraction`: A text entity extraction model.\n",
         "- `multi_label`: If a classification task, whether single (False) or multi-labeled (True).\n",
-        "- `sentiment_max`: If a sentiment analysis task, the maximum sentiment value.\n",
-        "\n",
-        "The instantiated object is the DAG (directed acyclic graph) for the training pipeline."
+        "- `sentiment_max`: If a sentiment analysis task, the maximum sentiment value.\n"
       ]
     },
     {
@@ -1453,7 +1560,7 @@
       },
       "outputs": [],
       "source": [
-        "dag = aip.AutoMLTextTrainingJob(\n",
+        "dag = aiplatform.AutoMLTextTrainingJob(\n",
         "    display_name=\"happydb_\" + TIMESTAMP,\n",
         "    prediction_type=\"classification\",\n",
         "    multi_label=False,\n",
@@ -1470,7 +1577,7 @@
       "source": [
         "#### Run the training pipeline\n",
         "\n",
-        "Next, you run the DAG to start the training job by invoking the method `run`, with the following parameters:\n",
+        "Next, you run the created DAG to start the training job by invoking the method `run`, with the following parameters:\n",
         "\n",
         "- `dataset`: The `Dataset` resource to train the model.\n",
         "- `model_display_name`: The human readable name for the trained model.\n",
@@ -1507,9 +1614,8 @@
       },
       "source": [
         "## Review model evaluation scores\n",
-        "After your model has finished training, you can review the evaluation scores for it.\n",
         "\n",
-        "First, you need to get a reference to the new model. As with datasets, you can either use the reference to the model variable you created when you deployed the model or you can list all of the models in your project."
+        "After your model training has finished, you can review the evaluation scores for it using the `list_model_evaluations()` method. This method will return an iterator for each evaluation slice."
       ]
     },
     {
@@ -1520,18 +1626,10 @@
       },
       "outputs": [],
       "source": [
-        "# Get model resource ID\n",
-        "models = aip.Model.list(filter=\"display_name=happydb_\" + TIMESTAMP)\n",
+        "model_evaluations = model.list_model_evaluations()\n",
         "\n",
-        "# Get a reference to the Model Service client\n",
-        "client_options = {\"api_endpoint\": f\"{REGION}-aiplatform.googleapis.com\"}\n",
-        "model_service_client = aip.gapic.ModelServiceClient(client_options=client_options)\n",
-        "\n",
-        "model_evaluations = model_service_client.list_model_evaluations(\n",
-        "    parent=models[0].resource_name\n",
-        ")\n",
-        "model_evaluation = list(model_evaluations)[0]\n",
-        "print(model_evaluation)"
+        "for model_evaluation in model_evaluations:\n",
+        "    print(model_evaluation.to_dict())"
       ]
     },
     {
@@ -1706,10 +1804,7 @@
       },
       "outputs": [],
       "source": [
-        "if \"IMPORT_FILES\" in globals():\n",
-        "    FILE = IMPORT_FILES[0]\n",
-        "else:\n",
-        "    FILE = IMPORT_FILE\n",
+        "FILE = IMPORT_FILE\n",
         "\n",
         "count = ! gsutil cat $FILE | wc -l\n",
         "print(\"Number of Examples\", int(count[0]))\n",
@@ -1746,10 +1841,10 @@
       },
       "outputs": [],
       "source": [
-        "dataset = aip.VideoDataset.create(\n",
+        "dataset = aiplatform.VideoDataset.create(\n",
         "    display_name=\"human_motion_\" + TIMESTAMP,\n",
         "    gcs_source=[IMPORT_FILE],\n",
-        "    import_schema_uri=aip.schema.dataset.ioformat.video.classification,\n",
+        "    import_schema_uri=aiplatform.schema.dataset.ioformat.video.classification,\n",
         ")\n",
         "\n",
         "print(dataset.resource_name)"
@@ -1773,9 +1868,7 @@
         "- `prediction_type`: The type task to train the model for.\n",
         "  - `classification`: A video classification model.\n",
         "  - `object_tracking`: A video object tracking model.\n",
-        "  - `action_recognition`: A video action recognition model.\n",
-        "\n",
-        "The instantiated object is the DAG (directed acyclic graph) for the training pipeline."
+        "  - `action_recognition`: A video action recognition model."
       ]
     },
     {
@@ -1786,7 +1879,7 @@
       },
       "outputs": [],
       "source": [
-        "dag = aip.AutoMLVideoTrainingJob(\n",
+        "dag = aiplatform.AutoMLVideoTrainingJob(\n",
         "    display_name=\"human_motion_\" + TIMESTAMP,\n",
         "    prediction_type=\"classification\",\n",
         ")\n",
@@ -1802,7 +1895,7 @@
       "source": [
         "#### Run the training pipeline\n",
         "\n",
-        "Next, you run the DAG to start the training job by invoking the method `run`, with the following parameters:\n",
+        "Next, you run the created DAG to start the training job by invoking the method `run`, with the following parameters:\n",
         "\n",
         "- `dataset`: The `Dataset` resource to train the model.\n",
         "- `model_display_name`: The human readable name for the trained model.\n",
@@ -1837,9 +1930,8 @@
       },
       "source": [
         "## Review model evaluation scores\n",
-        "After your model has finished training, you can review the evaluation scores for it.\n",
         "\n",
-        "First, you need to get a reference to the new model. As with datasets, you can either use the reference to the model variable you created when you deployed the model or you can list all of the models in your project."
+        "After your model training has finished, you can review the evaluation scores for it using the `list_model_evaluations()` method. This method will return an iterator for each evaluation slice."
       ]
     },
     {
@@ -1850,18 +1942,10 @@
       },
       "outputs": [],
       "source": [
-        "# Get model resource ID\n",
-        "models = aip.Model.list(filter=\"display_name=human_motion_\" + TIMESTAMP)\n",
+        "model_evaluations = model.list_model_evaluations()\n",
         "\n",
-        "# Get a reference to the Model Service client\n",
-        "client_options = {\"api_endpoint\": f\"{REGION}-aiplatform.googleapis.com\"}\n",
-        "model_service_client = aip.gapic.ModelServiceClient(client_options=client_options)\n",
-        "\n",
-        "model_evaluations = model_service_client.list_model_evaluations(\n",
-        "    parent=models[0].resource_name\n",
-        ")\n",
-        "model_evaluation = list(model_evaluations)[0]\n",
-        "print(model_evaluation)"
+        "for model_evaluation in model_evaluations:\n",
+        "    print(model_evaluation.to_dict())"
       ]
     },
     {
@@ -1930,9 +2014,10 @@
       },
       "outputs": [],
       "source": [
-        "delete_bucket = True\n",
+        "# Set this to true only if you'd like to delete your bucket\n",
+        "delete_bucket = False\n",
         "\n",
-        "if delete_bucket and \"BUCKET_URI\" in globals():\n",
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
         "    ! gsutil rm -r $BUCKET_URI"
       ]
     }

notebooks/community/ml_ops/stage2/get_started_bqml_training.ipynb

@@ -38,8 +38,13 @@
         "      View on GitHub\n",
         "    </a>\n",
         "  </td>\n",
+        "    <td>\n",
+        "        <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_bqml_training.ipynb\">\n",
+        "        <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\\\" alt=\"Colab logo\"> Run in Colab\n",
+        "        </a>\n",
+        "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_bqml_training.ipynb\">\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_bqml_training.ipynb\">\n",
         "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
         "      Open in Vertex AI Workbench\n",
         "    </a>\n",
@@ -93,8 +98,9 @@
         "- Train a BQML model\n",
         "- Evaluate the BQML model\n",
         "- Export the BQML model as a cloud model\n",
-        "- Upload the exported model as a Vertex AI Model resource\n",
-        "- Hyperparameter tune a BQML model with Vertex AI Vizier\n",
+        "- Upload the exported model as a `Vertex AI Model` resource\n",
+        "- Hyperparameter tune a BQML model with `Vertex AI Vizier`\n",
+        "- Automatically register a BQML model to `Vertex AI Model Registry`\n",
         "\n",
         "### Costs\n",
         "This tutorial uses billable components of Google Cloud:\n",
@@ -127,18 +133,20 @@
       "source": [
         "import os\n",
         "\n",
-        "# The Google Cloud Notebook product has specific requirements\n",
-        "IS_GOOGLE_CLOUD_NOTEBOOK = os.path.exists(\"/opt/deeplearning/metadata/env_version\")\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\") and not os.getenv(\"VIRTUAL_ENV\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\"/opt/deeplearning/metadata/env_version\")\n",
         "\n",
-        "# Google Cloud Notebook requires dependencies to be installed with '--user'\n",
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
         "USER_FLAG = \"\"\n",
-        "if IS_GOOGLE_CLOUD_NOTEBOOK:\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
         "    USER_FLAG = \"--user\"\n",
         "\n",
         "# Install the packages\n",
-        "! pip3 install --upgrade pyarrow $USER_FLAG\n",
-        "! pip3 install --upgrade google-cloud-aiplatform $USER_FLAG\n",
-        "! pip3 install --upgrade google-cloud-bigquery $USER_FLAG"
+        "! pip3 install --upgrade pyarrow \\\n",
+        "                        google-cloud-aiplatform \\\n",
+        "                        google-cloud-bigquery \\\n",
+        "                        google-cloud-bigquery-storage $USER_FLAG -q"
       ]
     },
     {
@@ -176,6 +184,23 @@
         "id": "project_id"
       },
       "source": [
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI, BigQuery, Compute Engine and Cloud Storage APIs](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,bigquery,compute_component,storage_component).\n",
+        "\n",
+        "1. If you are running this notebook locally, you need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+        "\n",
+        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands.\n",
+        "\n",
         "#### Set your project ID\n",
         "\n",
         "**If you don't know your project ID**, you may be able to get your project ID using `gcloud`."
@@ -276,6 +301,67 @@
         "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "f3bd8c0d0469"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already authenticated. Skip this step.\n",
+        "\n",
+        "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\n",
+        "\n",
+        "1. **Click Create service account**.\n",
+        "\n",
+        "2. In the **Service account name** field, enter a name, and click **Create**.\n",
+        "\n",
+        "3. In the **Grant this service account access to project** section, click the Role drop-down list. Type \"Vertex AI\" into the filter box, and select **Vertex AI Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "4. Click Create. A JSON file that contains your key downloads to your local environment.\n",
+        "\n",
+        "5. Enter the path to your service account key as the GOOGLE_APPLICATION_CREDENTIALS variable in the cell below and run the cell."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "e0953a00668e"
+      },
+      "outputs": [],
+      "source": [
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
+        "IS_COLAB = False\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
+        "    \"DL_ANACONDA_HOME\"\n",
+        "):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        IS_COLAB = True\n",
+        "        from google.colab import auth as google_auth\n",
+        "\n",
+        "        google_auth.authenticate_user()\n",
+        "\n",
+        "    # If you are running this notebook locally, replace the string below with the\n",
+        "    # path to your service account key and run this cell to authenticate your GCP\n",
+        "    # account.\n",
+        "    elif not os.getenv(\"IS_TESTING\"):\n",
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -299,7 +385,8 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
+        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
+        "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
       ]
     },
     {
@@ -310,8 +397,9 @@
       },
       "outputs": [],
       "source": [
-        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"gs://[your-bucket-name]\":\n",
-        "    BUCKET_NAME = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
+        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"[your-bucket-name]\":\n",
+        "    BUCKET_NAME = PROJECT_ID + \"aip-\" + TIMESTAMP\n",
+        "    BUCKET_URI = f\"gs://{BUCKET_NAME}\""
       ]
     },
     {
@@ -331,7 +419,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION $BUCKET_NAME"
+        "! gsutil mb -l $REGION $BUCKET_URI"
       ]
     },
     {
@@ -351,7 +439,55 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil ls -al $BUCKET_NAME"
+        "! gsutil ls -al $BUCKET_URI"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "set_service_account"
+      },
+      "source": [
+        "#### Service Account\n",
+        "\n",
+        "You use a service account to create Vertex AI Pipeline jobs. If you do not want to use your project's Compute Engine service account, set `SERVICE_ACCOUNT` to another service account ID."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "set_service_account"
+      },
+      "outputs": [],
+      "source": [
+        "SERVICE_ACCOUNT = \"[your-service-account]\"  # @param {type:\"string\"}"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "autoset_service_account"
+      },
+      "outputs": [],
+      "source": [
+        "if (\n",
+        "    SERVICE_ACCOUNT == \"\"\n",
+        "    or SERVICE_ACCOUNT is None\n",
+        "    or SERVICE_ACCOUNT == \"[your-service-account]\"\n",
+        "):\n",
+        "    # Get your service account from gcloud\n",
+        "    if not IS_COLAB:\n",
+        "        shell_output = !gcloud auth list 2>/dev/null\n",
+        "        SERVICE_ACCOUNT = shell_output[2].replace(\"*\", \"\").strip()\n",
+        "\n",
+        "    if IS_COLAB:\n",
+        "        shell_output = ! gcloud projects describe  $PROJECT_ID\n",
+        "        project_number = shell_output[-1].split(\":\")[1].strip().replace(\"'\", \"\")\n",
+        "        SERVICE_ACCOUNT = f\"{project_number}-compute@developer.gserviceaccount.com\"\n",
+        "\n",
+        "    print(\"Service Account:\", SERVICE_ACCOUNT)"
       ]
     },
     {
@@ -394,7 +530,7 @@
       },
       "outputs": [],
       "source": [
-        "aiplatform.init(project=PROJECT_ID, staging_bucket=BUCKET_NAME)"
+        "aiplatform.init(project=PROJECT_ID, staging_bucket=BUCKET_URI)"
       ]
     },
     {
@@ -694,10 +830,10 @@
       },
       "outputs": [],
       "source": [
-        "param = f\"{PROJECT_ID}:{BQ_DATASET_NAME}.{MODEL_NAME} {BUCKET_NAME}/{MODEL_NAME}\"\n",
+        "param = f\"{PROJECT_ID}:{BQ_DATASET_NAME}.{MODEL_NAME} {BUCKET_URI}/{MODEL_NAME}\"\n",
         "! bq extract -m $param\n",
         "\n",
-        "MODEL_DIR = f\"{BUCKET_NAME}/{BQ_DATASET_NAME}\"\n",
+        "MODEL_DIR = f\"{BUCKET_URI}/{BQ_DATASET_NAME}\"\n",
         "! gsutil ls $MODEL_DIR"
       ]
     },
@@ -828,7 +964,7 @@
         "id": "model_delete:mbsdk"
       },
       "source": [
-        "#### Delete the model\n",
+        "#### Delete the `Vertex AI Model` resource\n",
         "\n",
         "The method 'delete()' deletes the model."
       ]
@@ -844,6 +980,32 @@
         "model.delete()"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "7890ae6f6410"
+      },
+      "source": [
+        "### Delete the `BigQuery ML` model\n",
+        "\n",
+        "Next, delete the `BigQuery ML` instance of the model."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "f0b6163e70c0"
+      },
+      "outputs": [],
+      "source": [
+        "MODEL_QUERY = f\"\"\"\n",
+        "DROP MODEL `{BQ_DATASET_NAME}.{MODEL_NAME}`\n",
+        "\"\"\"\n",
+        "\n",
+        "job = bqclient.query(MODEL_QUERY)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -932,6 +1094,32 @@
         "print(results)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "3f3cee1236b1"
+      },
+      "source": [
+        "### Delete the `BigQuery ML` model\n",
+        "\n",
+        "Next, delete the `BigQuery ML` instance of the model."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "957b7d841502"
+      },
+      "outputs": [],
+      "source": [
+        "MODEL_QUERY = f\"\"\"\n",
+        "DROP MODEL `{BQ_DATASET_NAME}.{MODEL_NAME}`\n",
+        "\"\"\"\n",
+        "\n",
+        "job = bqclient.query(MODEL_QUERY)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -981,6 +1169,179 @@
         "print(\"{} created in {}\".format(tblname, job.ended - job.started))"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "4def8aaf3398"
+      },
+      "source": [
+        "### Delete the `BigQuery ML` model\n",
+        "\n",
+        "Next, delete the `BigQuery ML` instance of the model."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "ff5b32618018"
+      },
+      "outputs": [],
+      "source": [
+        "MODEL_QUERY = f\"\"\"\n",
+        "DROP MODEL `{BQ_DATASET_NAME}.{MODEL_NAME}`\n",
+        "\"\"\"\n",
+        "\n",
+        "job = bqclient.query(MODEL_QUERY)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "2b4498ca6fea"
+      },
+      "source": [
+        "## Model Registry\n",
+        "\n",
+        "Alternatively, you can implicitly upload your BigQuery ML model as a `Vertex AI Model` resource with exporting and importing the model artifacts. In this method, you add additional options when training the model that tells BigQuery ML to automatically upload and register the trained model as a `Model` resource.\n",
+        "\n",
+        "### Setting permissions to automatically register the model\n",
+        "\n",
+        "You need to set some additional IAM permissions for BigQuery ML to automatically upload and register the model after training. Depending on your service account, the setting of the permissions below may fail. In this case, we recommend executing the permissions in a Cloud Shell.\n",
+        "\n",
+        "Learn more about [Setting permissions for Model Registry](https://cloud.devsite.corp.google.com/bigquery-ml/docs/managing-models-vertex\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "29229f72d13d"
+      },
+      "outputs": [],
+      "source": [
+        "! gcloud projects add-iam-policy-binding $PROJECT_ID \\\n",
+        "    --member=serviceAccount:$SERVICE_ACCOUNT --role=roles/aiplatform.admin --condition=None"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "6c390ee7c11a"
+      },
+      "source": [
+        "### Training and registering the model\n",
+        "\n",
+        "Next, you train the model and automatically register the model to the `Vertex AI Model Registry`, by adding the following parameters as options:\n",
+        "\n",
+        "- `model_registry`: Set to \"vertex_ai\" to indicate automatic registation to `Vertex AI Model Registry`.\n",
+        "- `vertex_ai_model_id`: The human readable display name for the registered model.\n",
+        "- `vertex_ai_model_version_aliases`: Alternate names for the model."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "57db464f4c42"
+      },
+      "outputs": [],
+      "source": [
+        "MODEL_NAME = \"penguins\"\n",
+        "MODEL_QUERY = f\"\"\"\n",
+        "CREATE OR REPLACE MODEL `{BQ_DATASET_NAME}.{MODEL_NAME}`\n",
+        "OPTIONS(\n",
+        "    model_type='DNN_CLASSIFIER',\n",
+        "    labels = ['species'],\n",
+        "    model_registry=\"vertex_ai\",\n",
+        "    vertex_ai_model_id=\"bqml_model_{TIMESTAMP}\", \n",
+        "    vertex_ai_model_version_aliases=[\"1\"]\n",
+        "    )\n",
+        "AS\n",
+        "SELECT *\n",
+        "FROM `{BQ_TABLE}`\n",
+        "\"\"\"\n",
+        "\n",
+        "job = bqclient.query(MODEL_QUERY)\n",
+        "print(job.errors, job.state)\n",
+        "\n",
+        "while job.running():\n",
+        "    from time import sleep\n",
+        "\n",
+        "    sleep(30)\n",
+        "    print(\"Running ...\")\n",
+        "print(job.errors, job.state)\n",
+        "\n",
+        "tblname = job.ddl_target_table\n",
+        "tblname = \"{}.{}\".format(tblname.dataset_id, tblname.table_id)\n",
+        "print(\"{} created in {}\".format(tblname, job.ended - job.started))"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "5b4970272040"
+      },
+      "source": [
+        "### Find the model in the `Vertex Model Registry`\n",
+        "\n",
+        "Finally, you can use the `Vertex AI Model` list() method with a filter query to find the automatically registered model."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "76c22674ba99"
+      },
+      "outputs": [],
+      "source": [
+        "models = aiplatform.Model.list(filter=\"display_name=bqml_model_\" + TIMESTAMP)\n",
+        "model = models[0]\n",
+        "\n",
+        "print(model.gca_resource)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "48e6ef5d5ffa"
+      },
+      "outputs": [],
+      "source": [
+        "models = aiplatform.Model.list()\n",
+        "for model in models:\n",
+        "    if model.gca_resource.display_name.startswith(\"bqml\"):\n",
+        "        print(model.gca_resource.display_name)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "ef61354b1a5f"
+      },
+      "source": [
+        "### Delete the `BigQuery ML` model\n",
+        "\n",
+        "Next, delete the `BigQuery ML` instance of the model."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "f6004d1ce59d"
+      },
+      "outputs": [],
+      "source": [
+        "MODEL_QUERY = f\"\"\"\n",
+        "DROP MODEL `{BQ_DATASET_NAME}.{MODEL_NAME}`\n",
+        "\"\"\"\n",
+        "\n",
+        "job = bqclient.query(MODEL_QUERY)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -992,12 +1353,9 @@
         "To clean up all Google Cloud resources used in this project, you can [delete the Google Cloud\n",
         "project](https://cloud.google.com/resource-manager/docs/creating-managing-projects#shutting_down_projects) you used for the tutorial.\n",
         "\n",
-        "Otherwise, you can delete the individual resources you created in this tutorial:\n",
+        "Otherwise, you can delete the individual resources you created in this tutorial.\n",
         "\n",
-        "- Model\n",
-        "- Endpoint\n",
-        "- Dataset\n",
-        "- Cloud Storage Bucket"
+        "Set `delete_storage` to `True` to delete the Cloud Storage bucket used in this notebook."
       ]
     },
     {
@@ -1013,13 +1371,18 @@
         "endpoint.delete()\n",
         "\n",
         "# Delete the model using the Vertex model object\n",
-        "model.delete()\n",
+        "try:\n",
+        "    model.delete()\n",
+        "except Exception as e:\n",
+        "    print(e)\n",
         "\n",
-        "if os.getenv(\"IS_TESTING\"):\n",
+        "# Delete the created BigQuery dataset\n",
+        "! bq rm -r -f $PROJECT_ID:$BQ_DATASET_NAME\n",
+        "\n",
+        "delete_storage = False\n",
+        "if delete_storage or os.getenv(\"IS_TESTING\"):\n",
         "    # Delete the created GCS bucket\n",
-        "    ! gsutil rm -r $BUCKET_NAME\n",
-        "    # Delete the created BigQuery dataset\n",
-        "    ! bq rm -r -f $PROJECT_ID:$BQ_DATASET_NAME"
+        "    ! gsutil rm -r $BUCKET_URI"
       ]
     }
   ],

notebooks/community/ml_ops/stage2/get_started_vertex_distributed_training.ipynb

@@ -8,7 +8,7 @@
       },
       "outputs": [],
       "source": [
-        "# Copyright 2021 Google LLC\n",
+        "# Copyright 2022 Google LLC\n",
         "#\n",
         "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
         "# you may not use this file except in compliance with the License.\n",
@@ -32,6 +32,11 @@
         "# E2E ML on GCP: MLOps stage 2 : experimentation: get started with Vertex Distributed Training\n",
         "\n",
         "<table align=\"left\">\n",
+        "      <td>\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_vertex_distributed_training.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "    </a>\n",
+        "  </td>\n",
         "  <td>\n",
         "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_vertex_distributed_training.ipynb\">\n",
         "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
@@ -39,8 +44,9 @@
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://console.cloud.google.com/ai/platform/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_vertex_distributed_training.ipynb\">\n",
-        "      Open in Google Cloud Notebooks\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/ml_ops/stage2/get_started_vertex_distributed_training.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "Open in Vertex AI Workbench\n",
         "    </a>\n",
         "  </td>\n",
         "</table>\n",
@@ -56,7 +62,7 @@
         "## Overview\n",
         "\n",
         "\n",
-        "This tutorial demonstrates how to use Vertex AI for E2E MLOps on Google Cloud in production. This tutorial covers stage 2 : experimentation: get started with Vertex Distributed Training."
+        "This tutorial demonstrates how to use Vertex AI for E2E MLOps on Google Cloud in production. This tutorial covers stage 2 : experimentation: get started with Vertex Distributed Training. Please note: There are incompatibilities between Colab and Docker and the Docker section may not work until resolved by the platform."
       ]
     },
     {
@@ -100,6 +106,15 @@
         "id": "recommendation:mlops,stage2,vertex,distributed_training"
       },
       "source": [
+        "### Costs\n",
+        " \n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "Vertex AI\n",
+        "Cloud Storage\n",
+        "\n",
+        "Learn about [Vertex AI pricing](https://cloud.google.com/vertex-ai/pricing) and [Cloud Storage pricing](https://cloud.google.com/storage/pricing), and use the [Pricing Calculator](https://cloud.google.com/products/calculator/),\n",
+        "        to generate a cost estimate based on your projected usage.\n",
         "### Recommendations\n",
         "\n",
         "When doing E2E MLOps on Google Cloud, the following are best practices for when to use Vertex AI Distributed Training:\n",
@@ -126,59 +141,58 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "install_mlops"
+        "id": "XkYpRvOQyVYb"
       },
       "source": [
-        "## Installations\n",
+        "### Install additional packages\n",
         "\n",
-        "Install *one time* the packages for executing the MLOps notebooks."
+        "Install the packages required for executing this notebook."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "install_mlops"
+        "id": "xs_Kt8RcyXTC"
       },
       "outputs": [],
       "source": [
-        "ONCE_ONLY = False\n",
-        "if ONCE_ONLY:\n",
-        "    ! pip3 install -U tensorflow==2.5 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-data-validation==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-transform==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-io==0.18 $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-aiplatform[tensorboard] $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-pipeline-components $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-bigquery $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-logging $USER_FLAG\n",
-        "    ! pip3 install --upgrade apache-beam[gcp] $USER_FLAG\n",
-        "    ! pip3 install --upgrade pyarrow $USER_FLAG\n",
-        "    ! pip3 install --upgrade cloudml-hypertune $USER_FLAG\n",
-        "    ! pip3 install --upgrade kfp $USER_FLAG\n",
-        "    ! pip3 install --upgrade torchvision $USER_FLAG\n",
-        "    ! pip3 install --upgrade rpy2 $USER_FLAG"
+        "import os\n",
+        "\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\") and not os.getenv(\"VIRTUAL_ENV\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
+        "\n",
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
+        "USER_FLAG = \"\"\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "\n",
+        "! pip3 install {USER_FLAG} --upgrade google-cloud-aiplatform"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "restart"
+        "id": "oQhwq1iozAxh"
       },
       "source": [
         "### Restart the kernel\n",
         "\n",
-        "Once you've installed the additional packages, you need to restart the notebook kernel so it can find the packages."
+        "After you install the additional packages, you need to restart the notebook kernel so it can find the packages."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "restart"
+        "id": "zo3YFZXLzCRJ"
       },
       "outputs": [],
       "source": [
+        "# Automatically restart kernel after installs\n",
         "import os\n",
         "\n",
         "if not os.getenv(\"IS_TESTING\"):\n",
@@ -189,6 +203,32 @@
         "    app.kernel.do_shutdown(True)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "84cd83853240"
+      },
+      "source": [
+        "## Before you begin\n",
+        "\n",
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI, BigQuery, Compute Engine and Cloud Storage APIs](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,bigquery,compute_component,storage_component).\n",
+        "\n",
+        "1. If you are running this notebook locally, you need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+        "\n",
+        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -208,6 +248,8 @@
       },
       "outputs": [],
       "source": [
+        "import os\n",
+        "\n",
         "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
       ]
     },
@@ -261,11 +303,14 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "region"
+        "id": "qohAA9fJulvP"
       },
       "outputs": [],
       "source": [
-        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
+        "\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
       ]
     },
     {
@@ -283,7 +328,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "timestamp"
+        "id": "8NKwwe7aulvQ"
       },
       "outputs": [],
       "source": [
@@ -292,6 +337,82 @@
         "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "poKeKYG8ulvQ"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already\n",
+        "authenticated. Skip this step."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "MIpJGzF9ulvQ"
+      },
+      "source": [
+        "**If you are using Colab**, run the cell below and follow the instructions\n",
+        "when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "1. In the Cloud Console, go to the [**Create service account key**\n",
+        "   page](https://console.cloud.google.com/apis/credentials/serviceaccountkey).\n",
+        "\n",
+        "2. Click **Create service account**.\n",
+        "\n",
+        "3. In the **Service account name** field, enter a name, and\n",
+        "   click **Create**.\n",
+        "\n",
+        "4. In the **Grant this service account access to project** section, click the **Role** drop-down list. Type \"Vertex AI\"\n",
+        "into the filter box, and select\n",
+        "   **Vertex AI Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "5. Click *Create*. A JSON file that contains your key downloads to your\n",
+        "local environment.\n",
+        "\n",
+        "6. Enter the path to your service account key as the\n",
+        "`GOOGLE_APPLICATION_CREDENTIALS` variable in the cell below and run the cell."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "Vh6KDXB5ulvQ"
+      },
+      "outputs": [],
+      "source": [
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
+        "IS_COLAB = False\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
+        "    \"DL_ANACONDA_HOME\"\n",
+        "):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        IS_COLAB = True\n",
+        "        from google.colab import auth as google_auth\n",
+        "\n",
+        "        google_auth.authenticate_user()\n",
+        "\n",
+        "    # If you are running this notebook locally, replace the string below with the\n",
+        "    # path to your service account key and run this cell to authenticate your GCP\n",
+        "    # account.\n",
+        "    elif not os.getenv(\"IS_TESTING\"):\n",
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -315,7 +436,8 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
+        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
+        "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
       ]
     },
     {
@@ -326,8 +448,9 @@
       },
       "outputs": [],
       "source": [
-        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"gs://[your-bucket-name]\":\n",
-        "    BUCKET_NAME = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
+        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"[your-bucket-name]\":\n",
+        "    BUCKET_NAME = PROJECT_ID + \"aip-\" + TIMESTAMP\n",
+        "    BUCKET_URI = f\"gs://{BUCKET_NAME}\""
       ]
     },
     {
@@ -343,11 +466,11 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "create_bucket"
+        "id": "Moosy2rOulvR"
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION $BUCKET_NAME"
+        "! gsutil mb -l $REGION $BUCKET_URI"
       ]
     },
     {
@@ -363,11 +486,11 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "validate_bucket"
+        "id": "56irx2CvulvS"
       },
       "outputs": [],
       "source": [
-        "! gsutil ls -al $BUCKET_NAME"
+        "! gsutil ls -al $BUCKET_URI"
       ]
     },
     {
@@ -408,11 +531,11 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "init_aip:mbsdk"
+        "id": "wbvYPSTDulvS"
       },
       "outputs": [],
       "source": [
-        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_NAME)"
+        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_URI)"
       ]
     },
     {
@@ -441,7 +564,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "accelerators:training,prediction,ngpu,mbsdk"
+        "id": "PryARdnoulvT"
       },
       "outputs": [],
       "source": [
@@ -483,14 +606,14 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "container:training,prediction"
+        "id": "LhhUFw2nulvT"
       },
       "outputs": [],
       "source": [
         "if os.getenv(\"IS_TESTING_TF\"):\n",
         "    TF = os.getenv(\"IS_TESTING_TF\")\n",
         "else:\n",
-        "    TF = \"2.1\".replace(\".\", \"-\")\n",
+        "    TF = \"2.5\".replace(\".\", \"-\")\n",
         "\n",
         "if TF[0] == \"2\":\n",
         "    if TRAIN_GPU:\n",
@@ -551,7 +674,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "machine:training"
+        "id": "vytMaukeulvT"
       },
       "outputs": [],
       "source": [
@@ -613,7 +736,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "create_custom_pp_training_job:mbsdk"
+        "id": "mhw34XoOulvU"
       },
       "outputs": [],
       "source": [
@@ -621,7 +744,7 @@
         "\n",
         "job = aip.CustomPythonPackageTrainingJob(\n",
         "    display_name=DISPLAY_NAME,\n",
-        "    python_package_gcs_uri=f\"{BUCKET_NAME}/trainer_boston.tar.gz\",\n",
+        "    python_package_gcs_uri=f\"{BUCKET_URI}/trainer_boston.tar.gz\",\n",
         "    python_module_name=\"trainer.task\",\n",
         "    container_uri=TRAIN_IMAGE,\n",
         "    model_serving_container_image_uri=DEPLOY_IMAGE,\n",
@@ -662,7 +785,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "examine_training_package"
+        "id": "IAaZpZyyulvU"
       },
       "outputs": [],
       "source": [
@@ -711,7 +834,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "taskpy_contents:mirrored,boston"
+        "id": "zKzddzl6ulvV"
       },
       "outputs": [],
       "source": [
@@ -870,14 +993,14 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "tarball_training_script"
+        "id": "LFUHioqTulvV"
       },
       "outputs": [],
       "source": [
         "! rm -f custom.tar custom.tar.gz\n",
         "! tar cvf custom.tar custom\n",
         "! gzip custom.tar\n",
-        "! gsutil cp custom.tar.gz $BUCKET_NAME/trainer_boston.tar.gz"
+        "! gsutil cp custom.tar.gz $BUCKET_URI/trainer_boston.tar.gz"
       ]
     },
     {
@@ -895,11 +1018,11 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "run_custom_pp_training_job:mirrored"
+        "id": "LnUX0UkvulvV"
       },
       "outputs": [],
       "source": [
-        "MODEL_DIR = BUCKET_NAME\n",
+        "MODEL_DIR = BUCKET_URI\n",
         "\n",
         "CMDARGS = [\"--epochs=5\", \"--batch_size=16\", \"--distribute=mirrored\"]\n",
         "\n",
@@ -930,7 +1053,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "delete_job"
+        "id": "iUWHFpPoulvW"
       },
       "outputs": [],
       "source": [
@@ -952,7 +1075,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "model_delete:mbsdk"
+        "id": "-0gqCUTEulvW"
       },
       "outputs": [],
       "source": [
@@ -1037,7 +1160,7 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "create_custom_pp_training_job:mbsdk"
+        "id": "aXvPN8P6ulvX"
       },
       "source": [
         "### Create and run custom training job\n",
@@ -1063,7 +1186,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "create_custom_pp_training_job:mbsdk"
+        "id": "kYcFsVSEulvX"
       },
       "outputs": [],
       "source": [
@@ -1071,7 +1194,7 @@
         "\n",
         "job = aip.CustomPythonPackageTrainingJob(\n",
         "    display_name=DISPLAY_NAME,\n",
-        "    python_package_gcs_uri=f\"{BUCKET_NAME}/trainer_boston.tar.gz\",\n",
+        "    python_package_gcs_uri=f\"{BUCKET_URI}/trainer_boston.tar.gz\",\n",
         "    python_module_name=\"trainer.task\",\n",
         "    container_uri=TRAIN_IMAGE,\n",
         "    model_serving_container_image_uri=DEPLOY_IMAGE,\n",
@@ -1094,11 +1217,11 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "run_custom_pp_training_job:multiworker"
+        "id": "GHRxPU32ulvX"
       },
       "outputs": [],
       "source": [
-        "MODEL_DIR = BUCKET_NAME\n",
+        "MODEL_DIR = BUCKET_URI\n",
         "\n",
         "CMDARGS = [\"--epochs=5\", \"--batch_size=16\", \"--distribute=multiworker\"]\n",
         "\n",
@@ -1121,7 +1244,7 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "delete_job"
+        "id": "92D_hbuVulvX"
       },
       "source": [
         "### Delete a custom training job\n",
@@ -1133,7 +1256,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "delete_job"
+        "id": "CqrfWkB3ulvX"
       },
       "outputs": [],
       "source": [
@@ -1185,7 +1308,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "write_docker_file:training,multiworker"
+        "id": "pGI2viDAulvY"
       },
       "outputs": [],
       "source": [
@@ -1217,7 +1340,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "name_container:training"
+        "id": "7P8cdlFtulvY"
       },
       "outputs": [],
       "source": [
@@ -1237,11 +1360,15 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "build_container:training"
+        "id": "jmw5cakNulvY"
       },
       "outputs": [],
       "source": [
-        "! docker build custom -t $TRAIN_IMAGE"
+        "if not IS_COLAB:\n",
+        "    ! docker build custom -t $TRAIN_IMAGE\n",
+        "else:\n",
+        "    # install docker daemon\n",
+        "    ! apt-get -qq install docker.io"
       ]
     },
     {
@@ -1259,11 +1386,12 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "test_container:training"
+        "id": "jJGLjU-TulvZ"
       },
       "outputs": [],
       "source": [
-        "! docker run $TRAIN_IMAGE --epochs=5 --model-dir=./"
+        "if not IS_COLAB:\n",
+        "    ! docker run $TRAIN_IMAGE --epochs=5 --model-dir=./"
       ]
     },
     {
@@ -1281,11 +1409,42 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "register_container:training"
+        "id": "GAXGjae7ulvZ"
       },
       "outputs": [],
       "source": [
-        "! docker push $TRAIN_IMAGE"
+        "if not IS_COLAB:\n",
+        "    ! docker push $TRAIN_IMAGE"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "f50e9c553fb7"
+      },
+      "source": [
+        "*Executes in Colab*"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "a7e8c98f1e56"
+      },
+      "outputs": [],
+      "source": [
+        "%%bash -s $IS_COLAB $TRAIN_IMAGE\n",
+        "if [ $1 == \"False\" ]; then\n",
+        "  exit 0\n",
+        "fi\n",
+        "set -x\n",
+        "dockerd -b none --iptables=0 -l warn &\n",
+        "for i in $(seq 5); do [ ! -S \"/var/run/docker.sock\" ] && sleep 2 || break; done\n",
+        "docker build custom -t $2\n",
+        "docker run $2 --epochs=5 --model-dir=./\n",
+        "docker push $2\n",
+        "kill $(jobs -p)"
       ]
     },
     {
@@ -1305,13 +1464,13 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "worker_pool_primary"
+        "id": "CEAnXBzCulvZ"
       },
       "outputs": [],
       "source": [
         "PRIMARY_COMPUTE = \"n2-highcpu-64\"\n",
         "\n",
-        "MODEL_DIR = BUCKET_NAME\n",
+        "MODEL_DIR = BUCKET_URI\n",
         "\n",
         "CMDARGS = [\n",
         "    \"--model-dir=\" + MODEL_DIR,\n",
@@ -1348,7 +1507,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "worker_pool_training"
+        "id": "6dchPSfNulvZ"
       },
       "outputs": [],
       "source": [
@@ -1384,7 +1543,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "custom_job:worker_pool"
+        "id": "m2VgmqEOulva"
       },
       "outputs": [],
       "source": [
@@ -1408,7 +1567,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "run_custom_job:multiworker"
+        "id": "hg8vnI_Wulva"
       },
       "outputs": [],
       "source": [
@@ -1422,7 +1581,7 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "delete_job"
+        "id": "WT76Sc-culva"
       },
       "source": [
         "### Delete a custom training job\n",
@@ -1434,7 +1593,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "delete_job"
+        "id": "I_IxVfuDulva"
       },
       "outputs": [],
       "source": [
@@ -1483,7 +1642,7 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "custom_job:worker_pool"
+        "id": "L8Av8ATVulvb"
       },
       "source": [
         "### Create CustomJob with worker pool specifications\n",
@@ -1499,7 +1658,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "custom_job:worker_pool"
+        "id": "TUWEP1Lmulvb"
       },
       "outputs": [],
       "source": [
@@ -1511,7 +1670,7 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "run_custom_job:multiworker"
+        "id": "_95FH8jeulvb"
       },
       "source": [
         "### Run the CustomJob\n",
@@ -1523,7 +1682,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "run_custom_job:multiworker"
+        "id": "IEbrY05Gulvb"
       },
       "outputs": [],
       "source": [
@@ -1537,7 +1696,7 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "delete_job"
+        "id": "8R2Bnmwmulvb"
       },
       "source": [
         "### Delete a custom training job\n",
@@ -1549,7 +1708,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "delete_job"
+        "id": "s1geVE3Lulvb"
       },
       "outputs": [],
       "source": [
@@ -1592,7 +1751,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "docker_write:tpu"
+        "id": "nQVPtknpulvb"
       },
       "outputs": [],
       "source": [
@@ -1631,11 +1790,11 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "docker_push:tpu"
+        "id": "J_d_zEXUulvc"
       },
       "outputs": [],
       "source": [
-        "TRAIN_IMAGE = f\"gcr.io/\" + PROJECT_ID + \"/tpu-train:latest\"\n",
+        "TRAIN_IMAGE = \"gcr.io/\" + PROJECT_ID + \"/tpu-train:latest\"\n",
         "\n",
         "os.chdir(\"custom\")\n",
         "! docker build --quiet --tag={TRAIN_IMAGE} .\n",
@@ -1662,7 +1821,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "worker_pool_tpu"
+        "id": "d514eU7lulvc"
       },
       "outputs": [],
       "source": [
@@ -1710,7 +1869,7 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "custom_job:worker_pool"
+        "id": "RruSqNfrulvc"
       },
       "source": [
         "### Create CustomJob with worker pool specifications\n",
@@ -1726,7 +1885,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "custom_job:worker_pool"
+        "id": "2QvSqbbHulvc"
       },
       "outputs": [],
       "source": [
@@ -1738,7 +1897,7 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "run_custom_job:multiworker"
+        "id": "Iw4L3UIfulvd"
       },
       "source": [
         "### Run the CustomJob\n",
@@ -1750,7 +1909,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "run_custom_job:multiworker"
+        "id": "zmqCNS78ulvd"
       },
       "outputs": [],
       "source": [
@@ -1764,7 +1923,7 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "delete_job"
+        "id": "gWZoH9QKulvd"
       },
       "source": [
         "### Delete a custom training job\n",
@@ -1776,7 +1935,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "delete_job"
+        "id": "Lt8BJ4iBulvd"
       },
       "outputs": [],
       "source": [
@@ -1796,13 +1955,7 @@
         "\n",
         "Otherwise, you can delete the individual resources you created in this tutorial:\n",
         "\n",
-        "- Dataset\n",
-        "- Pipeline\n",
-        "- Model\n",
-        "- Endpoint\n",
-        "- Batch Job\n",
-        "- Custom Job\n",
-        "- Hyperparameter Tuning Job\n",
+        "\n",
         "- Cloud Storage Bucket"
       ]
     },
@@ -1810,70 +1963,15 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "cleanup"
+        "id": "U98Wzc01ulvd"
       },
       "outputs": [],
       "source": [
-        "delete_dataset = True\n",
-        "delete_pipeline = True\n",
-        "delete_model = True\n",
-        "delete_endpoint = True\n",
-        "delete_batchjob = True\n",
-        "delete_customjob = True\n",
-        "delete_hptjob = True\n",
-        "delete_bucket = True\n",
+        "# Set this to true only if you'd like to delete your bucket\n",
+        "delete_bucket = False\n",
         "\n",
-        "# Delete the dataset using the Vertex fully qualified identifier for the dataset\n",
-        "try:\n",
-        "    if delete_dataset and \"dataset_id\" in globals():\n",
-        "        clients[\"dataset\"].delete_dataset(name=dataset_id)\n",
-        "except Exception as e:\n",
-        "    print(e)\n",
-        "\n",
-        "# Delete the training pipeline using the Vertex fully qualified identifier for the pipeline\n",
-        "try:\n",
-        "    if delete_pipeline and \"pipeline_id\" in globals():\n",
-        "        clients[\"pipeline\"].delete_training_pipeline(name=pipeline_id)\n",
-        "except Exception as e:\n",
-        "    print(e)\n",
-        "\n",
-        "# Delete the model using the Vertex fully qualified identifier for the model\n",
-        "try:\n",
-        "    if delete_model and \"model_to_deploy_id\" in globals():\n",
-        "        clients[\"model\"].delete_model(name=model_to_deploy_id)\n",
-        "except Exception as e:\n",
-        "    print(e)\n",
-        "\n",
-        "# Delete the endpoint using the Vertex fully qualified identifier for the endpoint\n",
-        "try:\n",
-        "    if delete_endpoint and \"endpoint_id\" in globals():\n",
-        "        clients[\"endpoint\"].delete_endpoint(name=endpoint_id)\n",
-        "except Exception as e:\n",
-        "    print(e)\n",
-        "\n",
-        "# Delete the batch job using the Vertex fully qualified identifier for the batch job\n",
-        "try:\n",
-        "    if delete_batchjob and \"batch_job_id\" in globals():\n",
-        "        clients[\"job\"].delete_batch_prediction_job(name=batch_job_id)\n",
-        "except Exception as e:\n",
-        "    print(e)\n",
-        "\n",
-        "# Delete the custom job using the Vertex fully qualified identifier for the custom job\n",
-        "try:\n",
-        "    if delete_customjob and \"job_id\" in globals():\n",
-        "        clients[\"job\"].delete_custom_job(name=job_id)\n",
-        "except Exception as e:\n",
-        "    print(e)\n",
-        "\n",
-        "# Delete the hyperparameter tuning job using the Vertex fully qualified identifier for the hyperparameter tuning job\n",
-        "try:\n",
-        "    if delete_hptjob and \"hpt_job_id\" in globals():\n",
-        "        clients[\"job\"].delete_hyperparameter_tuning_job(name=hpt_job_id)\n",
-        "except Exception as e:\n",
-        "    print(e)\n",
-        "\n",
-        "if delete_bucket and \"BUCKET_NAME\" in globals():\n",
-        "    ! gsutil rm -r $BUCKET_NAME"
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil rm -r $BUCKET_URI"
       ]
     }
   ],

notebooks/community/ml_ops/stage2/get_started_vertex_experiments.ipynb

@@ -38,8 +38,13 @@
         "      View on GitHub\n",
         "    </a>\n",
         "  </td>\n",
+        "    <td>\n",
+        "        <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_vertex_experiments.ipynb\">\n",
+        "        <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "        </a>\n",
+        "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_vertex_experiments.ipynb\">\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/ml_ops/stage2/get_started_vertex_experiments.ipynb\">\n",
         "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
         "      Open in Vertex AI Workbench\n",
         "    </a>\n",
@@ -137,15 +142,18 @@
       "source": [
         "import os\n",
         "\n",
-        "# The Google Cloud Notebook product has specific requirements\n",
-        "IS_GOOGLE_CLOUD_NOTEBOOK = os.path.exists(\"/opt/deeplearning/metadata/env_version\")\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\") and not os.getenv(\"VIRTUAL_ENV\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
         "\n",
-        "# Google Cloud Notebook requires dependencies to be installed with '--user'\n",
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
         "USER_FLAG = \"\"\n",
-        "if IS_GOOGLE_CLOUD_NOTEBOOK:\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
         "    USER_FLAG = \"--user\"\n",
         "\n",
-        "! pip3 install --upgrade google-cloud-logging $USER_FLAG"
+        "! pip3 install --upgrade google-cloud-logging $USER_FLAG -q"
       ]
     },
     {
@@ -183,6 +191,24 @@
         "id": "project_id"
       },
       "source": [
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI, Compute Engine, Cloud Storage and Cloud Logging APIs](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,compute_component,storage_component,logging).\n",
+        "\n",
+        "1. If you are running this notebook locally, you need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+        "\n",
+        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands.\n",
+        "\n",
+        "\n",
         "#### Set your project ID\n",
         "\n",
         "**If you don't know your project ID**, you may be able to get your project ID using `gcloud`."
@@ -283,6 +309,67 @@
         "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "f3bd8c0d0469"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already authenticated. Skip this step.\n",
+        "\n",
+        "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\n",
+        "\n",
+        "1. **Click Create service account**.\n",
+        "\n",
+        "2. In the **Service account name** field, enter a name, and click **Create**.\n",
+        "\n",
+        "3. In the **Grant this service account access to project** section, click the Role drop-down list. Type \"Vertex AI\" into the filter box, and select **Vertex AI Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "4. Click Create. A JSON file that contains your key downloads to your local environment.\n",
+        "\n",
+        "5. Enter the path to your service account key as the GOOGLE_APPLICATION_CREDENTIALS variable in the cell below and run the cell."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "e0953a00668e"
+      },
+      "outputs": [],
+      "source": [
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
+        "IS_COLAB = False\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
+        "    \"DL_ANACONDA_HOME\"\n",
+        "):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        IS_COLAB = True\n",
+        "        from google.colab import auth as google_auth\n",
+        "\n",
+        "        google_auth.authenticate_user()\n",
+        "\n",
+        "    # If you are running this notebook locally, replace the string below with the\n",
+        "    # path to your service account key and run this cell to authenticate your GCP\n",
+        "    # account.\n",
+        "    elif not os.getenv(\"IS_TESTING\"):\n",
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -505,7 +592,7 @@
         "from google.cloud.logging.handlers import CloudLoggingHandler\n",
         "\n",
         "# Connect to the Cloud Logging service\n",
-        "cl_client = google.cloud.logging.Client()\n",
+        "cl_client = google.cloud.logging.Client(project=PROJECT_ID)\n",
         "handler = CloudLoggingHandler(cl_client, name=\"mylog\")\n",
         "\n",
         "# Create a logger instance and logging level\n",
@@ -612,7 +699,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "bd7fb247cbae"
+        "id": "1ed46e349cf2"
       },
       "outputs": [],
       "source": [

notebooks/community/ml_ops/stage2/get_started_vertex_feature_store.ipynb

@@ -38,11 +38,20 @@
         "      View on GitHub\n",
         "    </a>\n",
         "  </td>\n",
+        "    \n",
         "  <td>\n",
-        "    <a href=\"https://console.cloud.google.com/ai/platform/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_vertex_feature_store.ipynb\">\n",
-        "      Open in Google Cloud Notebooks\n",
+        "        <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_vertex_feature_store.ipynb\">\n",
+        "        <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "        </a>\n",
+        "  </td>\n",
+        "    \n",
+        "  <td>\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/ml_ops/stage2/get_started_vertex_feature_store.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "      Open in Vertex AI Workbench\n",
         "    </a>\n",
         "  </td>\n",
+        "    \n",
         "</table>\n",
         "<br/><br/><br/>"
       ]
@@ -67,9 +76,9 @@
       "source": [
         "### Dataset\n",
         "\n",
-        "The dataset used for this tutorial is the Movie Recommendations. The version of the dataset you will use in this tutorial is stored in a public Cloud Storage bucket, in Avro format.\n",
+        "The dataset used for this tutorial is the `Movie Recommendations` dataset. The version of the dataset you will use in this tutorial is stored in a public Cloud Storage bucket, in Avro format.\n",
         "\n",
-        "The dataset predicts whether a persons will watch a movie."
+        "This dataset is used to predict whether a person will watch a movie or not."
       ]
     },
     {
@@ -80,7 +89,7 @@
       "source": [
         "### Objective\n",
         "\n",
-        "In this tutorial, you learn how to use `Vertex AI Feature Store` for when training and prediction with `Vertex AI`.\n",
+        "In this tutorial, you learn how to use `Vertex AI Feature Store` when training and predicting with `Vertex AI`.\n",
         "\n",
         "This tutorial uses the following Google Cloud ML services:\n",
         "\n",
@@ -98,6 +107,22 @@
         "- Perform batch serving from a `Featurestore` resource."
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "81c777b8ad32"
+      },
+      "source": [
+        "### Costs\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "- Vertex AI\n",
+        "- Cloud Storage\n",
+        "- BigQuery\n",
+        "\n",
+        "Learn about [Vertex AI pricing](https://cloud.google.com/vertex-ai/pricing), [Cloud Storage pricing](https://cloud.google.com/storage/pricing) and [BigQuery pricing](https://cloud.google.com/bigquery/pricing) and use the [Pricing Calculator](https://cloud.google.com/products/calculator/) to generate a cost estimate based on your projected usage."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -106,7 +131,7 @@
       "source": [
         "## Installations\n",
         "\n",
-        "Install *one time* the packages for executing the MLOps notebooks."
+        "Install the following packages for further running this notebook."
       ]
     },
     {
@@ -117,24 +142,21 @@
       },
       "outputs": [],
       "source": [
-        "ONCE_ONLY = False\n",
-        "if ONCE_ONLY:\n",
-        "    ! pip3 install -U tensorflow==2.5 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-data-validation==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-transform==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-io==0.18 $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-aiplatform[tensorboard] $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-pipeline-components $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-bigquery $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-logging $USER_FLAG\n",
-        "    ! pip3 install --upgrade apache-beam[gcp] $USER_FLAG\n",
-        "    ! pip3 install --upgrade pyarrow $USER_FLAG\n",
-        "    ! pip3 install --upgrade cloudml-hypertune $USER_FLAG\n",
-        "    ! pip3 install --upgrade kfp $USER_FLAG\n",
-        "    ! pip3 install --upgrade torchvision $USER_FLAG\n",
-        "    ! pip3 install --upgrade rpy2 $USER_FLAG\n",
-        "    ! pip3 install --upgrade python-tabulate $USER_FLAG\n",
-        "    ! pip3 install -U opencv-python-headless==4.5.2.52 $USER_FLAG"
+        "import os\n",
+        "\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\") and not os.getenv(\"VIRTUAL_ENV\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
+        "\n",
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
+        "USER_FLAG = \"\"\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "\n",
+        "# Install the dependecies\n",
+        "! pip3 install --upgrade google-cloud-aiplatform google-cloud-bigquery pyarrow avro $USER_FLAG -q"
       ]
     },
     {
@@ -166,6 +188,30 @@
         "    app.kernel.do_shutdown(True)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "project_id"
+      },
+      "source": [
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI, Compute Engine, Cloud Storage and Cloud Logging APIs](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,compute_component,storage_component,logging).\n",
+        "\n",
+        "1. If you are running this notebook locally, you need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+        "\n",
+        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -242,7 +288,10 @@
       },
       "outputs": [],
       "source": [
-        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
+        "\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
       ]
     },
     {
@@ -269,15 +318,72 @@
         "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "29b110b44457"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already authenticated. Skip this step.\n",
+        "\n",
+        "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\n",
+        "\n",
+        "1. **Click Create service account**.\n",
+        "\n",
+        "2. In the **Service account name** field, enter a name, and click **Create**.\n",
+        "\n",
+        "3. In the **Grant this service account access to project** section, click the Role drop-down list. Type \"Vertex\" into the filter box, and select **Vertex Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "4. Click Create. A JSON file that contains your key downloads to your local environment.\n",
+        "\n",
+        "5. Enter the path to your service account key as the GOOGLE_APPLICATION_CREDENTIALS variable in the cell below and run the cell."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "89788a802687"
+      },
+      "outputs": [],
+      "source": [
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
+        "IS_COLAB = \"google.colab\" in sys.modules\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
+        "    \"DL_ANACONDA_HOME\"\n",
+        "):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        from google.colab import auth as google_auth\n",
+        "\n",
+        "        google_auth.authenticate_user()\n",
+        "\n",
+        "    # If you are running this notebook locally, replace the string below with the\n",
+        "    # path to your service account key and run this cell to authenticate your GCP\n",
+        "    # account.\n",
+        "    elif not os.getenv(\"IS_TESTING\"):\n",
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
         "id": "setup_vars"
       },
       "source": [
-        "### Set up variables\n",
-        "\n",
-        "Next, set up some variables used throughout the tutorial.\n",
         "### Import libraries and define constants"
       ]
     },
@@ -289,28 +395,7 @@
       },
       "outputs": [],
       "source": [
-        "import google.cloud.aiplatform as aip"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "import_bq"
-      },
-      "source": [
-        "#### Import BigQuery\n",
-        "\n",
-        "Import the BigQuery package into your Python environment."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "import_bq"
-      },
-      "outputs": [],
-      "source": [
+        "import google.cloud.aiplatform as aiplatform\n",
         "from google.cloud import bigquery"
       ]
     },
@@ -320,9 +405,7 @@
         "id": "init_bq"
       },
       "source": [
-        "### Create BigQuery client\n",
-        "\n",
-        "Create the BigQuery client."
+        "Initialize Vertex AI and BigQuery clients."
       ]
     },
     {
@@ -333,7 +416,8 @@
       },
       "outputs": [],
       "source": [
-        "bqclient = bigquery.Client()"
+        "aiplatform.init(project=PROJECT_ID)\n",
+        "bqclient = bigquery.Client(project=PROJECT_ID)"
       ]
     },
     {
@@ -350,11 +434,11 @@
         "\n",
         "Now it's time to do a live prediction. You get a transaction from the cash register, but all it has is the credit card number and this transaction. It does not have the enriched data the model needs. During serving, the credit card number is used as an index to Feature Store to get the enriched data needed for the model.\n",
         "\n",
-        "Next problem. Let's say the enriched data the model was trained on was timestamp June 1. This transaction is June 15. Assume that the user has made other transactions between June 1 and 15, and the enriched data has been continuously updated in Feature Store. But the model was trained on June 1st data. FeatureStore knows the version number and serves the June 1 version to the model (not the current June 15); otherwise, if you used June 15 data you have training-serving skew.\n",
+        "On the other hand, let's say the enriched data the model was trained on was timestamped on June 1st. The current transaction is from June 15th. Assume that the user has made other transactions between June 1st and 15th, and the enriched data has been continuously updated in Feature Store. But the model was trained on June 1st data. FeatureStore knows the version number and serves the June 1st version to the model (not the current June 15th). Otherwise, if you used June 15th data, you would have training-serving skew.\n",
         "\n",
-        "Next problem, data drift. Things change, suddenly one day everybody is buying toilet paper! There is a significant change in the distribution of the current stored enriched data from the distribution that the deployed model was trained on. FeatureStore can detect changes/thresholds in distribution changes and trigger a notification for retraining the model.\n",
+        "Another problem here is the data drift. Things change and suddenly one day, everybody is buying toilet paper! There is a significant change in the distribution of existing enriched data from the distribution that the deployed model was trained on. FeatureStore can detect changes/thresholds in distribution changes and trigger a notification for retraining the model.\n",
         "\n",
-        "Learn more about [Vertex AI Feature Store API](https://cloud.google.com/vertex-ai/docs/featurestore)"
+        "Learn more about [Vertex AI Feature Store API](https://cloud.google.com/vertex-ai/docs/featurestore)."
       ]
     },
     {
@@ -369,9 +453,9 @@
         "\n",
         "        Featurestore -> EntityType -> Feature\n",
         "\n",
-        "- `Featurestore`: the place to store your features\n",
+        "- `Featurestore`: the place to store your features.\n",
         "- `EntityType`: under a `Featurestore`, an `EntityType` describes an object to be modeled, real one or virtual one.\n",
-        "- `Feature`: under an `EntityType`, a `Feature` describes an attribute of the `EntityType`\n",
+        "- `Feature`: under an `EntityType`, a `Feature` describes an attribute of the `EntityType`.\n",
         "\n",
         "Learn more about [Vertex AI Feature Store data model](https://cloud.google.com/vertex-ai/docs/featurestore/concepts).\n",
         "\n",
@@ -405,9 +489,9 @@
       "outputs": [],
       "source": [
         "# Represents featurestore resource path.\n",
-        "FEATURESTORE_NAME = \"movies\"\n",
+        "FEATURESTORE_NAME = \"movies_\" + TIMESTAMP\n",
         "\n",
-        "featurestore = aip.Featurestore.create(\n",
+        "featurestore = aiplatform.Featurestore.create(\n",
         "    featurestore_id=FEATURESTORE_NAME,\n",
         "    online_store_fixed_node_count=1,\n",
         "    project=PROJECT_ID,\n",
@@ -436,7 +520,7 @@
       },
       "outputs": [],
       "source": [
-        "for featurestore in aip.Featurestore.list():\n",
+        "for featurestore in aiplatform.Featurestore.list():\n",
         "    print(featurestore)"
       ]
     },
@@ -463,7 +547,7 @@
       },
       "outputs": [],
       "source": [
-        "featurestore = featurestore = aip.Featurestore(\n",
+        "featurestore = featurestore = aiplatform.Featurestore(\n",
         "    featurestore_name=FEATURESTORE_NAME, project=PROJECT_ID, location=REGION\n",
         ")\n",
         "print(featurestore)"
@@ -522,7 +606,7 @@
       "outputs": [],
       "source": [
         "def create_features(featurestore_name, entity_name, features):\n",
-        "    entity_type = aip.EntityType(\n",
+        "    entity_type = aiplatform.EntityType(\n",
         "        entity_type_name=entity_name, featurestore_id=featurestore_name\n",
         "    )\n",
         "\n",
@@ -573,7 +657,7 @@
       },
       "outputs": [],
       "source": [
-        "for featurestore in aip.Featurestore.list():\n",
+        "for featurestore in aiplatform.Featurestore.list():\n",
         "    print(featurestore)"
       ]
     },
@@ -585,7 +669,7 @@
       "source": [
         "### Search `Feature` resources using a filter\n",
         "\n",
-        "You can narrow your search of `Feature` resources using the method `list_features()` and specifying a `filter` filter."
+        "You can narrow your search of `Feature` resources using the method `list_features()` and specifying a `filter` string."
       ]
     },
     {
@@ -637,17 +721,26 @@
       },
       "outputs": [],
       "source": [
-        "features = aip.Feature.search(query=\"value_type=DOUBLE\")\n",
+        "features = aiplatform.Feature.search(query=\"value_type=DOUBLE\")\n",
         "print(\"By data type\")\n",
         "for feature in features:\n",
         "    print(features)\n",
         "\n",
-        "aip.Feature.search(query=\"feature_id=title\")\n",
+        "aiplatform.Feature.search(query=\"feature_id=title\")\n",
         "print(\"By Name\")\n",
         "for feature in features:\n",
         "    print(features)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "277e9884cf37"
+      },
+      "source": [
+        "Define paths to the feature data."
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -677,7 +770,7 @@
         "\n",
         "### Data layout\n",
         "\n",
-        "Each imported `EntityType` resource data must have an ID; also, each `EntityType` resource data item can optionally have a timestamp, sepecifying when the feature values were generated.\n",
+        "Each imported `EntityType` resource data must have an ID. Also, each `EntityType` resource data item can optionally have a timestamp, sepecifying when the feature values were generated.\n",
         "\n",
         "When importing, specify the following in your request:\n",
         "\n",
@@ -685,7 +778,7 @@
         "- Data source URL\n",
         "- Destination: featurestore/entity types/features to be imported\n",
         "\n",
-        "The feature values for the movies dataset are in Avro format. The Avro schemas are as follows:\n",
+        "The feature values for `Movie Recommendations` dataset are in Avro format. The Avro schemas are as follows:\n",
         "\n",
         "**Users entity**:\n",
         "\n",
@@ -797,7 +890,7 @@
       "source": [
         "#### Delete the entity types and corresponding features and feature values\n",
         "\n",
-        "Next, in preparation to repeat importing feature values from a dataframe, you first delete the existing entity types, and corresponding content."
+        "Now, in preparation to repeat the process of importing feature values but from a dataframe this time, you delete the existing entity types, and the corresponding content."
       ]
     },
     {
@@ -822,7 +915,7 @@
       "source": [
         "## Create entity types for your `Featurestore` resource\n",
         "\n",
-        "Next, you create the `EntityType` resources for your `Featurestore` resource using the `create_entity_type()` method, with the following parameters:\n",
+        "Next, you create the `EntityType` resources again for your `Featurestore` resource using the `create_entity_type()` method, with the following parameters:\n",
         "\n",
         "- `entity_type_id`: The name of the `EntityType` resource.\n",
         "- `description`:  A description of the entity type."
@@ -851,7 +944,7 @@
       "source": [
         "### Add `Feature` resources for your `EntityType` resources\n",
         "\n",
-        "Next, you create the `Feature` resources for each of the `EntityType` resources in your `Featurestore` resource using the `create_feature()` method, with the following parameters:\n",
+        "Further, you create the `Feature` resources again for each of the `EntityType` resources in your `Featurestore` resource using the `create_feature()` method, with the following parameters:\n",
         "\n",
         "- `feature_id`: The name of the `Feature` resource.\n",
         "- `description`: A description of the feature.\n",
@@ -867,7 +960,7 @@
       "outputs": [],
       "source": [
         "def create_features(featurestore_name, entity_name, features):\n",
-        "    entity_type = aip.EntityType(\n",
+        "    entity_type = aiplatform.EntityType(\n",
         "        entity_type_name=entity_name, featurestore_id=featurestore_name\n",
         "    )\n",
         "\n",
@@ -899,6 +992,15 @@
         ")"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "8715a3f719c8"
+      },
+      "source": [
+        "Now, copy the `users` and `movies` data into avro files."
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -1041,7 +1143,7 @@
       "source": [
         "## Batch Serving\n",
         "\n",
-        "The Vertex AI Feature Store batch serving service is optimized for serving large batches of features in real-time with high-throughput, typically for training a model or batch prediction.\n",
+        "The Vertex AI Feature Store's batch serving service is optimized for serving large batches of features in real-time with high throughput, typically for training a model or batch prediction.\n",
         "\n",
         "One can batch serve to the following destinations:\n",
         "\n",
@@ -1093,7 +1195,7 @@
         "\n",
         "You batch serve entity data items to a BigQuery table using the `read_serve_to_bq()` method, with the following parameters:\n",
         "\n",
-        "- `bq_destination_output_uri`: The destination BigQuery table to serve the features to.\n",
+        "- `bq_destination_output_uri`: The destination BigQuery table to receive the served features.\n",
         "- `serving_feature_ids`: A dictionary of entity type and corresponding features to serve.\n",
         "- `read_instances_uri`: A Cloud Storage location to read the entity data items from.\n",
         "\n",
@@ -1126,6 +1228,7 @@
         "id": "delete_bq_dataset"
       },
       "source": [
+        "## Cleaning up\n",
         "### Delete a BigQuery dataset\n",
         "\n",
         "Use the method `delete_dataset()` to delete a BigQuery dataset along with all its tables, by setting the parameter `delete_contents` to `True`."

notebooks/community/ml_ops/stage2/get_started_vertex_tensorboard.ipynb

@@ -8,7 +8,7 @@
       },
       "outputs": [],
       "source": [
-        "# Copyright 2021 Google LLC\n",
+        "# Copyright 2022 Google LLC\n",
         "#\n",
         "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
         "# you may not use this file except in compliance with the License.\n",
@@ -29,9 +29,14 @@
         "id": "title:generic,gcp"
       },
       "source": [
-        "# E2E ML on GCP: MLOps stage 2 : experimentation: get started with Vertex Tensorboard\n",
+        "# E2E ML on GCP: MLOps stage 2 : experimentation: get started with Vertex AI Tensorboard\n",
         "\n",
         "<table align=\"left\">\n",
+        "   <td>\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_vertex_tensorboard.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "    </a>\n",
+        "  </td>\n",
         "  <td>\n",
         "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_vertex_tensorboard.ipynb\">\n",
         "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
@@ -39,8 +44,9 @@
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://console.cloud.google.com/ai/platform/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_vertex_tensorboard.ipynb\">\n",
-        "      Open in Google Cloud Notebooks\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/notebook_template.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "      Open in Vertex AI Workbench\n",
         "    </a>\n",
         "  </td>\n",
         "</table>\n",
@@ -56,7 +62,7 @@
         "## Overview\n",
         "\n",
         "\n",
-        "This tutorial demonstrates how to use Vertex AI for E2E MLOps on Google Cloud in production. This tutorial covers stage 2 : experimentation: get started with Vertex Tensorboard."
+        "This tutorial demonstrates how to use Vertex AI for E2E MLOps on Google Cloud in production. This tutorial covers stage 2 : experimentation: get started with Vertex AI Tensorboard."
       ]
     },
     {
@@ -81,6 +87,68 @@
         "- Using Vertex AI TensorBoard with Vertex AI Training."
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "b132d4ef86d6"
+      },
+      "source": [
+        "### Costs \n",
+        "\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "* Vertex AI\n",
+        "* Cloud Storage\n",
+        "\n",
+        "Learn about [Vertex AI\n",
+        "pricing](https://cloud.google.com/vertex-ai/pricing) and [Cloud Storage\n",
+        "pricing](https://cloud.google.com/storage/pricing), and use the [Pricing\n",
+        "Calculator](https://cloud.google.com/products/calculator/)\n",
+        "to generate a cost estimate based on your projected usage."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "56cb7f08a9e8"
+      },
+      "source": [
+        "### Set up your local development environment\n",
+        "\n",
+        "**If you are using Colab or Google Cloud Notebooks**, your environment already meets\n",
+        "all the requirements to run this notebook. You can skip this step.\n",
+        "\n",
+        "**Otherwise**, make sure your environment meets this notebook's requirements.\n",
+        "You need the following:\n",
+        "\n",
+        "* The Google Cloud SDK\n",
+        "* Git\n",
+        "* Python 3\n",
+        "* virtualenv\n",
+        "* Jupyter notebook running in a virtual environment with Python 3\n",
+        "\n",
+        "The Google Cloud guide to [Setting up a Python development\n",
+        "environment](https://cloud.google.com/python/setup) and the [Jupyter\n",
+        "installation guide](https://jupyter.org/install) provide detailed instructions\n",
+        "for meeting these requirements. The following steps provide a condensed set of\n",
+        "instructions:\n",
+        "\n",
+        "1. [Install and initialize the Cloud SDK.](https://cloud.google.com/sdk/docs/)\n",
+        "\n",
+        "1. [Install Python 3.](https://cloud.google.com/python/setup#installing_python)\n",
+        "\n",
+        "1. [Install\n",
+        "   virtualenv](https://cloud.google.com/python/setup#installing_and_using_virtualenv)\n",
+        "   and create a virtual environment that uses Python 3. Activate the virtual environment.\n",
+        "\n",
+        "1. To install Jupyter, run `pip3 install jupyter` on the\n",
+        "command-line in a terminal shell.\n",
+        "\n",
+        "1. To launch Jupyter, run `jupyter notebook` on the command-line in a terminal shell.\n",
+        "\n",
+        "1. Open this notebook in the Jupyter Notebook Dashboard.\n"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -89,7 +157,7 @@
       "source": [
         "### Recommendations\n",
         "\n",
-        "When doing E2E MLOps on Google Cloud, the following best practices for visualizing your training with TensorBoard.\n",
+        "When doing E2E MLOps on Google Cloud, the following are the best practices for visualizing your training with TensorBoard.\n",
         "\n",
         "#### Local TensorBoard\n",
         "\n",
@@ -112,31 +180,32 @@
       "source": [
         "## Installations\n",
         "\n",
-        "Install *one time* the packages for executing the MLOps notebooks."
+        "Install the following packages for executing this notebook."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "install_mlops"
+        "id": "020040f91150"
       },
       "outputs": [],
       "source": [
-        "ONCE_ONLY = False\n",
-        "if ONCE_ONLY:\n",
-        "    ! pip3 install -U tensorflow==2.5 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-data-validation==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-transform==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-io==0.18 $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-aiplatform[tensorboard] $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-pipeline-components $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-bigquery $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-logging $USER_FLAG\n",
-        "    ! pip3 install --upgrade apache-beam[gcp] $USER_FLAG\n",
-        "    ! pip3 install --upgrade pyarrow $USER_FLAG\n",
-        "    ! pip3 install --upgrade cloudml-hypertune $USER_FLAG\n",
-        "    ! pip3 install --upgrade kfp $USER_FLAG"
+        "import os\n",
+        "\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\") and not os.getenv(\"VIRTUAL_ENV\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
+        "\n",
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
+        "USER_FLAG = \"\"\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "\n",
+        "! pip3 install -U tensorflow==2.8 $USER_FLAG -q\n",
+        "! pip3 install --upgrade google-cloud-aiplatform[tensorboard] $USER_FLAG -q"
       ]
     },
     {
@@ -168,6 +237,32 @@
         "    app.kernel.do_shutdown(True)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "2721ef0202d9"
+      },
+      "source": [
+        "## Before you begin\n",
+        "\n",
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com). \n",
+        "\n",
+        "1. If you are running this notebook locally, you will need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+        "\n",
+        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -244,7 +339,10 @@
       },
       "outputs": [],
       "source": [
-        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
+        "\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
       ]
     },
     {
@@ -271,6 +369,82 @@
         "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "2700e693f1b3"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already\n",
+        "authenticated. Skip this step."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "885395904904"
+      },
+      "source": [
+        "**If you are using Colab**, run the cell below and follow the instructions\n",
+        "when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "1. In the Cloud Console, go to the [**Create service account key**\n",
+        "   page](https://console.cloud.google.com/apis/credentials/serviceaccountkey).\n",
+        "\n",
+        "2. Click **Create service account**.\n",
+        "\n",
+        "3. In the **Service account name** field, enter a name, and\n",
+        "   click **Create**.\n",
+        "\n",
+        "4. In the **Grant this service account access to project** section, click the **Role** drop-down list. Type \"Vertex AI\"\n",
+        "into the filter box, and select\n",
+        "   **Vertex AI Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "5. Click *Create*. A JSON file that contains your key downloads to your\n",
+        "local environment.\n",
+        "\n",
+        "6. Enter the path to your service account key as the\n",
+        "`GOOGLE_APPLICATION_CREDENTIALS` variable in the cell below and run the cell."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "eff327d0552b"
+      },
+      "outputs": [],
+      "source": [
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
+        "IS_COLAB = False\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
+        "    \"DL_ANACONDA_HOME\"\n",
+        "):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        IS_COLAB = True\n",
+        "        from google.colab import auth as google_auth\n",
+        "\n",
+        "        google_auth.authenticate_user()\n",
+        "\n",
+        "    # If you are running this notebook locally, replace the string below with the\n",
+        "    # path to your service account key and run this cell to authenticate your GCP\n",
+        "    # account.\n",
+        "    elif not os.getenv(\"IS_TESTING\"):\n",
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -294,7 +468,7 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
+        "BUCKET_URI = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
       ]
     },
     {
@@ -305,8 +479,8 @@
       },
       "outputs": [],
       "source": [
-        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"gs://[your-bucket-name]\":\n",
-        "    BUCKET_NAME = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
+        "if BUCKET_URI == \"\" or BUCKET_URI is None or BUCKET_URI == \"gs://[your-bucket-name]\":\n",
+        "    BUCKET_URI = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
       ]
     },
     {
@@ -326,7 +500,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION $BUCKET_NAME"
+        "! gsutil mb -l $REGION $BUCKET_URI"
       ]
     },
     {
@@ -346,7 +520,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil ls -al $BUCKET_NAME"
+        "! gsutil ls -al $BUCKET_URI"
       ]
     },
     {
@@ -384,9 +558,16 @@
         "    or SERVICE_ACCOUNT is None\n",
         "    or SERVICE_ACCOUNT == \"[your-service-account]\"\n",
         "):\n",
-        "    # Get your GCP project id from gcloud\n",
-        "    shell_output = !gcloud auth list 2>/dev/null\n",
-        "    SERVICE_ACCOUNT = shell_output[2].strip()\n",
+        "    # Get your service account from gcloud\n",
+        "    if not IS_COLAB:\n",
+        "        shell_output = !gcloud auth list 2>/dev/null\n",
+        "        SERVICE_ACCOUNT = shell_output[2].replace(\"*\", \"\").strip()\n",
+        "\n",
+        "    if IS_COLAB:\n",
+        "        shell_output = ! gcloud projects describe  $PROJECT_ID\n",
+        "        project_number = shell_output[-1].split(\":\")[1].strip().replace(\"'\", \"\")\n",
+        "        SERVICE_ACCOUNT = f\"{project_number}-compute@developer.gserviceaccount.com\"\n",
+        "\n",
         "    print(\"Service Account:\", SERVICE_ACCOUNT)"
       ]
     },
@@ -410,7 +591,7 @@
       },
       "outputs": [],
       "source": [
-        "import google.cloud.aiplatform as aip"
+        "import google.cloud.aiplatform as aiplatform"
       ]
     },
     {
@@ -454,7 +635,7 @@
       },
       "outputs": [],
       "source": [
-        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_NAME)"
+        "aiplatform.init(project=PROJECT_ID, staging_bucket=BUCKET_URI)"
       ]
     },
     {
@@ -484,13 +665,15 @@
       },
       "outputs": [],
       "source": [
+        "import os\n",
+        "\n",
         "if os.getenv(\"IS_TESTING_TRAIN_GPU\"):\n",
         "    TRAIN_GPU, TRAIN_NGPU = (\n",
-        "        aip.gapic.AcceleratorType.NVIDIA_TESLA_K80,\n",
+        "        aiplatform.gapic.AcceleratorType.NVIDIA_TESLA_K80,\n",
         "        int(os.getenv(\"IS_TESTING_TRAIN_GPU\")),\n",
         "    )\n",
         "else:\n",
-        "    TRAIN_GPU, TRAIN_NGPU = (aip.gapic.AcceleratorType.NVIDIA_TESLA_K80, 1)"
+        "    TRAIN_GPU, TRAIN_NGPU = (aiplatform.gapic.AcceleratorType.NVIDIA_TESLA_K80, 1)"
       ]
     },
     {
@@ -663,9 +846,9 @@
         "\n",
         "You can upload your TensorBoard logs and share with others using `tensorboard dev` command. Once uploaded, a URL is returned to open up the TensorBoard instance in a brower for visualizing.\n",
         "\n",
-        "*Note:* Your TensorBoard instance is publicly visable.\n",
+        "*Note:* Your TensorBoard instance is publicly visible.\n",
         "\n",
-        "*Note:* In this example, while running within a notebook, the command will freeze since it is waiting for an interactive yes/no input. You can kill the command with a Ctrl C or kernel interupt.\n",
+        "*Note:* This cell is for demonstration purposes and must be ran in a terminal shell. In this example, while running within a notebook, the command will freeze since it is waiting for an interactive yes/no input. You can kill the command with a Ctrl C or kernel interupt.\n",
         "\n",
         "Learn more about [What is TensorBoard.dev](https://tensorboard.dev/)."
       ]
@@ -678,7 +861,7 @@
       },
       "outputs": [],
       "source": [
-        "! tensorboard dev upload --logdir {LOG_DIR} \\\n",
+        "! tensorboard dev upload --logdir logs \\\n",
         "  --name \"Simple experiment with MNIST\" \\\n",
         "  --description \"Training results\" \\\n",
         "  --one_shot"
@@ -706,7 +889,7 @@
       "outputs": [],
       "source": [
         "TENSORBOARD_DISPLAY_NAME = \"example\"\n",
-        "tensorboard = aip.Tensorboard.create(display_name=TENSORBOARD_DISPLAY_NAME)\n",
+        "tensorboard = aiplatform.Tensorboard.create(display_name=TENSORBOARD_DISPLAY_NAME)\n",
         "tensorboard_resource_name = tensorboard.gca_resource.name\n",
         "print(\"TensorBoard resource name:\", tensorboard_resource_name)"
       ]
@@ -746,9 +929,9 @@
         "\n",
         "url = output[1].split(' ')[-1]\n",
         "\n",
-        "print(url)\n",
+        "#print(url)\n",
         "\n",
-        "from IPython.core.display import display, HTML\n",
+        "from IPython.display import display, HTML\n",
         "display(HTML(\"<a href='\" + url + \"'>click here for TensorBoard instance</a>\"))"
       ]
     },
@@ -953,7 +1136,7 @@
         "! rm -f custom.tar custom.tar.gz\n",
         "! tar cvf custom.tar custom\n",
         "! gzip custom.tar\n",
-        "! gsutil cp custom.tar.gz $BUCKET_NAME/trainer_example.tar.gz"
+        "! gsutil cp custom.tar.gz $BUCKET_URI/trainer_example.tar.gz"
       ]
     },
     {
@@ -985,7 +1168,7 @@
       },
       "outputs": [],
       "source": [
-        "job = aip.CustomTrainingJob(\n",
+        "job = aiplatform.CustomTrainingJob(\n",
         "    display_name=\"example_\" + TIMESTAMP,\n",
         "    script_path=\"custom/trainer/task.py\",\n",
         "    container_uri=TRAIN_IMAGE,\n",
@@ -1021,7 +1204,7 @@
       },
       "outputs": [],
       "source": [
-        "MODEL_DIR = \"{}/{}\".format(BUCKET_NAME, TIMESTAMP)\n",
+        "MODEL_DIR = \"{}/{}\".format(BUCKET_URI, TIMESTAMP)\n",
         "\n",
         "EPOCHS = 20\n",
         "STEPS = 100\n",
@@ -1143,14 +1326,8 @@
         "\n",
         "Otherwise, you can delete the individual resources you created in this tutorial:\n",
         "\n",
-        "- Dataset\n",
-        "- Pipeline\n",
         "- Model\n",
-        "- Endpoint\n",
-        "- AutoML Training Job\n",
-        "- Batch Job\n",
         "- Custom Job\n",
-        "- Hyperparameter Tuning Job\n",
         "- Cloud Storage Bucket"
       ]
     },
@@ -1162,61 +1339,14 @@
       },
       "outputs": [],
       "source": [
-        "delete_all = True\n",
+        "# Delete the custom training job\n",
+        "job.delete()\n",
         "\n",
-        "if delete_all:\n",
-        "    # Delete the dataset using the Vertex dataset object\n",
-        "    try:\n",
-        "        if \"dataset\" in globals():\n",
-        "            dataset.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
+        "# Set this to true only if you'd like to delete your bucket\n",
+        "delete_bucket = False\n",
         "\n",
-        "    # Delete the model using the Vertex model object\n",
-        "    try:\n",
-        "        if \"model\" in globals():\n",
-        "            model.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the endpoint using the Vertex endpoint object\n",
-        "    try:\n",
-        "        if \"endpoint\" in globals():\n",
-        "            endpoint.undeploy_all()\n",
-        "            endpoint.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the AutoML or Pipeline training job\n",
-        "    try:\n",
-        "        if \"dag\" in globals():\n",
-        "            dag.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the custom training job\n",
-        "    try:\n",
-        "        if \"job\" in globals():\n",
-        "            job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the batch prediction job using the Vertex batch prediction object\n",
-        "    try:\n",
-        "        if \"batch_predict_job\" in globals():\n",
-        "            batch_predict_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the hyperparameter tuning job using the Vertex hyperparameter tuning object\n",
-        "    try:\n",
-        "        if \"hpt_job\" in globals():\n",
-        "            hpt_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    if \"BUCKET_NAME\" in globals():\n",
-        "        ! gsutil rm -r $BUCKET_NAME"
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil rm -r $BUCKET_URI"
       ]
     }
   ],

notebooks/community/ml_ops/stage2/get_started_vertex_training.ipynb

@@ -29,7 +29,7 @@
         "id": "title:generic,gcp"
       },
       "source": [
-        "# E2E ML on GCP: MLOps stage 2 : experimentation: get started with Vertex Training\n",
+        "# E2E ML on GCP: MLOps stage 2 : experimentation: get started with Vertex AI Training\n",
         "\n",
         "<table align=\"left\">\n",
         "  <td>\n",
@@ -39,8 +39,14 @@
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://console.cloud.google.com/ai/platform/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_vertex_training.ipynb\">\n",
-        "      Open in Google Cloud Notebooks\n",
+        "        <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_vertex_training.ipynb\">\n",
+        "        <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "        </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/ml_ops/stage2/get_started_vertex_training.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "      Open in Vertex AI Workbench\n",
         "    </a>\n",
         "  </td>\n",
         "</table>\n",
@@ -127,7 +133,7 @@
       "source": [
         "## Installations\n",
         "\n",
-        "Install *one time* the packages for executing the MLOps notebooks."
+        "Install the packages required for executing this notebook"
       ]
     },
     {
@@ -138,20 +144,20 @@
       },
       "outputs": [],
       "source": [
-        "ONCE_ONLY = False\n",
-        "if ONCE_ONLY:\n",
-        "    ! pip3 install -U tensorflow==2.5 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-data-validation==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-transform==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-io==0.18 $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-aiplatform[tensorboard] $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-pipeline-components $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-bigquery $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-logging $USER_FLAG\n",
-        "    ! pip3 install --upgrade apache-beam[gcp] $USER_FLAG\n",
-        "    ! pip3 install --upgrade pyarrow $USER_FLAG\n",
-        "    ! pip3 install --upgrade cloudml-hypertune $USER_FLAG\n",
-        "    ! pip3 install --upgrade kfp $USER_FLAG"
+        "import os\n",
+        "\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\") and not os.getenv(\"VIRTUAL_ENV\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
+        "\n",
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
+        "USER_FLAG = \"\"\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "\n",
+        "! pip3 install --upgrade google-cloud-aiplatform $USER_FLAG -q"
       ]
     },
     {
@@ -173,8 +179,6 @@
       },
       "outputs": [],
       "source": [
-        "import os\n",
-        "\n",
         "if not os.getenv(\"IS_TESTING\"):\n",
         "    # Automatically restart kernel after installs\n",
         "    import IPython\n",
@@ -183,6 +187,36 @@
         "    app.kernel.do_shutdown(True)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "before_you_begin"
+      },
+      "source": [
+        "## Before you begin\n",
+        "\n",
+        "### GPU runtime\n",
+        "\n",
+        "*Make sure you're running this notebook in a GPU runtime if you have that option. In Colab, select* **Runtime > Change Runtime Type > GPU**\n",
+        "\n",
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "2. [Make sure that billing is enabled for your project.](https://cloud.google.com/billing/docs/how-to/modify-project)\n",
+        "\n",
+        "3. [Enable the following APIs: Vertex AI APIs, Compute Engine APIs, and Cloud Storage.](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,compute_component,storage-component.googleapis.com)\n",
+        "\n",
+        "4. If you are running this notebook locally, you will need to install the [Cloud SDK]((https://cloud.google.com/sdk)).\n",
+        "\n",
+        "5. Enter your project ID in the cell below. Then run the  cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$`."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -259,7 +293,10 @@
       },
       "outputs": [],
       "source": [
-        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
+        "\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
       ]
     },
     {
@@ -286,6 +323,67 @@
         "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "gcp_authenticate"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already authenticated. Skip this step.\n",
+        "\n",
+        "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\n",
+        "\n",
+        "**Click Create service account**.\n",
+        "\n",
+        "In the **Service account name** field, enter a name, and click **Create**.\n",
+        "\n",
+        "In the **Grant this service account access to project** section, click the Role drop-down list. Type \"Vertex\" into the filter box, and select **Vertex Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "Click Create. A JSON file that contains your key downloads to your local environment.\n",
+        "\n",
+        "Enter the path to your service account key as the GOOGLE_APPLICATION_CREDENTIALS variable in the cell below and run the cell."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "gcp_authenticate"
+      },
+      "outputs": [],
+      "source": [
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
+        "IS_COLAB = False\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
+        "    \"DL_ANACONDA_HOME\"\n",
+        "):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        IS_COLAB = True\n",
+        "        from google.colab import auth as google_auth\n",
+        "\n",
+        "        google_auth.authenticate_user()\n",
+        "\n",
+        "    # If you are running this notebook locally, replace the string below with the\n",
+        "    # path to your service account key and run this cell to authenticate your GCP\n",
+        "    # account.\n",
+        "    elif not os.getenv(\"IS_TESTING\"):\n",
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -309,7 +407,8 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
+        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
+        "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
       ]
     },
     {
@@ -320,8 +419,9 @@
       },
       "outputs": [],
       "source": [
-        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"gs://[your-bucket-name]\":\n",
-        "    BUCKET_NAME = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
+        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"[your-bucket-name]\":\n",
+        "    BUCKET_NAME = PROJECT_ID + \"aip-\" + TIMESTAMP\n",
+        "    BUCKET_URI = \"gs://\" + BUCKET_NAME"
       ]
     },
     {
@@ -341,7 +441,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION $BUCKET_NAME"
+        "! gsutil mb -l $REGION $BUCKET_URI"
       ]
     },
     {
@@ -361,7 +461,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil ls -al $BUCKET_NAME"
+        "! gsutil ls -al $BUCKET_URI"
       ]
     },
     {
@@ -384,7 +484,7 @@
       },
       "outputs": [],
       "source": [
-        "import google.cloud.aiplatform as aip"
+        "import google.cloud.aiplatform as aiplatform"
       ]
     },
     {
@@ -406,7 +506,7 @@
       },
       "outputs": [],
       "source": [
-        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_NAME)"
+        "aiplatform.init(project=PROJECT_ID, staging_bucket=BUCKET_URI)"
       ]
     },
     {
@@ -441,7 +541,7 @@
       "source": [
         "if os.getenv(\"IS_TESTING_TRAIN_GPU\"):\n",
         "    TRAIN_GPU, TRAIN_NGPU = (\n",
-        "        aip.gapic.AcceleratorType.NVIDIA_TESLA_K80,\n",
+        "        aiplatform.gapic.AcceleratorType.NVIDIA_TESLA_K80,\n",
         "        int(os.getenv(\"IS_TESTING_TRAIN_GPU\")),\n",
         "    )\n",
         "else:\n",
@@ -449,7 +549,7 @@
         "\n",
         "if os.getenv(\"IS_TESTING_DEPLOY_GPU\"):\n",
         "    DEPLOY_GPU, DEPLOY_NGPU = (\n",
-        "        aip.gapic.AcceleratorType.NVIDIA_TESLA_K80,\n",
+        "        aiplatform.gapic.AcceleratorType.NVIDIA_TESLA_K80,\n",
         "        int(os.getenv(\"IS_TESTING_DEPLOY_GPU\")),\n",
         "    )\n",
         "else:\n",
@@ -484,7 +584,7 @@
         "if os.getenv(\"IS_TESTING_TF\"):\n",
         "    TF = os.getenv(\"IS_TESTING_TF\")\n",
         "else:\n",
-        "    TF = \"2.1\".replace(\".\", \"-\")\n",
+        "    TF = \"2.5\".replace(\".\", \"-\")\n",
         "\n",
         "if TF[0] == \"2\":\n",
         "    if TRAIN_GPU:\n",
@@ -602,7 +702,7 @@
         "DISPLAY_NAME = \"boston_\" + TIMESTAMP\n",
         "REQUIREMENTS = [\"tensorflow==2.3\"]\n",
         "\n",
-        "job = aip.CustomTrainingJob(\n",
+        "job = aiplatform.CustomTrainingJob(\n",
         "    display_name=DISPLAY_NAME,\n",
         "    script_path=\"task.py\",\n",
         "    requirements=REQUIREMENTS,\n",
@@ -693,12 +793,12 @@
       "outputs": [],
       "source": [
         "CMDARGS = [\n",
-        "    \"--model-dir=\" + BUCKET_NAME,\n",
+        "    \"--model-dir=\" + BUCKET_URI,\n",
         "]\n",
         "\n",
         "job.run(args=CMDARGS, replica_count=1, machine_type=TRAIN_COMPUTE, sync=True)\n",
         "\n",
-        "! gsutil cat {BUCKET_NAME}/test.txt"
+        "! gsutil cat {BUCKET_URI}/test.txt"
       ]
     },
     {
@@ -768,9 +868,9 @@
       "source": [
         "DISPLAY_NAME = \"boston_\" + TIMESTAMP\n",
         "\n",
-        "job = aip.CustomPythonPackageTrainingJob(\n",
+        "job = aiplatform.CustomPythonPackageTrainingJob(\n",
         "    display_name=DISPLAY_NAME,\n",
-        "    python_package_gcs_uri=f\"{BUCKET_NAME}/trainer_boston.tar.gz\",\n",
+        "    python_package_gcs_uri=f\"{BUCKET_URI}/trainer_boston.tar.gz\",\n",
         "    python_module_name=\"trainer.task\",\n",
         "    container_uri=TRAIN_IMAGE,\n",
         ")"
@@ -900,7 +1000,7 @@
         "! rm -f custom.tar custom.tar.gz\n",
         "! tar cvf custom.tar custom\n",
         "! gzip custom.tar\n",
-        "! gsutil cp custom.tar.gz $BUCKET_NAME/trainer_boston.tar.gz"
+        "! gsutil cp custom.tar.gz $BUCKET_URI/trainer_boston.tar.gz"
       ]
     },
     {
@@ -922,11 +1022,11 @@
       },
       "outputs": [],
       "source": [
-        "CMDARGS = [\"--model-dir=\" + BUCKET_NAME, \"--epochs=5\"]\n",
+        "CMDARGS = [\"--model-dir=\" + BUCKET_URI, \"--epochs=5\"]\n",
         "\n",
         "job.run(args=CMDARGS, replica_count=1, machine_type=TRAIN_COMPUTE, sync=True)\n",
         "\n",
-        "! gsutil cat {BUCKET_NAME}/test.txt"
+        "! gsutil cat {BUCKET_URI}/test.txt"
       ]
     },
     {
@@ -1151,7 +1251,11 @@
       },
       "outputs": [],
       "source": [
-        "! docker build custom -t $TRAIN_IMAGE"
+        "if not IS_COLAB:\n",
+        "    ! docker build custom -t $TRAIN_IMAGE\n",
+        "else:\n",
+        "    # install docker daemon\n",
+        "    ! apt-get -qq install docker.io"
       ]
     },
     {
@@ -1173,7 +1277,8 @@
       },
       "outputs": [],
       "source": [
-        "! docker run $TRAIN_IMAGE --epochs=5 --model-dir=./"
+        "if not IS_COLAB:\n",
+        "    ! docker run $TRAIN_IMAGE --epochs=5 --model-dir=./"
       ]
     },
     {
@@ -1195,7 +1300,38 @@
       },
       "outputs": [],
       "source": [
-        "! docker push $TRAIN_IMAGE"
+        "if not IS_COLAB:\n",
+        "    ! docker push $TRAIN_IMAGE"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "f50e9c553fb7"
+      },
+      "source": [
+        "*Executes in Colab*"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "a7e8c98f1e56"
+      },
+      "outputs": [],
+      "source": [
+        "%%bash -s $IS_COLAB $TRAIN_IMAGE\n",
+        "if [ $1 == \"False\" ]; then\n",
+        "  exit 0\n",
+        "fi\n",
+        "set -x\n",
+        "dockerd -b none --iptables=0 -l warn &\n",
+        "for i in $(seq 5); do [ ! -S \"/var/run/docker.sock\" ] && sleep 2 || break; done\n",
+        "docker build custom -t $2\n",
+        "docker run $2 --epochs=5 --model-dir=./\n",
+        "docker push $2\n",
+        "kill $(jobs -p)"
       ]
     },
     {
@@ -1229,7 +1365,7 @@
       },
       "outputs": [],
       "source": [
-        "job = aip.CustomContainerTrainingJob(\n",
+        "job = aiplatform.CustomContainerTrainingJob(\n",
         "    display_name=\"boston_\" + TIMESTAMP,\n",
         "    container_uri=TRAIN_IMAGE,\n",
         "    command=[\"python3\", \"trainer/task.py\"],\n",
@@ -1257,11 +1393,11 @@
       },
       "outputs": [],
       "source": [
-        "CMDARGS = [\"--model-dir=\" + BUCKET_NAME, \"--epochs=5\"]\n",
+        "CMDARGS = [\"--model-dir=\" + BUCKET_URI, \"--epochs=5\"]\n",
         "\n",
         "job.run(args=CMDARGS, replica_count=1, machine_type=TRAIN_COMPUTE, sync=True)\n",
         "\n",
-        "! gsutil cat {BUCKET_NAME}/test.txt"
+        "! gsutil cat {BUCKET_URI}/test.txt"
       ]
     },
     {
@@ -1466,7 +1602,7 @@
         "! rm -f custom.tar custom.tar.gz\n",
         "! tar cvf custom.tar custom\n",
         "! gzip custom.tar\n",
-        "! gsutil cp custom.tar.gz $BUCKET_NAME/trainer_boston.tar.gz"
+        "! gsutil cp custom.tar.gz $BUCKET_URI/trainer_boston.tar.gz"
       ]
     },
     {
@@ -1496,7 +1632,7 @@
         "if os.getenv(\"IS_TESTING_TF\"):\n",
         "    TF = os.getenv(\"IS_TESTING_TF\")\n",
         "else:\n",
-        "    TF = \"2.1\".replace(\".\", \"-\")\n",
+        "    TF = \"2.5\".replace(\".\", \"-\")\n",
         "\n",
         "if TF[0] == \"2\":\n",
         "    if TRAIN_GPU:\n",
@@ -1551,9 +1687,9 @@
       "source": [
         "DISPLAY_NAME = \"boston_\" + TIMESTAMP\n",
         "\n",
-        "job = aip.CustomPythonPackageTrainingJob(\n",
+        "job = aiplatform.CustomPythonPackageTrainingJob(\n",
         "    display_name=DISPLAY_NAME,\n",
-        "    python_package_gcs_uri=f\"{BUCKET_NAME}/trainer_boston.tar.gz\",\n",
+        "    python_package_gcs_uri=f\"{BUCKET_URI}/trainer_boston.tar.gz\",\n",
         "    python_module_name=\"trainer.task\",\n",
         "    container_uri=TRAIN_IMAGE,\n",
         "    model_serving_container_image_uri=DEPLOY_IMAGE,\n",
@@ -1587,12 +1723,12 @@
       },
       "outputs": [],
       "source": [
-        "MODEL_DIR = \"{}/{}\".format(BUCKET_NAME, TIMESTAMP)\n",
+        "MODEL_DIR = \"{}/{}\".format(BUCKET_URI, TIMESTAMP)\n",
         "\n",
         "EPOCHS = 20\n",
         "STEPS = 100\n",
         "\n",
-        "DIRECT = True\n",
+        "DIRECT = False\n",
         "if DIRECT:\n",
         "    CMDARGS = [\n",
         "        \"--model-dir=\" + MODEL_DIR,\n",
@@ -1758,17 +1894,7 @@
         "To clean up all Google Cloud resources used in this project, you can [delete the Google Cloud\n",
         "project](https://cloud.google.com/resource-manager/docs/creating-managing-projects#shutting_down_projects) you used for the tutorial.\n",
         "\n",
-        "Otherwise, you can delete the individual resources you created in this tutorial:\n",
-        "\n",
-        "- Dataset\n",
-        "- Pipeline\n",
-        "- Model\n",
-        "- Endpoint\n",
-        "- AutoML Training Job\n",
-        "- Batch Job\n",
-        "- Custom Job\n",
-        "- Hyperparameter Tuning Job\n",
-        "- Cloud Storage Bucket"
+        "Otherwise, you can delete the individual resources you created in this tutorial."
       ]
     },
     {
@@ -1779,61 +1905,24 @@
       },
       "outputs": [],
       "source": [
-        "delete_all = True\n",
+        "delete_bucket = False\n",
+        "delete_model = True\n",
+        "delete_job = True\n",
         "\n",
-        "if delete_all:\n",
-        "    # Delete the dataset using the Vertex dataset object\n",
+        "if delete_model:\n",
         "    try:\n",
-        "        if \"dataset\" in globals():\n",
-        "            dataset.delete()\n",
+        "        model.delete()\n",
         "    except Exception as e:\n",
         "        print(e)\n",
         "\n",
-        "    # Delete the model using the Vertex model object\n",
+        "if delete_job:\n",
         "    try:\n",
-        "        if \"model\" in globals():\n",
-        "            model.delete()\n",
+        "        job.delete()\n",
         "    except Exception as e:\n",
         "        print(e)\n",
         "\n",
-        "    # Delete the endpoint using the Vertex endpoint object\n",
-        "    try:\n",
-        "        if \"endpoint\" in globals():\n",
-        "            endpoint.undeploy_all()\n",
-        "            endpoint.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the AutoML or Pipeline training job\n",
-        "    try:\n",
-        "        if \"dag\" in globals():\n",
-        "            dag.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the custom training job\n",
-        "    try:\n",
-        "        if \"job\" in globals():\n",
-        "            job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the batch prediction job using the Vertex batch prediction object\n",
-        "    try:\n",
-        "        if \"batch_predict_job\" in globals():\n",
-        "            batch_predict_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the hyperparameter tuning job using the Vertex hyperparameter tuning object\n",
-        "    try:\n",
-        "        if \"hpt_job\" in globals():\n",
-        "            hpt_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    if \"BUCKET_NAME\" in globals():\n",
-        "        ! gsutil rm -r $BUCKET_NAME"
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil rm -rf {BUCKET_URI}"
       ]
     }
   ],

notebooks/community/ml_ops/stage2/get_started_vertex_training_pytorch.ipynb

@@ -33,13 +33,18 @@
         "\n",
         "<table align=\"left\">\n",
         "  <td>\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_vertex_training_pytorch.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
         "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_vertex_training_pytorch.ipynb\">\n",
         "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
         "      View on GitHub\n",
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/notebook_template.ipynb\">\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/notebook_template.ipynb\">\n",
         "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
         "      Open in Vertex AI Workbench\n",
         "    </a>\n",
@@ -172,7 +177,7 @@
       "source": [
         "## Installations\n",
         "\n",
-        "Install *one time* the packages for executing the MLOps notebooks."
+        "Install the following packages to execute this notebook."
       ]
     },
     {
@@ -183,10 +188,22 @@
       },
       "outputs": [],
       "source": [
-        "! pip3 install --upgrade google-cloud-aiplatform[tensorboard] $USER_FLAG\n",
-        "! pip3 install --upgrade google-cloud-pipeline-components $USER_FLAG\n",
-        "! pip3 install --upgrade cloudml-hypertune $USER_FLAG\n",
-        "! pip3 install --upgrade torchvision $USER_FLAG"
+        "import os\n",
+        "\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\") and not os.getenv(\"VIRTUAL_ENV\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
+        "\n",
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
+        "USER_FLAG = \"\"\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "\n",
+        "! pip3 install --upgrade google-cloud-aiplatform $USER_FLAG -q\n",
+        "! pip3 install --upgrade cloudml-hypertune $USER_FLAG -q\n",
+        "! pip3 install --upgrade torchvision $USER_FLAG -q"
       ]
     },
     {
@@ -218,6 +235,32 @@
         "    app.kernel.do_shutdown(True)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "84cd83853240"
+      },
+      "source": [
+        "## Before you begin\n",
+        "\n",
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI, BigQuery, Compute Engine and Cloud Storage APIs](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,bigquery,compute_component,storage_component).\n",
+        "\n",
+        "1. If you are running this notebook locally, you need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+        "\n",
+        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -294,7 +337,10 @@
       },
       "outputs": [],
       "source": [
-        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
+        "\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
       ]
     },
     {
@@ -321,6 +367,67 @@
         "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "77c385f0db59"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already authenticated. Skip this step.\n",
+        "\n",
+        "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\n",
+        "\n",
+        "1. **Click Create service account**.\n",
+        "\n",
+        "2. In the **Service account name** field, enter a name, and click **Create**.\n",
+        "\n",
+        "3. In the **Grant this service account access to project** section, click the Role drop-down list. Type \"Vertex AI\" into the filter box, and select **Vertex AI Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "4. Click Create. A JSON file that contains your key downloads to your local environment.\n",
+        "\n",
+        "5. Enter the path to your service account key as the GOOGLE_APPLICATION_CREDENTIALS variable in the cell below and run the cell."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "535223fa4b84"
+      },
+      "outputs": [],
+      "source": [
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
+        "IS_COLAB = False\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
+        "    \"DL_ANACONDA_HOME\"\n",
+        "):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        IS_COLAB = True\n",
+        "        from google.colab import auth as google_auth\n",
+        "\n",
+        "        google_auth.authenticate_user()\n",
+        "\n",
+        "    # If you are running this notebook locally, replace the string below with the\n",
+        "    # path to your service account key and run this cell to authenticate your GCP\n",
+        "    # account.\n",
+        "    elif not os.getenv(\"IS_TESTING\"):\n",
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -994,11 +1101,52 @@
       "source": [
         "APP_NAME = \"cifar10\"\n",
         "DEPLOY_IMAGE = f\"gcr.io/{PROJECT_ID}/pytorch_predict_{APP_NAME}\"\n",
-        "print(DEPLOY_IMAGE)\n",
-        "\n",
-        "! docker build --tag=$DEPLOY_IMAGE ./\n",
-        "\n",
-        "! docker push $DEPLOY_IMAGE"
+        "print(DEPLOY_IMAGE)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "85739262f629"
+      },
+      "outputs": [],
+      "source": [
+        "if not IS_COLAB:\n",
+        "    ! docker build --tag=$DEPLOY_IMAGE ./\n",
+        "    ! docker push $DEPLOY_IMAGE\n",
+        "else:\n",
+        "    # install docker daemon\n",
+        "    ! apt-get -qq install docker.io"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "f50e9c553fb7"
+      },
+      "source": [
+        "*Executes in Colab*"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "a7e8c98f1e56"
+      },
+      "outputs": [],
+      "source": [
+        "%%bash -s $IS_COLAB $DEPLOY_IMAGE\n",
+        "if [ $1 == \"False\" ]; then\n",
+        "  exit 0\n",
+        "fi\n",
+        "set -x\n",
+        "dockerd -b none --iptables=0 -l warn &\n",
+        "for i in $(seq 5); do [ ! -S \"/var/run/docker.sock\" ] && sleep 2 || break; done\n",
+        "docker build --tag=$2 ./\n",
+        "docker push $2\n",
+        "kill $(jobs -p)"
       ]
     },
     {
@@ -1211,7 +1359,6 @@
         "Otherwise, you can delete the individual resources you created in this tutorial:\n",
         "\n",
         "- Model\n",
-        "- Custom Job (Custom job deleted in previous cell)\n",
         "- Cloud Storage Bucket"
       ]
     },
@@ -1226,8 +1373,8 @@
         "# Delete the model using the Vertex model object\n",
         "model.delete()\n",
         "\n",
-        "\n",
-        "if os.getenv(\"IS_TESTING\"):\n",
+        "delete_bucket = False\n",
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
         "    ! gsutil rm -r $BUCKET_URI"
       ]
     }

notebooks/community/ml_ops/stage2/get_started_vertex_training_r.ipynb

@@ -39,7 +39,12 @@
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_vertex_training_r.ipynb\">\n",
+        "        <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_vertex_training_r.ipynb\">\n",
+        "        <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "        </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/ml_ops/stage2/get_started_vertex_training_r.ipynb\">\n",
         "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
         "      Open in Vertex AI Workbench\n",
         "    </a>\n",
@@ -129,7 +134,7 @@
       "source": [
         "## Installations\n",
         "\n",
-        "Install *one time* the packages for executing the MLOps notebooks."
+        "Install the packages required for executing this notebook."
       ]
     },
     {
@@ -142,25 +147,19 @@
       "source": [
         "import os\n",
         "\n",
-        "# The Google Cloud Notebook product has specific requirements\n",
-        "IS_GOOGLE_CLOUD_NOTEBOOK = os.path.exists(\"/opt/deeplearning/metadata/env_version\")\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\") and not os.getenv(\"VIRTUAL_ENV\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
         "\n",
-        "# Google Cloud Notebook requires dependencies to be installed with '--user'\n",
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
         "USER_FLAG = \"\"\n",
-        "if IS_GOOGLE_CLOUD_NOTEBOOK:\n",
-        "    USER_FLAG = \"--user\""
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "install_mlops"
-      },
-      "outputs": [],
-      "source": [
-        "! pip3 install --upgrade google-cloud-aiplatform[tensorboard] $USER_FLAG\n",
-        "! pip3 install --upgrade rpy2 $USER_FLAG"
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "\n",
+        "! pip3 install --upgrade google-cloud-aiplatform[tensorboard] $USER_FLAG -q\n",
+        "! pip3 install --upgrade rpy2 $USER_FLAG -q"
       ]
     },
     {
@@ -215,7 +214,7 @@
         "\n",
         "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
         "\n",
-        "1. [Enable the Vertex AI API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com). {TODO: Update the APIs needed for your tutorial. Edit the API names, and update the link to append the API IDs, separating each one with a comma. For example, container.googleapis.com,cloudbuild.googleapis.com}\n",
+        "1. [Enable the Vertex AI API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com). \n",
         "\n",
         "1. If you are running this notebook locally, you will need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
         "\n",
@@ -332,6 +331,67 @@
         "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "3ffa6b6c7cdb"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already authenticated. Skip this step.\n",
+        "\n",
+        "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\n",
+        "\n",
+        "1. **Click Create service account**.\n",
+        "\n",
+        "2. In the **Service account name** field, enter a name, and click **Create**.\n",
+        "\n",
+        "3. In the **Grant this service account access to project** section, click the Role drop-down list. Type \"Vertex AI\" into the filter box, and select **Vertex AI Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "4. Click Create. A JSON file that contains your key downloads to your local environment.\n",
+        "\n",
+        "5. Enter the path to your service account key as the GOOGLE_APPLICATION_CREDENTIALS variable in the cell below and run the cell."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "2b72272258fc"
+      },
+      "outputs": [],
+      "source": [
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
+        "IS_COLAB = False\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
+        "    \"DL_ANACONDA_HOME\"\n",
+        "):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        IS_COLAB = True\n",
+        "        from google.colab import auth as google_auth\n",
+        "\n",
+        "        google_auth.authenticate_user()\n",
+        "\n",
+        "    # If you are running this notebook locally, replace the string below with the\n",
+        "    # path to your service account key and run this cell to authenticate your GCP\n",
+        "    # account.\n",
+        "    elif not os.getenv(\"IS_TESTING\"):\n",
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -1366,7 +1426,9 @@
       },
       "outputs": [],
       "source": [
-        "if os.getenv(\"IS_TESTING\"):\n",
+        "delete_bucket = False\n",
+        "\n",
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
         "    ! gsutil rm -r $BUCKET_URI"
       ]
     }

notebooks/community/ml_ops/stage2/get_started_vertex_training_sklearn.ipynb

@@ -33,21 +33,23 @@
         "\n",
         "<table align=\"left\">\n",
         "  <td>\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_vertex_training_sklearn.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
         "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_vertex_training_sklearn.ipynb\">\n",
         "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
         "      View on GitHub\n",
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://console.cloud.google.com/ai/platform/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_vertex_training_sklearn.ipynb\">\n",
+        "    <a href=\"https://console.cloud.google.com/ai/platform/notebooks/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/ml_ops/stage2/get_started_vertex_training_sklearn.ipynb\">\n",
         "     <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
         "Open in Vertex AI Workbench\n",
         "    </a>\n",
         "  </td>\n",
         "</table>\n",
-        "    </a>\n",
-        "  </td>\n",
-        "</table>\n",
         "<br/><br/><br/>"
       ]
     },
@@ -60,7 +62,7 @@
         "## Overview\n",
         "\n",
         "\n",
-        "This tutorial demonstrates how to use Vertex AI for E2E MLOps on Google Cloud in production. This tutorial covers stage 2 : experimentation: get started with Vertex Training for Scikit-Learn."
+        "This tutorial demonstrates how to use Vertex AI for E2E MLOps on Google Cloud in production. This tutorial covers stage 2 : experimentation: get started with Vertex AI Training for scikit-Learn."
       ]
     },
     {
@@ -97,15 +99,156 @@
         "- Create a `Vertex AI Model` resource."
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "b132d4ef86d6"
+      },
+      "source": [
+        "### Costs \n",
+        "\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "* Vertex AI\n",
+        "* Cloud Storage\n",
+        "\n",
+        "Learn about [Vertex AI\n",
+        "pricing](https://cloud.google.com/vertex-ai/pricing) and [Cloud Storage\n",
+        "pricing](https://cloud.google.com/storage/pricing), and use the [Pricing\n",
+        "Calculator](https://cloud.google.com/products/calculator/)\n",
+        "to generate a cost estimate based on your projected usage."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "94a148f11da5"
+      },
+      "source": [
+        "### Set up your local development environment\n",
+        "\n",
+        "**If you are using Colab or Google Cloud Notebooks**, your environment already meets\n",
+        "all the requirements to run this notebook. You can skip this step.\n",
+        "\n",
+        "**Otherwise**, make sure your environment meets this notebook's requirements.\n",
+        "You need the following:\n",
+        "\n",
+        "* The Google Cloud SDK\n",
+        "* Git\n",
+        "* Python 3\n",
+        "* virtualenv\n",
+        "* Jupyter notebook running in a virtual environment with Python 3\n",
+        "\n",
+        "The Google Cloud guide to [Setting up a Python development\n",
+        "environment](https://cloud.google.com/python/setup) and the [Jupyter\n",
+        "installation guide](https://jupyter.org/install) provide detailed instructions\n",
+        "for meeting these requirements. The following steps provide a condensed set of\n",
+        "instructions:\n",
+        "\n",
+        "1. [Install and initialize the Cloud SDK.](https://cloud.google.com/sdk/docs/)\n",
+        "\n",
+        "1. [Install Python 3.](https://cloud.google.com/python/setup#installing_python)\n",
+        "\n",
+        "1. [Install\n",
+        "   virtualenv](https://cloud.google.com/python/setup#installing_and_using_virtualenv)\n",
+        "   and create a virtual environment that uses Python 3. Activate the virtual environment.\n",
+        "\n",
+        "1. To install Jupyter, run `pip3 install jupyter` on the\n",
+        "command-line in a terminal shell.\n",
+        "\n",
+        "1. To launch Jupyter, run `jupyter notebook` on the command-line in a terminal shell.\n",
+        "\n",
+        "1. Open this notebook in the Jupyter Notebook Dashboard.\n"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
         "id": "install_mlops"
       },
       "source": [
-        "## Installations\n",
+        "### Install additional packages\n",
         "\n",
-        "You will not need special packages for this notebook."
+        "Install the following packages for executing this notebook."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "78168417490e"
+      },
+      "outputs": [],
+      "source": [
+        "import os\n",
+        "\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\") and not os.getenv(\"VIRTUAL_ENV\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
+        "\n",
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
+        "USER_FLAG = \"\"\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "\n",
+        "! pip3 install {USER_FLAG} --upgrade google-cloud-aiplatform -q"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "restart"
+      },
+      "source": [
+        "### Restart the kernel\n",
+        "\n",
+        "Once you've installed the additional packages, you need to restart the notebook kernel so it can find the packages."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "restart"
+      },
+      "outputs": [],
+      "source": [
+        "import os\n",
+        "\n",
+        "if not os.getenv(\"IS_TESTING\"):\n",
+        "    # Automatically restart kernel after installs\n",
+        "    import IPython\n",
+        "\n",
+        "    app = IPython.Application.instance()\n",
+        "    app.kernel.do_shutdown(True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "2721ef0202d9"
+      },
+      "source": [
+        "## Before you begin\n",
+        "\n",
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com). \n",
+        "\n",
+        "1. If you are running this notebook locally, you will need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+        "\n",
+        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
       ]
     },
     {
@@ -184,7 +327,10 @@
       },
       "outputs": [],
       "source": [
-        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
+        "\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
       ]
     },
     {
@@ -211,6 +357,67 @@
         "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "77c385f0db59"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already authenticated. Skip this step.\n",
+        "\n",
+        "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\n",
+        "\n",
+        "1. **Click Create service account**.\n",
+        "\n",
+        "2. In the **Service account name** field, enter a name, and click **Create**.\n",
+        "\n",
+        "3. In the **Grant this service account access to project** section, click the Role drop-down list. Type \"Vertex AI\" into the filter box, and select **Vertex AI Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "4. Click Create. A JSON file that contains your key downloads to your local environment.\n",
+        "\n",
+        "5. Enter the path to your service account key as the GOOGLE_APPLICATION_CREDENTIALS variable in the cell below and run the cell."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "535223fa4b84"
+      },
+      "outputs": [],
+      "source": [
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
+        "IS_COLAB = False\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
+        "    \"DL_ANACONDA_HOME\"\n",
+        "):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        IS_COLAB = True\n",
+        "        from google.colab import auth as google_auth\n",
+        "\n",
+        "        google_auth.authenticate_user()\n",
+        "\n",
+        "    # If you are running this notebook locally, replace the string below with the\n",
+        "    # path to your service account key and run this cell to authenticate your GCP\n",
+        "    # account.\n",
+        "    elif not os.getenv(\"IS_TESTING\"):\n",
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -468,9 +675,9 @@
         "id": "sklearn_intro"
       },
       "source": [
-        "## Introduction to Scikit-learn training\n",
+        "## Introduction to scikit-learn training\n",
         "\n",
-        "Once you have trained a Scikit-learn model, you will want to save it at a Cloud Storage location, so it can subsequently be uploaded to a `Vertex AI Model` resource. The Scikit-learn package does not have support to save the model to a Cloud Storage location. Instead, you will do the following steps to save to a Cloud Storage location.\n",
+        "Once you have trained a scikit-learn model, you will want to save it at a Cloud Storage location, so it can subsequently be uploaded to a `Vertex AI Model` resource. The Scikit-learn package does not have support to save the model to a Cloud Storage location. Instead, you will do the following steps to save to a Cloud Storage location.\n",
         "\n",
         "1. Save the in-memory model to the local filesystem in pickle format (e.g., model.pkl).\n",
         "2. Create a Cloud Storage storage client.\n",
@@ -955,7 +1162,6 @@
         "\n",
         "\n",
         "- Model\n",
-        "- Custom Job (already deleted in previous cell)\n",
         "- Cloud Storage Bucket"
       ]
     },
@@ -970,7 +1176,8 @@
         "# Delete the model using the Vertex model object\n",
         "model.delete()\n",
         "\n",
-        "if os.getenv(\"IS_TESTING\"):\n",
+        "delete_bucket = False\n",
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
         "    ! gsutil rm -r $BUCKET_URI"
       ]
     }

notebooks/community/ml_ops/stage2/get_started_vertex_training_xgboost.ipynb

@@ -29,9 +29,15 @@
         "id": "title:generic,gcp"
       },
       "source": [
-        "# E2E ML on GCP: MLOps stage 2 : experimentation: get started with Vertex Training for XGBoost\n",
+        "# E2E ML on GCP: MLOps stage 2 : experimentation: get started with Vertex AI Training for XGBoost\n",
         "\n",
         "<table align=\"left\">\n",
+        "    <td>\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_vertex_training_xgboost.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "    </a>\n",
+        "  </td>\n",
+        "    \n",
         "  <td>\n",
         "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_vertex_training_xgboost.ipynb\">\n",
         "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
@@ -39,8 +45,9 @@
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://console.cloud.google.com/ai/platform/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_vertex_training_xgboost.ipynb\">\n",
-        "      Open in Google Cloud Notebooks\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/ml_ops/stage2/get_started_vertex_training_xgboost.ipynb\">\n",
+        "    <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "      Open in Vertex AI Workbench\n",
         "    </a>\n",
         "  </td>\n",
         "</table>\n",
@@ -56,7 +63,7 @@
         "## Overview\n",
         "\n",
         "\n",
-        "This tutorial demonstrates how to use Vertex AI for E2E MLOps on Google Cloud in production. This tutorial covers stage 2 : experimentation: get started with Vertex Training for XGBoost."
+        "This tutorial demonstrates how to use Vertex AI for E2E MLOps on Google Cloud in production. This tutorial covers stage 2 : experimentation: get started with Vertex AI Training for XGBoost."
       ]
     },
     {
@@ -90,7 +97,21 @@
         "- Training using a Python package.\n",
         "- Report accuracy when hyperparameter tuning.\n",
         "- Save the model artifacts to Cloud Storage using GCSFuse.\n",
-        "- Create a `Vertex AI Model` resource."
+        "- Create a `Vertex AI Model` resource.\n",
+        "\n",
+        "### Costs \n",
+        "\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "* Vertex AI\n",
+        "* Cloud Storage\n",
+        "\n",
+        "\n",
+        "Learn about [Vertex AI\n",
+        "pricing](https://cloud.google.com/vertex-ai/pricing) and [Cloud Storage\n",
+        "pricing](https://cloud.google.com/storage/pricing), and use the [Pricing\n",
+        "Calculator](https://cloud.google.com/products/calculator/)\n",
+        "to generate a cost estimate based on your projected usage."
       ]
     },
     {
@@ -101,62 +122,57 @@
       "source": [
         "## Installations\n",
         "\n",
-        "Install *one time* the packages for executing the MLOps notebooks."
+        "Install the following packages to execute this notebook."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "install_mlops"
-      },
-      "outputs": [],
-      "source": [
-        "ONCE_ONLY = False\n",
-        "if ONCE_ONLY:\n",
-        "    ! pip3 install -U tensorflow==2.5 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-data-validation==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-transform==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-io==0.18 $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-aiplatform[tensorboard] $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-pipeline-components $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-bigquery $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-logging $USER_FLAG\n",
-        "    ! pip3 install --upgrade apache-beam[gcp] $USER_FLAG\n",
-        "    ! pip3 install --upgrade pyarrow $USER_FLAG\n",
-        "    ! pip3 install --upgrade cloudml-hypertune $USER_FLAG\n",
-        "    ! pip3 install --upgrade kfp $USER_FLAG\n",
-        "    ! pip3 install --upgrade torchvision $USER_FLAG\n",
-        "    ! pip3 install --upgrade rpy2 $USER_FLAG"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "restart"
-      },
-      "source": [
-        "### Restart the kernel\n",
-        "\n",
-        "Once you've installed the additional packages, you need to restart the notebook kernel so it can find the packages."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "restart"
+        "id": "ncRJ_Dfdox9L"
       },
       "outputs": [],
       "source": [
         "import os\n",
         "\n",
-        "if not os.getenv(\"IS_TESTING\"):\n",
-        "    # Automatically restart kernel after installs\n",
-        "    import IPython\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\") and not os.getenv(\"VIRTUAL_ENV\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
         "\n",
-        "    app = IPython.Application.instance()\n",
-        "    app.kernel.do_shutdown(True)"
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
+        "USER_FLAG = \"\"\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "\n",
+        "! pip3 install --upgrade google-cloud-aiplatform $USER_FLAG -q"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "2721ef0202d9"
+      },
+      "source": [
+        "## Before you begin\n",
+        "\n",
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com). \n",
+        "\n",
+        "1. If you are running this notebook locally, you will need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+        "\n",
+        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
       ]
     },
     {
@@ -231,11 +247,14 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "region"
+        "id": "sKBTnvJpox9P"
       },
       "outputs": [],
       "source": [
-        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+        "REGION = \"[your-region]\"  # @param {type:\"string\"}\n",
+        "\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\"  # @param {type: \"string\"}"
       ]
     },
     {
@@ -253,7 +272,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "timestamp"
+        "id": "JYtXOocrox9Q"
       },
       "outputs": [],
       "source": [
@@ -262,6 +281,67 @@
         "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "77c385f0db59"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already authenticated. Skip this step.\n",
+        "\n",
+        "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\n",
+        "\n",
+        "1. **Click Create service account**.\n",
+        "\n",
+        "2. In the **Service account name** field, enter a name, and click **Create**.\n",
+        "\n",
+        "3. In the **Grant this service account access to project** section, click the Role drop-down list. Type \"Vertex AI\" into the filter box, and select **Vertex AI Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "4. Click Create. A JSON file that contains your key downloads to your local environment.\n",
+        "\n",
+        "5. Enter the path to your service account key as the GOOGLE_APPLICATION_CREDENTIALS variable in the cell below and run the cell."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "NNc5Bf_NpPTq"
+      },
+      "outputs": [],
+      "source": [
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
+        "IS_COLAB = False\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
+        "    \"DL_ANACONDA_HOME\"\n",
+        "):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        IS_COLAB = True\n",
+        "        from google.colab import auth as google_auth\n",
+        "\n",
+        "        google_auth.authenticate_user()\n",
+        "\n",
+        "    # If you are running this notebook locally, replace the string below with the\n",
+        "    # path to your service account key and run this cell to authenticate your GCP\n",
+        "    # account.\n",
+        "    elif not os.getenv(\"IS_TESTING\"):\n",
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -272,7 +352,7 @@
         "\n",
         "**The following steps are required, regardless of your notebook environment.**\n",
         "\n",
-        "When you initialize the Vertex SDK for Python, you specify a Cloud Storage staging bucket. The staging bucket is where all the data associated with your dataset and model resources are retained across sessions.\n",
+        "When you initialize the Vertex AI SDK for Python, you specify a Cloud Storage staging bucket. The staging bucket is where all the data associated with your dataset and model resources are retained across sessions.\n",
         "\n",
         "Set the name of your Cloud Storage bucket below. Bucket names must be globally unique across all Google Cloud projects, including those outside of your organization."
       ]
@@ -285,7 +365,7 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
+        "BUCKET_URI = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
       ]
     },
     {
@@ -296,8 +376,8 @@
       },
       "outputs": [],
       "source": [
-        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"gs://[your-bucket-name]\":\n",
-        "    BUCKET_NAME = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
+        "if BUCKET_URI == \"\" or BUCKET_URI is None or BUCKET_URI == \"gs://[your-bucket-name]\":\n",
+        "    BUCKET_URI = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
       ]
     },
     {
@@ -313,11 +393,11 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "create_bucket"
+        "id": "aO4sKJfFox9R"
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION $BUCKET_NAME"
+        "! gsutil mb -l $REGION $BUCKET_URI"
       ]
     },
     {
@@ -333,11 +413,11 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "validate_bucket"
+        "id": "yWnghzKFox9S"
       },
       "outputs": [],
       "source": [
-        "! gsutil ls -al $BUCKET_NAME"
+        "! gsutil ls -al $BUCKET_URI"
       ]
     },
     {
@@ -378,11 +458,11 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "init_aip:mbsdk"
+        "id": "JZg2sszQox9T"
       },
       "outputs": [],
       "source": [
-        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_NAME)"
+        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_URI)"
       ]
     },
     {
@@ -411,10 +491,12 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "accelerators:training,cpu,prediction,cpu,mbsdk"
+        "id": "cQUrG4Mbox9T"
       },
       "outputs": [],
       "source": [
+        "import os\n",
+        "\n",
         "if os.getenv(\"IS_TESTING_TRAIN_GPU\"):\n",
         "    TRAIN_GPU, TRAIN_NGPU = (\n",
         "        aip.gapic.AcceleratorType.NVIDIA_TESLA_K80,\n",
@@ -453,7 +535,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "container:training,prediction,xgboost"
+        "id": "XujRA5ueox9U"
       },
       "outputs": [],
       "source": [
@@ -497,7 +579,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "machine:training"
+        "id": "UMPFgENkox9U"
       },
       "outputs": [],
       "source": [
@@ -561,7 +643,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "examine_training_package:xgboost"
+        "id": "f4wS4eISox9V"
       },
       "outputs": [],
       "source": [
@@ -616,7 +698,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "taskpy_contents:iris,xgboost"
+        "id": "WiSnFuDoox9W"
       },
       "outputs": [],
       "source": [
@@ -731,14 +813,14 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "tarball_training_script"
+        "id": "dnmdycf6ox9X"
       },
       "outputs": [],
       "source": [
         "! rm -f custom.tar custom.tar.gz\n",
         "! tar cvf custom.tar custom\n",
         "! gzip custom.tar\n",
-        "! gsutil cp custom.tar.gz $BUCKET_NAME/trainer_iris.tar.gz"
+        "! gsutil cp custom.tar.gz $BUCKET_URI/trainer_iris.tar.gz"
       ]
     },
     {
@@ -770,7 +852,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "create_custom_pp_training_job:mbsdk"
+        "id": "rVEMz1xqox9X"
       },
       "outputs": [],
       "source": [
@@ -778,7 +860,7 @@
         "\n",
         "job = aip.CustomPythonPackageTrainingJob(\n",
         "    display_name=DISPLAY_NAME,\n",
-        "    python_package_gcs_uri=f\"{BUCKET_NAME}/trainer_iris.tar.gz\",\n",
+        "    python_package_gcs_uri=f\"{BUCKET_URI}/trainer_iris.tar.gz\",\n",
         "    python_module_name=\"trainer.task\",\n",
         "    container_uri=TRAIN_IMAGE,\n",
         "    model_serving_container_image_uri=DEPLOY_IMAGE,\n",
@@ -809,11 +891,11 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "prepare_custom_cmdargs:iris,xgboost"
+        "id": "AoUfpBqVox9Y"
       },
       "outputs": [],
       "source": [
-        "MODEL_DIR = \"{}/{}\".format(BUCKET_NAME, TIMESTAMP)\n",
+        "MODEL_DIR = \"{}/{}\".format(BUCKET_URI, TIMESTAMP)\n",
         "DATASET_DIR = \"gs://cloud-samples-data/ai-platform/iris\"\n",
         "\n",
         "ROUNDS = 20\n",
@@ -858,7 +940,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "run_custom_job:mbsdk"
+        "id": "JCruQq1aox9Y"
       },
       "outputs": [],
       "source": [
@@ -899,7 +981,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "list_job"
+        "id": "KBM_KLMSox9Y"
       },
       "outputs": [],
       "source": [
@@ -922,7 +1004,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "custom_job_wait:mbsdk"
+        "id": "lHPMHbSyox9Z"
       },
       "outputs": [],
       "source": [
@@ -944,7 +1026,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "delete_job"
+        "id": "tlYg7Sp-ox9Z"
       },
       "outputs": [],
       "source": [
@@ -964,14 +1046,7 @@
         "\n",
         "Otherwise, you can delete the individual resources you created in this tutorial:\n",
         "\n",
-        "- Dataset\n",
-        "- Pipeline\n",
-        "- Model\n",
-        "- Endpoint\n",
-        "- AutoML Training Job\n",
-        "- Batch Job\n",
-        "- Custom Job\n",
-        "- Hyperparameter Tuning Job\n",
+        "- Custom Job (Custome Training job is remove in previous step)\n",
         "- Cloud Storage Bucket"
       ]
     },
@@ -979,65 +1054,14 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "cleanup:mbsdk"
+        "id": "JyWy23gDox9a"
       },
       "outputs": [],
       "source": [
-        "delete_all = True\n",
+        "delete_bucket = False\n",
         "\n",
-        "if delete_all:\n",
-        "    # Delete the dataset using the Vertex dataset object\n",
-        "    try:\n",
-        "        if \"dataset\" in globals():\n",
-        "            dataset.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the model using the Vertex model object\n",
-        "    try:\n",
-        "        if \"model\" in globals():\n",
-        "            model.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the endpoint using the Vertex endpoint object\n",
-        "    try:\n",
-        "        if \"endpoint\" in globals():\n",
-        "            endpoint.undeploy_all()\n",
-        "            endpoint.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the AutoML or Pipeline training job\n",
-        "    try:\n",
-        "        if \"dag\" in globals():\n",
-        "            dag.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the custom training job\n",
-        "    try:\n",
-        "        if \"job\" in globals():\n",
-        "            job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the batch prediction job using the Vertex batch prediction object\n",
-        "    try:\n",
-        "        if \"batch_predict_job\" in globals():\n",
-        "            batch_predict_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the hyperparameter tuning job using the Vertex hyperparameter tuning object\n",
-        "    try:\n",
-        "        if \"hpt_job\" in globals():\n",
-        "            hpt_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    if \"BUCKET_NAME\" in globals():\n",
-        "        ! gsutil rm -r $BUCKET_NAME"
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil rm -r $BUCKET_URI"
       ]
     }
   ],

notebooks/community/ml_ops/stage2/get_started_vertex_vizier.ipynb

@@ -29,7 +29,7 @@
         "id": "title:generic,gcp"
       },
       "source": [
-        "# E2E ML on GCP: MLOps stage 2 : experimentation: get started with Vertex Vizier\n",
+        "# E2E ML on GCP: MLOps stage 2 : experimentation: get started with Vertex AI Vizier\n",
         "\n",
         "<table align=\"left\">\n",
         "  <td>\n",
@@ -39,7 +39,12 @@
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_vertex_vizier.ipynb\">\n",
+        "        <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_vertex_vizier.ipynb\">\n",
+        "        <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "        </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/ml_ops/stage2/get_started_vertex_vizier.ipynb\">\n",
         "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
         "      Open in Vertex AI Workbench\n",
         "    </a>\n",
@@ -137,7 +142,7 @@
       "source": [
         "## Installations\n",
         "\n",
-        "Install *one time* the packages for executing the MLOps notebooks."
+        "Install the packages required for executing this notebook."
       ]
     },
     {
@@ -150,25 +155,18 @@
       "source": [
         "import os\n",
         "\n",
-        "# The Google Cloud Notebook product has specific requirements\n",
-        "IS_GOOGLE_CLOUD_NOTEBOOK = os.path.exists(\"/opt/deeplearning/metadata/env_version\")\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\") and not os.getenv(\"VIRTUAL_ENV\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
         "\n",
-        "# Google Cloud Notebook requires dependencies to be installed with '--user'\n",
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
         "USER_FLAG = \"\"\n",
-        "if IS_GOOGLE_CLOUD_NOTEBOOK:\n",
-        "    USER_FLAG = \"--user\""
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "install_mlops"
-      },
-      "outputs": [],
-      "source": [
-        "! pip3 install --upgrade google-cloud-aiplatform[tensorboard] $USER_FLAG\n",
-        "    "
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "\n",
+        "! pip3 install --upgrade google-cloud-aiplatform[tensorboard] $USER_FLAG"
       ]
     },
     {
@@ -200,6 +198,32 @@
         "    app.kernel.do_shutdown(True)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "2721ef0202d9"
+      },
+      "source": [
+        "## Before you begin\n",
+        "\n",
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com). \n",
+        "\n",
+        "1. If you are running this notebook locally, you will need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+        "\n",
+        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -305,6 +329,67 @@
         "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "gcp_authenticate"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already authenticated. Skip this step.\n",
+        "\n",
+        "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\n",
+        "\n",
+        "**Click Create service account**.\n",
+        "\n",
+        "In the **Service account name** field, enter a name, and click **Create**.\n",
+        "\n",
+        "In the **Grant this service account access to project** section, click the Role drop-down list. Type \"Vertex\" into the filter box, and select **Vertex Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "Click Create. A JSON file that contains your key downloads to your local environment.\n",
+        "\n",
+        "Enter the path to your service account key as the GOOGLE_APPLICATION_CREDENTIALS variable in the cell below and run the cell."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "gcp_authenticate"
+      },
+      "outputs": [],
+      "source": [
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
+        "IS_COLAB = False\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
+        "    \"DL_ANACONDA_HOME\"\n",
+        "):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        IS_COLAB = True\n",
+        "        from google.colab import auth as google_auth\n",
+        "\n",
+        "        google_auth.authenticate_user()\n",
+        "\n",
+        "    # If you are running this notebook locally, replace the string below with the\n",
+        "    # path to your service account key and run this cell to authenticate your GCP\n",
+        "    # account.\n",
+        "    elif not os.getenv(\"IS_TESTING\"):\n",
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -1598,6 +1683,8 @@
       },
       "outputs": [],
       "source": [
+        "delete_bucket = False\n",
+        "\n",
         "if os.getenv(\"IS_TESTING\"):\n",
         "    ! gsutil rm -r $BUCKET_URI"
       ]

notebooks/community/ml_ops/stage2/get_started_with_cmek_training.ipynb

@@ -38,8 +38,14 @@
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://console.cloud.google.com/ai/platform/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_with_cmek_training.ipynb\">\n",
-        "      Open in Google Cloud Notebooks\n",
+        "        <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_with_cmek_training.ipynb\">\n",
+        "        <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "        </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/ml_ops/stage2/get_started_with_cmek_training.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "      Open in Vertex AI Workbench\n",
         "    </a>\n",
         "  </td>\n",
         "</table>\n",
@@ -91,6 +97,26 @@
         "- Train an AutoML model with CMEK encryption."
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "5e2eba58ad71"
+      },
+      "source": [
+        "### Costs \n",
+        "\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "* Vertex AI\n",
+        "* Cloud Storage\n",
+        "\n",
+        "Learn about [Vertex AI\n",
+        "pricing](https://cloud.google.com/vertex-ai/pricing) and [Cloud Storage\n",
+        "pricing](https://cloud.google.com/storage/pricing), and use the [Pricing\n",
+        "Calculator](https://cloud.google.com/products/calculator/)\n",
+        "to generate a cost estimate based on your projected usage."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -110,10 +136,21 @@
       },
       "outputs": [],
       "source": [
-        "USER_FLAG = \"--user\"\n",
+        "import os\n",
         "\n",
-        "! pip3 install --upgrade google-cloud-aiplatform $USER_FLAG\n",
-        "! pip3 install --upgrade google-cloud-kms $USER_FLAG"
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\") and not os.getenv(\"VIRTUAL_ENV\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
+        "\n",
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
+        "USER_FLAG = \"\"\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "\n",
+        "! pip3 install --upgrade google-cloud-aiplatform $USER_FLAG -q\n",
+        "! pip3 install --upgrade google-cloud-kms $USER_FLAG -q"
       ]
     },
     {
@@ -145,6 +182,39 @@
         "    app.kernel.do_shutdown(True)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "013daf3de88e"
+      },
+      "source": [
+        "## Before you begin"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "d1afc945645f"
+      },
+      "source": [
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com). \n",
+        "\n",
+        "1. If you are running this notebook locally, you will need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+        "\n",
+        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -248,6 +318,82 @@
         "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "d35af059208d"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already\n",
+        "authenticated. Skip this step."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "a00567d0660a"
+      },
+      "source": [
+        "**If you are using Colab**, run the cell below and follow the instructions\n",
+        "when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "1. In the Cloud Console, go to the [**Create service account key**\n",
+        "   page](https://console.cloud.google.com/apis/credentials/serviceaccountkey).\n",
+        "\n",
+        "2. Click **Create service account**.\n",
+        "\n",
+        "3. In the **Service account name** field, enter a name, and\n",
+        "   click **Create**.\n",
+        "\n",
+        "4. In the **Grant this service account access to project** section, click the **Role** drop-down list. Type \"Vertex AI\"\n",
+        "into the filter box, and select\n",
+        "   **Vertex AI Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "5. Click *Create*. A JSON file that contains your key downloads to your\n",
+        "local environment.\n",
+        "\n",
+        "6. Enter the path to your service account key as the\n",
+        "`GOOGLE_APPLICATION_CREDENTIALS` variable in the cell below and run the cell."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "40160162ea4c"
+      },
+      "outputs": [],
+      "source": [
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
+        "IS_COLAB = False\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
+        "    \"DL_ANACONDA_HOME\"\n",
+        "):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        IS_COLAB = True\n",
+        "        from google.colab import auth as google_auth\n",
+        "\n",
+        "        google_auth.authenticate_user()\n",
+        "\n",
+        "    # If you are running this notebook locally, replace the string below with the\n",
+        "    # path to your service account key and run this cell to authenticate your GCP\n",
+        "    # account.\n",
+        "    elif not os.getenv(\"IS_TESTING\"):\n",
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -271,7 +417,7 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
+        "BUCKET_URI = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
       ]
     },
     {
@@ -282,8 +428,8 @@
       },
       "outputs": [],
       "source": [
-        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"gs://[your-bucket-name]\":\n",
-        "    BUCKET_NAME = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
+        "if BUCKET_URI == \"\" or BUCKET_URI is None or BUCKET_URI == \"gs://[your-bucket-name]\":\n",
+        "    BUCKET_URI = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
       ]
     },
     {
@@ -303,7 +449,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION $BUCKET_NAME"
+        "! gsutil mb -l $REGION $BUCKET_URI"
       ]
     },
     {
@@ -323,7 +469,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil ls -al $BUCKET_NAME"
+        "! gsutil ls -al $BUCKET_URI"
       ]
     },
     {
@@ -346,7 +492,7 @@
       },
       "outputs": [],
       "source": [
-        "import google.cloud.aiplatform as aip\n",
+        "import google.cloud.aiplatform as aiplatform\n",
         "from google.cloud import kms"
       ]
     },
@@ -369,7 +515,7 @@
       },
       "outputs": [],
       "source": [
-        "aip.init(project=PROJECT_ID, location=REGION, staging_bucket=BUCKET_NAME)"
+        "aiplatform.init(project=PROJECT_ID, location=REGION, staging_bucket=BUCKET_URI)"
       ]
     },
     {
@@ -384,7 +530,7 @@
         "\n",
         "### Enable KMS API\n",
         "\n",
-        "First, you enble the [Cloud Key Management Service (KMS)](https://console.cloud.google.com/flows/enableapi?apiid=cloudkms.googleapis.com)\n",
+        "First, you enable the [Cloud Key Management Service (KMS)](https://console.cloud.google.com/flows/enableapi?apiid=cloudkms.googleapis.com)\n",
         "\n",
         "Learn more about [Customer managed encryption keys (CMEK)](https://cloud.google.com/vertex-ai/docs/general/cmek)"
       ]
@@ -549,6 +695,8 @@
         "\n",
         "Next, you set permissions for your Vertex AI service account to encrypt and decrypt resources using your key.\n",
         "\n",
+        "Note: Compute Engine default service account which is used by this notebook instance for authentication purposes during Google API calls, should be granted the role of Cloud KMS Admin.\n",
+        "\n",
         "Learn more about [Grant Vertex AI permissions](https://cloud.google.com/vertex-ai/docs/general/cmek#grant_permissions)"
       ]
     },
@@ -638,9 +786,9 @@
       },
       "outputs": [],
       "source": [
-        "aip.init(\n",
+        "aiplatform.init(\n",
         "    project=PROJECT_ID,\n",
-        "    staging_bucket=BUCKET_NAME,\n",
+        "    staging_bucket=BUCKET_URI,\n",
         "    location=REGION,\n",
         "    encryption_spec_key_name=ENCRYPTION_SPEC_KEY_NAME,\n",
         ")"
@@ -689,10 +837,10 @@
       },
       "outputs": [],
       "source": [
-        "dataset = aip.ImageDataset.create(\n",
+        "dataset = aiplatform.ImageDataset.create(\n",
         "    display_name=\"flowers_\" + TIMESTAMP,\n",
         "    gcs_source=[IMPORT_FILE],\n",
-        "    import_schema_uri=aip.schema.dataset.ioformat.image.single_label_classification,\n",
+        "    import_schema_uri=aiplatform.schema.dataset.ioformat.image.single_label_classification,\n",
         ")\n",
         "\n",
         "print(dataset.resource_name)"
@@ -727,7 +875,7 @@
         "\n",
         "# This will take around half an hour to run\n",
         "model = job.run(\n",
-        "    dataset=ds,\n",
+        "    dataset=dataset,\n",
         "    model_display_name=\"flowers_\" + TIMESTAMP,\n",
         "    training_fraction_split=0.6,\n",
         "    validation_fraction_split=0.2,\n",
@@ -827,6 +975,25 @@
         "endpoint.undeploy_all()"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "ba77c4e02355"
+      },
+      "source": [
+        "## Cleaning up\n",
+        "\n",
+        "To clean up all Google Cloud resources used in this project, you can [delete the Google Cloud\n",
+        "project](https://cloud.google.com/resource-manager/docs/creating-managing-projects#shutting_down_projects) you used for the tutorial.\n",
+        "\n",
+        "Otherwise, you can delete the individual resources you created in this tutorial:\n",
+        "\n",
+        "- Model\n",
+        "- Dataset\n",
+        "- Cloud Storage Bucket\n",
+        "- Endpoint"
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -835,17 +1002,54 @@
       },
       "outputs": [],
       "source": [
-        "# missing\n",
+        "# Delete endpoint resource\n",
         "endpoint.delete()\n",
+        "\n",
+        "# Delete model resource\n",
         "model.delete()\n",
+        "\n",
+        "# Delete dataset resource\n",
         "dataset.delete()\n",
         "\n",
-        "! gcloud kms keys versions destroy key-version \\\n",
-        "  --key key {KEY_ID} \\\n",
+        "# Set this to true only if you'd like to delete your bucket\n",
+        "delete_bucket = False\n",
+        "\n",
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil rm -r $BUCKET_URI"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "d88c8a053a90"
+      },
+      "source": [
+        "## Destroying CMEK by providing key-version value and other parameters."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "5d8d2fc34346"
+      },
+      "outputs": [],
+      "source": [
+        "! gcloud kms keys versions destroy 1 \\\n",
+        "  --key {KEY_ID} \\\n",
         "  --keyring={KEY_RING_ID} \\\n",
         "  --location={REGION} "
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "f7e42e642ad3"
+      },
+      "source": [
+        "## List of keys "
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,

notebooks/community/ml_ops/stage2/get_started_with_tfhub_models.ipynb

@@ -33,18 +33,19 @@
         "\n",
         "<table align=\"left\">\n",
         "  <td>\n",
-        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage1/get_started_with_tfhub_models.ipynb\">\n",
-        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
-        "    </a>\n",
-        "  </td>\n",
-        "  <td>\n",
-        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage1/get_started_with_tfhub_models.ipynb\">\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_with_tfhub_models.ipynb\">\n",
         "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
         "      View on GitHub\n",
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://console.cloud.google.com/ai/platform/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage1/get_started_with_tfhub_models.ipynb\">\n",
+        "        <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_with_tfhub_models.ipynb\">\n",
+        "        <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "        </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/ml_ops/stage2/get_started_with_tfhub_models.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
         "      Open in Vertex AI Workbench\n",
         "    </a>\n",
         "  </td>\n",
@@ -143,14 +144,20 @@
       "source": [
         "import os\n",
         "\n",
-        "# Google Cloud Notebook\n",
-        "if os.path.exists(\"/opt/deeplearning/metadata/env_version\"):\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\") and not os.getenv(\"VIRTUAL_ENV\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
+        "\n",
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
+        "USER_FLAG = \"\"\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
         "    USER_FLAG = \"--user\"\n",
-        "else:\n",
         "    USER_FLAG = \"\"\n",
         "\n",
-        "! pip3 install --upgrade google-cloud-aiplatform $USER_FLAG\n",
-        "! pip3 install tensorflow-datasets $USER_FLAG"
+        "! pip3 install --upgrade google-cloud-aiplatform $USER_FLAG -q\n",
+        "! pip3 install tensorflow-datasets $USER_FLAG -q"
       ]
     },
     {
@@ -222,7 +229,7 @@
         "\n",
         "2. [Make sure that billing is enabled for your project.](https://cloud.google.com/billing/docs/how-to/modify-project)\n",
         "\n",
-        "3. [Enable the following APIs: Vertex AI APIs, Compute Engine APIs, and Cloud Storage.](https://console.cloud.google.com/flows/enableapi?apiid=ml.googleapis.com,compute_component,storage-component.googleapis.com)\n",
+        "3. [Enable the following APIs: Vertex AI APIs, Compute Engine APIs, and Cloud Storage.](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,compute_component,storage-component.googleapis.com)\n",
         "\n",
         "4. If you are running this notebook locally, you will need to install the [Cloud SDK]((https://cloud.google.com/sdk)).\n",
         "\n",
@@ -346,7 +353,7 @@
       "source": [
         "### Authenticate your Google Cloud account\n",
         "\n",
-        "**If you are using Google Cloud Notebooks**, your environment is already authenticated. Skip this step.\n",
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already authenticated. Skip this step.\n",
         "\n",
         "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
         "\n",
@@ -381,9 +388,13 @@
         "import os\n",
         "import sys\n",
         "\n",
-        "# If on Google Cloud Notebook, then don't execute this code\n",
-        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\"):\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
+        "IS_COLAB = False\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
+        "    \"DL_ANACONDA_HOME\"\n",
+        "):\n",
         "    if \"google.colab\" in sys.modules:\n",
+        "        IS_COLAB = True\n",
         "        from google.colab import auth as google_auth\n",
         "\n",
         "        google_auth.authenticate_user()\n",
@@ -1386,7 +1397,7 @@
       },
       "outputs": [],
       "source": [
-        "delete_bucket = True\n",
+        "delete_bucket = False\n",
         "\n",
         "if delete_bucket and \"BUCKET_URI\" in globals():\n",
         "    ! gsutil rm -r $BUCKET_URI"

notebooks/community/ml_ops/stage2/mlops_experimentation.ipynb

@@ -39,8 +39,14 @@
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://console.cloud.google.com/ai/platform/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/mlops_experimentation.ipynb\">\n",
-        "      Open in Google Cloud Notebooks\n",
+        "        <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/mlops_experimentation.ipynb\">\n",
+        "        <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "        </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/ml_ops/stage2/mlops_experimentation.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "      Open in Vertex AI Workbench\n",
         "    </a>\n",
         "  </td>\n",
         "</table>\n",
@@ -173,6 +179,19 @@
       },
       "outputs": [],
       "source": [
+        "import os\n",
+        "\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\") and not os.getenv(\"VIRTUAL_ENV\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
+        "\n",
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
+        "USER_FLAG = \"\"\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "\n",
         "ONCE_ONLY = False\n",
         "if ONCE_ONLY:\n",
         "    ! pip3 install -U tensorflow==2.5 $USER_FLAG\n",
@@ -220,6 +239,32 @@
         "    app.kernel.do_shutdown(True)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "2721ef0202d9"
+      },
+      "source": [
+        "## Before you begin\n",
+        "\n",
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com). \n",
+        "\n",
+        "1. If you are running this notebook locally, you will need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+        "\n",
+        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -296,7 +341,9 @@
       },
       "outputs": [],
       "source": [
-        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+        "REGION = \"[your-region]\"  # @param {type:\"string\"}\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
       ]
     },
     {
@@ -323,6 +370,75 @@
         "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "648aa9824ac6"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already\n",
+        "authenticated. Skip this step.\n",
+        "\n",
+        "**If you are using Colab**, run the cell below and follow the instructions\n",
+        "when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "1. In the Cloud Console, go to the [**Create service account key**\n",
+        "   page](https://console.cloud.google.com/apis/credentials/serviceaccountkey).\n",
+        "\n",
+        "2. Click **Create service account**.\n",
+        "\n",
+        "3. In the **Service account name** field, enter a name, and\n",
+        "   click **Create**.\n",
+        "\n",
+        "4. In the **Grant this service account access to project** section, click the **Role** drop-down list. Type \"Vertex AI\"\n",
+        "into the filter box, and select\n",
+        "   **Vertex AI Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "5. Click *Create*. A JSON file that contains your key downloads to your\n",
+        "local environment.\n",
+        "\n",
+        "6. Enter the path to your service account key as the\n",
+        "`GOOGLE_APPLICATION_CREDENTIALS` variable in the cell below and run the cell."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "535223fa4b84"
+      },
+      "outputs": [],
+      "source": [
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
+        "IS_COLAB = False\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
+        "    \"DL_ANACONDA_HOME\"\n",
+        "):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        IS_COLAB = True\n",
+        "        from google.colab import auth as google_auth\n",
+        "\n",
+        "        google_auth.authenticate_user()\n",
+        "\n",
+        "    # If you are running this notebook locally, replace the string below with the\n",
+        "    # path to your service account key and run this cell to authenticate your GCP\n",
+        "    # account.\n",
+        "    elif not os.getenv(\"IS_TESTING\"):\n",
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -436,9 +552,16 @@
         "    or SERVICE_ACCOUNT is None\n",
         "    or SERVICE_ACCOUNT == \"[your-service-account]\"\n",
         "):\n",
-        "    # Get your GCP project id from gcloud\n",
-        "    shell_output = !gcloud auth list 2>/dev/null\n",
-        "    SERVICE_ACCOUNT = shell_output[2].replace(\"*\", \"\").strip()\n",
+        "    # Get your service account from gcloud\n",
+        "    if not IS_COLAB:\n",
+        "        shell_output = !gcloud auth list 2>/dev/null\n",
+        "        SERVICE_ACCOUNT = shell_output[2].replace(\"*\", \"\").strip()\n",
+        "\n",
+        "    if IS_COLAB:\n",
+        "        shell_output = ! gcloud projects describe  $PROJECT_ID\n",
+        "        project_number = shell_output[-1].split(\":\")[1].strip().replace(\"'\", \"\")\n",
+        "        SERVICE_ACCOUNT = f\"{project_number}-compute@developer.gserviceaccount.com\"\n",
+        "\n",
         "    print(\"Service Account:\", SERVICE_ACCOUNT)"
       ]
     },
@@ -583,6 +706,8 @@
       },
       "outputs": [],
       "source": [
+        "import os\n",
+        "\n",
         "if os.getenv(\"IS_TESTING_TRAIN_GPU\"):\n",
         "    TRAIN_GPU, TRAIN_NGPU = (\n",
         "        aip.gapic.AcceleratorType.NVIDIA_TESLA_K80,\n",
@@ -1218,7 +1343,7 @@
         "setup_cfg = \"[egg_info]\\n\\ntag_build =\\n\\ntag_date = 0\"\n",
         "! echo \"$setup_cfg\" > custom/setup.cfg\n",
         "\n",
-        "setup_py = \"import setuptools\\n\\nsetuptools.setup(\\n\\n    install_requires=[\\n\\n        'google-cloud-aiplatform',\\n\\n        'cloudml-hypertune',\\n\\n        'tensorflow_datasets==1.3.0',\\n\\n        'tensorflow_data_validation==1.2',\\n\\n    ],\\n\\n    packages=setuptools.find_packages())\"\n",
+        "setup_py = \"import setuptools\\n\\nsetuptools.setup(\\n\\n    install_requires=[\\n\\n        'google-cloud-aiplatform',\\n\\n        'cloudml-hypertune',\\n\\n        'tensorflow_datasets==1.3.0',\\n\\n        'tensorflow==2.5',\\n\\n    'tensorflow_data_validation==1.2',\\n\\n    ],\\n\\n    packages=setuptools.find_packages())\"\n",
         "! echo \"$setup_py\" > custom/setup.py\n",
         "\n",
         "pkg_info = \"Metadata-Version: 1.0\\n\\nName: Chicago Taxi tabular binary classifier\\n\\nVersion: 0.0.0\\n\\nSummary: Demostration training script\\n\\nHome-page: www.google.com\\n\\nAuthor: Google\\n\\nAuthor-email: cdpe@google.com\\n\\nLicense: Public\\n\\nDescription: Demo\\n\\nPlatform: Vertex AI\"\n",
@@ -3011,9 +3136,8 @@
       },
       "source": [
         "## Review model evaluation scores\n",
-        "After your model has finished training, you can review the evaluation scores for it.\n",
         "\n",
-        "First, you need to get a reference to the new model. As with datasets, you can either use the reference to the model variable you created when you deployed the model or you can list all of the models in your project."
+        "After your model training has finished, you can review the evaluation scores for it using the `list_model_evaluations()` method. This method will return an iterator for each evaluation slice."
       ]
     },
     {
@@ -3024,18 +3148,10 @@
       },
       "outputs": [],
       "source": [
-        "# Get model resource ID\n",
-        "models = aip.Model.list(filter=\"display_name=chicago_\" + TIMESTAMP)\n",
+        "model_evaluations = model.list_model_evaluations()\n",
         "\n",
-        "# Get a reference to the Model Service client\n",
-        "client_options = {\"api_endpoint\": f\"{REGION}-aiplatform.googleapis.com\"}\n",
-        "model_service_client = aip.gapic.ModelServiceClient(client_options=client_options)\n",
-        "\n",
-        "model_evaluations = model_service_client.list_model_evaluations(\n",
-        "    parent=models[0].resource_name\n",
-        ")\n",
-        "model_evaluation = list(model_evaluations)[0]\n",
-        "print(model_evaluation)"
+        "for model_evaluation in model_evaluations:\n",
+        "    print(model_evaluation.to_dict())"
       ]
     },
     {

notebooks/community/ml_ops/stage3/README.md

@@ -27,7 +27,7 @@ The third stage in MLOps is formalization to develop an automated pipeline proce
 - Use early stop procedure in training script to detect failure to achieve training objective.
 - Store the results of the trained model evaluation in Vertex AI ML Metadata.
 
-<img src='stage3.png'>
+<img src='stage3v3.png'>
 
 ## Notebooks
 
@@ -144,6 +144,39 @@ The steps performed include:
 - Testing the deployed model infrastructure.
 ```
 
+[Get Started with TFX Pipelines with Vertex AI](get_started_with_tfx_pipeline.ipynb)
+
+```
+The steps performed include:
+
+- Create a TFX e2e pipeline.
+- Execute the pipeline locally.
+- Execute the pipeline on Google Cloud using `Vertex AI Training`
+- Execute the pipeline using `Vertex AI Pipelines`.
+```
+
+[Get Started with machine management](get_started_with_machine_management.ipynb)
+
+```
+The steps performed in this tutorial include:
+
+- Create a custom component with a self-contained training job.
+- Execute pipeline using component-level settings for machine resources
+- Convert the self-contained training componnt into a Vertex AI CustomJob.
+- Execute pipeline using customjob-level settings for machine resources
+```
+
+[Get Started with Apache Airflow and Vertex AI Pipelines](get_started_with_airflow_and_vertex_pipelines.ipynb)
+
+```
+The steps performed in this tutorial include:
+
+- Create Cloud Composer environment.
+- Upload Airflow DAG to Composer environment that performs data processing -- i.e., creates a BigQuery table from a CSV file.
+- Create a Vertex Pipeline that triggers the Airflow DAG.
+- Execute the `Vertex AI Pipeline`.
+```
+
 ### E2E Stage Example
 
 [Stage 3: Formalization](mlops_formalization.ipynb)

notebooks/community/ml_ops/stage3/get_started_with_automl_pipeline_components.ipynb

@@ -8,7 +8,7 @@
       },
       "outputs": [],
       "source": [
-        "# Copyright 2021 Google LLC\n",
+        "# Copyright 2022 Google LLC\n",
         "#\n",
         "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
         "# you may not use this file except in compliance with the License.\n",
@@ -38,8 +38,14 @@
         "      View on GitHub\n",
         "    </a>\n",
         "  </td>\n",
+        "    <td>\n",
+        "        <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage3/get_started_with_automl_pipeline_components.ipynb\">\n",
+        "        <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "        </a>\n",
+        "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://console.cloud.google.com/ai/platform/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage3/get_started_with_automl_pipeline_components.ipynb\">\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/ml_ops/stage3/get_started_with_automl_pipeline_components.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
         "      Open in Vertex AI Workbench\n",
         "    </a>\n",
         "  </td>\n",
@@ -67,7 +73,7 @@
       "source": [
         "### Dataset\n",
         "\n",
-        "The dataset used for this tutorial is the [Flowers dataset](https://www.tensorflow.org/datasets/catalog/tf_flowers) from [TensorFlow Datasets](https://www.tensorflow.org/datasets/catalog/overview). The version of the dataset you will use in this tutorial is stored in a public Cloud Storage bucket. The trained model predicts the type of flower an image is from a class of five flowers: daisy, dandelion, rose, sunflower, or tulip."
+        "The dataset used for this tutorial is the [Flowers dataset](https://www.tensorflow.org/datasets/catalog/tf_flowers) from [TensorFlow Datasets](https://www.tensorflow.org/datasets/catalog/overview). The version of the dataset you will use in this tutorial is stored in a public Cloud Storage bucket. The trained model predicts the type of flower in the given image from the five classes of flowers: daisy, dandelion, rose, sunflower, or tulip."
       ]
     },
     {
@@ -94,7 +100,15 @@
         "    - Training a Vertex AI AutoML trained model.\n",
         "    - Test the serving binary with a batch prediction job.\n",
         "    - Deploying a Vertex AI AutoML trained model.\n",
-        "- Execute a Vertex AI pipeline."
+        "- Execute a Vertex AI pipeline.\n",
+        "\n",
+        "### Costs\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "- Vertex AI\n",
+        "- Cloud Storage\n",
+        "\n",
+        "Learn about [Vertex AI pricing](https://cloud.google.com/vertex-ai/pricing) and [Cloud Storage pricing](https://cloud.google.com/storage/pricing) and use the [Pricing Calculator](https://cloud.google.com/products/calculator/) to generate a cost estimate based on your projected usage."
       ]
     },
     {
@@ -105,7 +119,7 @@
       "source": [
         "## Installations\n",
         "\n",
-        "Install *one time* the packages for executing the MLOps notebooks."
+        "Install the following packages for executing this MLOps notebook."
       ]
     },
     {
@@ -116,24 +130,25 @@
       },
       "outputs": [],
       "source": [
-        "ONCE_ONLY = False\n",
-        "if ONCE_ONLY:\n",
-        "    ! pip3 install -U tensorflow==2.5 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-data-validation==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-transform==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-io==0.18 $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-aiplatform[tensorboard] $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-pipeline-components $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-bigquery $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-logging $USER_FLAG\n",
-        "    ! pip3 install --upgrade apache-beam[gcp] $USER_FLAG\n",
-        "    ! pip3 install --upgrade pyarrow $USER_FLAG\n",
-        "    ! pip3 install --upgrade cloudml-hypertune $USER_FLAG\n",
-        "    ! pip3 install --upgrade kfp $USER_FLAG\n",
-        "    ! pip3 install --upgrade torchvision $USER_FLAG\n",
-        "    ! pip3 install --upgrade rpy2 $USER_FLAG\n",
-        "    ! pip3 install --upgrade python-tabulate $USER_FLAG\n",
-        "    ! pip3 install -U opencv-python-headless==4.5.2.52 $USER_FLAG"
+        "import os\n",
+        "\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\") and not os.getenv(\"VIRTUAL_ENV\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
+        "\n",
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
+        "USER_FLAG = \"\"\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "    \n",
+        "! pip3 install tensorflow-io==0.18 $USER_FLAG -q\n",
+        "! pip3 install --upgrade google-cloud-aiplatform \\\n",
+        "                        google-cloud-pipeline-components \\\n",
+        "                        google-cloud-logging \\\n",
+        "                        pyarrow \\\n",
+        "                        kfp $USER_FLAG -q"
       ]
     },
     {
@@ -144,7 +159,7 @@
       "source": [
         "### Restart the kernel\n",
         "\n",
-        "Once you've installed the additional packages, you need to restart the notebook kernel so it can find the packages."
+        "Once you've installed the additional packages, you need to restart the notebook kernel so that it can find the packages."
       ]
     },
     {
@@ -165,6 +180,30 @@
         "    app.kernel.do_shutdown(True)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "BF1j6f9HApxa"
+      },
+      "source": [
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com).\n",
+        "\n",
+        "1. If you are running this notebook locally, you will need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+        "\n",
+        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -241,7 +280,10 @@
       },
       "outputs": [],
       "source": [
-        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
+        "\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
       ]
     },
     {
@@ -268,6 +310,67 @@
         "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "c38be665ca50"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "**If you are using Vertex AI Notebook Notebooks**, your environment is already authenticated. Skip this step.\n",
+        "\n",
+        "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\n",
+        "\n",
+        "1. **Click Create service account**.\n",
+        "\n",
+        "2. In the **Service account name** field, enter a name, and click **Create**.\n",
+        "\n",
+        "3. In the **Grant this service account access to project** section, click the Role drop-down list. Type \"Vertex\" into the filter box, and select **Vertex Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "4. Click Create. A JSON file that contains your key downloads to your local environment.\n",
+        "\n",
+        "5. Enter the path to your service account key as the GOOGLE_APPLICATION_CREDENTIALS variable in the cell below and run the cell."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "e0953a00668e"
+      },
+      "outputs": [],
+      "source": [
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
+        "IS_COLAB = False\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
+        "    \"DL_ANACONDA_HOME\"\n",
+        "):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        IS_COLAB = True\n",
+        "        from google.colab import auth as google_auth\n",
+        "\n",
+        "        google_auth.authenticate_user()\n",
+        "\n",
+        "    # If you are running this notebook locally, replace the string below with the\n",
+        "    # path to your service account key and run this cell to authenticate your GCP\n",
+        "    # account.\n",
+        "    elif not os.getenv(\"IS_TESTING\"):\n",
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -355,7 +458,7 @@
       "source": [
         "#### Service Account\n",
         "\n",
-        "**If you don't know your service account**, try to get your service account using `gcloud` command by executing the second cell below."
+        "You use a service account to create Vertex AI Pipeline jobs. If you do not want to use your project's Compute Engine service account, set `SERVICE_ACCOUNT` to another service account ID."
       ]
     },
     {
@@ -382,9 +485,16 @@
         "    or SERVICE_ACCOUNT is None\n",
         "    or SERVICE_ACCOUNT == \"[your-service-account]\"\n",
         "):\n",
-        "    # Get your GCP project id from gcloud\n",
-        "    shell_output = !gcloud auth list 2>/dev/null\n",
-        "    SERVICE_ACCOUNT = shell_output[2].replace(\"*\", \"\").strip()\n",
+        "    # Get your service account from gcloud\n",
+        "    if not IS_COLAB:\n",
+        "        shell_output = !gcloud auth list 2>/dev/null\n",
+        "        SERVICE_ACCOUNT = shell_output[2].replace(\"*\", \"\").strip()\n",
+        "\n",
+        "    if IS_COLAB:\n",
+        "        shell_output = ! gcloud projects describe  $PROJECT_ID\n",
+        "        project_number = shell_output[-1].split(\":\")[1].strip().replace(\"'\", \"\")\n",
+        "        SERVICE_ACCOUNT = f\"{project_number}-compute@developer.gserviceaccount.com\"\n",
+        "\n",
         "    print(\"Service Account:\", SERVICE_ACCOUNT)"
       ]
     },
@@ -396,7 +506,7 @@
       "source": [
         "#### Set service account access for Vertex AI Pipelines\n",
         "\n",
-        "Run the following commands to grant your service account access to read and write pipeline artifacts in the bucket that you created in the previous step -- you only need to run these once per service account."
+        "Run the following commands to grant your service account access to read and write pipeline artifacts in the bucket that you created in the previous step. You only need to run this step once per service account."
       ]
     },
     {
@@ -418,32 +528,7 @@
         "id": "setup_vars"
       },
       "source": [
-        "### Set up variables\n",
-        "\n",
-        "Next, set up some variables used throughout the tutorial.\n",
-        "### Import libraries and define constants"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "import_aip:mbsdk"
-      },
-      "outputs": [],
-      "source": [
-        "import google.cloud.aiplatform as aip"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "import_tf"
-      },
-      "source": [
-        "#### Import TensorFlow\n",
-        "\n",
-        "Import the TensorFlow package into your Python environment."
+        "### Import libraries"
       ]
     },
     {
@@ -454,22 +539,14 @@
       },
       "outputs": [],
       "source": [
-        "import tensorflow as tf"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "import_kfp"
-      },
-      "outputs": [],
-      "source": [
+        "import base64\n",
         "import json\n",
         "\n",
+        "import google.cloud.aiplatform as aiplatform\n",
+        "import tensorflow as tf\n",
         "from kfp import dsl\n",
         "from kfp.v2 import compiler\n",
-        "from kfp.v2.dsl import component"
+        "from kfp.v2.dsl import Artifact, Input, Output, component"
       ]
     },
     {
@@ -491,7 +568,7 @@
       },
       "outputs": [],
       "source": [
-        "aip.init(project=PROJECT_ID, location=REGION, staging_bucket=BUCKET_URI)"
+        "aiplatform.init(project=PROJECT_ID, location=REGION, staging_bucket=BUCKET_URI)"
       ]
     },
     {
@@ -531,7 +608,7 @@
         "- Takes as input the region and Model artifacts returned from an AutoML training component.\n",
         "- Create a client interface to the Vertex AI Model service (`metadata[\"resource_name\"]).\n",
         "- Construct the resource ID for the model from the model artifact parameter.\n",
-        "- Retrieve the model evaluation\n",
+        "- Retrieve the model evaluation.\n",
         "- Return the model evaluation as a string."
       ]
     },
@@ -543,9 +620,6 @@
       },
       "outputs": [],
       "source": [
-        "from kfp.v2.dsl import Artifact, Input, Model, Output\n",
-        "\n",
-        "\n",
         "@component(packages_to_install=[\"google-cloud-aiplatform\"])\n",
         "def evaluateAutoMLModelOp(\n",
         "    model: Input[Artifact], region: str, model_evaluation: Output[Artifact]\n",
@@ -578,7 +652,7 @@
         "1. Use the prebuilt component `ImageDatasetCreateOp` to create a Vertex AI Dataset resource, where:\n",
         "    - The display name for the dataset is passed into the pipeline.\n",
         "    - The import file for the dataset is passed into the pipeline.\n",
-        "    - The component returns the dataset resource as `outputs[\"dataset\"]`\n",
+        "    - The component returns the dataset resource as `outputs[\"dataset\"]`.\n",
         "\n",
         "\n",
         "2. Use the prebuilt component `AutoMLImageTrainingJobRunOp` to train a Vertex AI AutoML Model resource, where:\n",
@@ -597,12 +671,12 @@
         "    - The component returns the endpoint resource as `outputs[\"endpoint\"]`.\n",
         "\n",
         "\n",
-        "5. Use the prebuilt component `ModelDeployOp` to deploy the trained AutoML model to, where:\n",
+        "5. Use the prebuilt component `ModelDeployOp` to deploy the trained AutoML model where:\n",
         "    - The display name for the dataset is passed into the pipeline.\n",
         "    - The model is the output from the `AutoMLTrainingJobRunOp`.\n",
-        "    - The endpoint is the output from the `EndpointCreateOp`\n",
+        "    - The endpoint is the output from the `EndpointCreateOp`.\n",
         "\n",
-        "*Note:* Since each component is executed as a graph node in its own execution context, you pass the parameter `project` for each component op, in constrast to doing a `aip.init(project=project)` if this was a Python script calling the SDK methods directly within the same execution context."
+        "*Note:* Since each component is executed as a graph node in its own execution context, you pass the parameter `project` for each component op, in constrast to doing a `aiplatform.init(project=project)` if this was a Python script calling the SDK methods directly within the same execution context."
       ]
     },
     {
@@ -634,7 +708,7 @@
         "        project=project,\n",
         "        display_name=display_name,\n",
         "        gcs_source=import_file,\n",
-        "        import_schema_uri=aip.schema.dataset.ioformat.image.single_label_classification,\n",
+        "        import_schema_uri=aiplatform.schema.dataset.ioformat.image.single_label_classification,\n",
         "    )\n",
         "\n",
         "    training_op = gcc_aip.AutoMLImageTrainingJobRunOp(\n",
@@ -672,7 +746,7 @@
         "        display_name=display_name,\n",
         "    ).after(batch_op)\n",
         "\n",
-        "    deploy_op = gcc_aip.ModelDeployOp(\n",
+        "    _ = gcc_aip.ModelDeployOp(\n",
         "        model=training_op.outputs[\"model\"],\n",
         "        endpoint=endpoint_op.outputs[\"endpoint\"],\n",
         "        automatic_resources_min_replica_count=1,\n",
@@ -689,7 +763,7 @@
       "source": [
         "### Get test item(s)\n",
         "\n",
-        "In the pipeline, you do a batch prediction to your Vertex model. You will use arbitrary examples out of the dataset as a test items. Don't be concerned that the examples were likely used in training the model -- we just want to demonstrate how to make a prediction."
+        "In the pipeline, you do a batch prediction on your Vertex model. You will use arbitrary examples from the dataset as test items. Don't be concerned that the examples were likely used while training the model. This step is just to demonstrate how to make a prediction."
       ]
     },
     {
@@ -749,14 +823,14 @@
       "source": [
         "### Make the batch input file\n",
         "\n",
-        "Now make a batch input file, which you will store in your local Cloud Storage bucket. The batch input file can only be in JSONL. For JSONL file, you make one dictionary entry per line for each data item (instance). The dictionary contains the key/value pairs:\n",
+        "Now make a batch input file, which you will store in your local Cloud Storage bucket. The batch input file can only be in JSONL format. For JSONL file, you make one dictionary entry per line for each data item (instance). The dictionary contains key/value pairs:\n",
         "\n",
         "- `content`: The Cloud Storage path to the image.\n",
         "- `mime_type`: The content type. In our example, it is a `jpeg` file.\n",
         "\n",
         "For example:\n",
         "\n",
-        "                        {'content': '[your-bucket]/file1.jpg', 'mime_type': 'jpeg'}"
+        "    {'content': '[your-bucket]/file1.jpg', 'mime_type': 'jpeg'}"
       ]
     },
     {
@@ -767,10 +841,6 @@
       },
       "outputs": [],
       "source": [
-        "import json\n",
-        "\n",
-        "import tensorflow as tf\n",
-        "\n",
         "gcs_input_uri = BUCKET_URI + \"/test.jsonl\"\n",
         "with tf.io.gfile.GFile(gcs_input_uri, \"w\") as f:\n",
         "    data = {\"content\": test_item_1, \"mime_type\": \"image/jpeg\"}\n",
@@ -811,7 +881,7 @@
         "    pipeline_func=pipeline, package_path=\"automl_icn_training.json\"\n",
         ")\n",
         "\n",
-        "pipeline = aip.PipelineJob(\n",
+        "pipeline = aiplatform.PipelineJob(\n",
         "    display_name=\"automl_icn_training\",\n",
         "    template_path=\"automl_icn_training.json\",\n",
         "    pipeline_root=PIPELINE_ROOT,\n",
@@ -916,7 +986,7 @@
         "output = json.loads(output[0])\n",
         "model_id = output[\"artifacts\"][\"model\"][\"artifacts\"][0][\"metadata\"][\"resourceName\"]\n",
         "print(\"\\n\")\n",
-        "print(endpoint_id)\n",
+        "print(model_id)\n",
         "print(\"endpoint-create\")\n",
         "artifacts = print_pipeline_output(pipeline, \"endpoint-create\")\n",
         "print(\"\\n\\n\")\n",
@@ -991,7 +1061,7 @@
       },
       "outputs": [],
       "source": [
-        "endpoint = aip.Endpoint(endpoint_id)"
+        "endpoint = aiplatform.Endpoint(endpoint_id)"
       ]
     },
     {
@@ -1002,7 +1072,7 @@
       "source": [
         "## Send a online prediction request\n",
         "\n",
-        "Send a online prediction to your deployed model."
+        "Send a online prediction request to your deployed model."
       ]
     },
     {
@@ -1013,7 +1083,7 @@
       "source": [
         "### Get test item\n",
         "\n",
-        "You will use an arbitrary example out of the dataset as a test item. Don't be concerned that the example was likely used in training the model -- we just want to demonstrate how to make a prediction."
+        "You will use an arbitrary example out of the dataset as a test item. Don't be concerned that the example was likely used while training the model. This step is just to demonstrate how to make a prediction."
       ]
     },
     {
@@ -1045,7 +1115,7 @@
         "\n",
         "#### Request\n",
         "\n",
-        "Since in this example your test item is in a Cloud Storage bucket, you open and read the contents of the image using `tf.io.gfile.Gfile()`. To pass the test data to the prediction service, you encode the bytes into base64 -- which makes the content safe from modification while transmitting binary data over the network.\n",
+        "Since in this example your test item is in a Cloud Storage bucket, you open and read the contents of the image using `tf.io.gfile.Gfile()`. To pass the test data to the prediction service, you encode the bytes into base64 which makes the content safe from modification while transmitting binary data over the network.\n",
         "\n",
         "The format of each instance is:\n",
         "\n",
@@ -1071,10 +1141,6 @@
       },
       "outputs": [],
       "source": [
-        "import base64\n",
-        "\n",
-        "import tensorflow as tf\n",
-        "\n",
         "with tf.io.gfile.GFile(test_item, \"rb\") as f:\n",
         "    content = f.read()\n",
         "\n",
@@ -1092,9 +1158,16 @@
         "id": "9d347472d5ba"
       },
       "source": [
+        "# Cleaning up\n",
+        "\n",
+        "To clean up all Google Cloud resources used in this project, you can [delete the Google Cloud\n",
+        "project](https://cloud.google.com/resource-manager/docs/creating-managing-projects#shutting_down_projects) you used for the tutorial.\n",
+        "\n",
+        "Otherwise, you can delete the individual resources you created in this tutorial.\n",
+        "\n",
         "#### Delete the Vertex AI Model, Endpoint and BatchPredictionJob resources\n",
         "\n",
-        "Next, undelpoy and delete the Vertex AI Model, Endpoint and BatchPredictionJob resources."
+        "Undelpoy and delete the Vertex AI Model, Endpoint and BatchPredictionJob resources."
       ]
     },
     {
@@ -1108,25 +1181,22 @@
         "endpoint.undeploy_all()\n",
         "endpoint.delete()\n",
         "\n",
-        "model = aip.Model(model_id)\n",
+        "model = aiplatform.Model(model_id)\n",
         "model.delete()\n",
         "\n",
-        "batch_job = aip.BatchPredictionJob(batch_job_id)\n",
+        "batch_job = aiplatform.BatchPredictionJob(batch_job_id)\n",
         "batch_job.delete()"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "cleanup:mbsdk"
+        "id": "a802da1f6fa7"
       },
       "source": [
-        "# Cleaning up\n",
+        "#### Delete the Cloud Storage bucket\n",
         "\n",
-        "To clean up all Google Cloud resources used in this project, you can [delete the Google Cloud\n",
-        "project](https://cloud.google.com/resource-manager/docs/creating-managing-projects#shutting_down_projects) you used for the tutorial.\n",
-        "\n",
-        "Otherwise, you can delete the individual resources you created in this tutorial."
+        "Set `delete_bucket` to *True* to delete the Cloud storage bucket used in this notebook."
       ]
     },
     {
@@ -1137,12 +1207,10 @@
       },
       "outputs": [],
       "source": [
-        "delete_all = True\n",
+        "delete_bucket = False\n",
         "\n",
-        "if delete_all:\n",
-        "\n",
-        "    if \"BUCKET_URI\" in globals():\n",
-        "        ! gsutil rm -r $BUCKET_URI"
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil rm -r $BUCKET_URI"
       ]
     }
   ],

notebooks/community/ml_ops/stage3/get_started_with_bq_tfdv_pipeline_components.ipynb

@@ -8,7 +8,7 @@
       },
       "outputs": [],
       "source": [
-        "# Copyright 2021 Google LLC\n",
+        "# Copyright 2022 Google LLC\n",
         "#\n",
         "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
         "# you may not use this file except in compliance with the License.\n",
@@ -33,14 +33,20 @@
         "\n",
         "<table align=\"left\">\n",
         "  <td>\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage3/get_started_with_bq_tfdv_pipeline_components.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
         "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage3/get_started_with_bq_tfdv_pipeline_components.ipynb\">\n",
         "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
         "      View on GitHub\n",
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://console.cloud.google.com/ai/platform/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage3/get_started_with_bq_tfdv_pipeline_components.ipynb\">\n",
-        "      Open in Google Cloud Notebooks\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/ml_ops/stage3/get_started_with_bq_tfdv_pipeline_components.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "      Open in Vertex AI Workbench\n",
         "    </a>\n",
         "  </td>\n",
         "</table>\n",
@@ -93,6 +99,28 @@
         "- Execute a Vertex AI pipeline."
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0c997d8d92ce"
+      },
+      "source": [
+        "### Costs \n",
+        "\n",
+        "\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "* Vertex AI\n",
+        "* Cloud Storage\n",
+        "\n",
+        "\n",
+        "Learn about [Vertex AI\n",
+        "pricing](https://cloud.google.com/vertex-ai/pricing) and [Cloud Storage\n",
+        "pricing](https://cloud.google.com/storage/pricing), and use the [Pricing\n",
+        "Calculator](https://cloud.google.com/products/calculator/)\n",
+        "to generate a cost estimate based on your projected usage."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -101,31 +129,33 @@
       "source": [
         "## Installations\n",
         "\n",
-        "Install *one time* the packages for executing the MLOps notebooks."
+        "Install the packages for executing this notebook."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "install_mlops"
+        "id": "1fd00fa70a2a"
       },
       "outputs": [],
       "source": [
-        "ONCE_ONLY = False\n",
-        "if ONCE_ONLY:\n",
-        "    ! pip3 install -U tensorflow==2.5 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-data-validation==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-transform==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-io==0.18 $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-aiplatform[tensorboard] $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-pipeline-components $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-bigquery $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-logging $USER_FLAG\n",
-        "    ! pip3 install --upgrade apache-beam[gcp] $USER_FLAG\n",
-        "    ! pip3 install --upgrade pyarrow $USER_FLAG\n",
-        "    ! pip3 install --upgrade cloudml-hypertune $USER_FLAG\n",
-        "    ! pip3 install --upgrade kfp $USER_FLAG"
+        "import os\n",
+        "\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\") and not os.getenv(\"VIRTUAL_ENV\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
+        "\n",
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
+        "USER_FLAG = \"\"\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "\n",
+        "! pip3 install -U tensorflow $USER_FLAG -q\n",
+        "! pip3 install --upgrade google-cloud-aiplatform[tensorboard] $USER_FLAG -q\n",
+        "! pip3 install --upgrade kfp $USER_FLAG -q"
       ]
     },
     {
@@ -157,6 +187,30 @@
         "    app.kernel.do_shutdown(True)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "BF1j6f9HApxa"
+      },
+      "source": [
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,dataflow.googleapis.com).\n",
+        "\n",
+        "1. If you are running this notebook locally, you will need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+        "\n",
+        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -176,6 +230,8 @@
       },
       "outputs": [],
       "source": [
+        "import os\n",
+        "\n",
         "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
       ]
     },
@@ -233,7 +289,9 @@
       },
       "outputs": [],
       "source": [
-        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+        "REGION = \"[your-region]\"  # @param {type:\"string\"}\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
       ]
     },
     {
@@ -260,6 +318,82 @@
         "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "648aa9824ac6"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already\n",
+        "authenticated. Skip this step."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "fc52bba17ee3"
+      },
+      "source": [
+        "**If you are using Colab**, run the cell below and follow the instructions\n",
+        "when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "1. In the Cloud Console, go to the [**Create service account key**\n",
+        "   page](https://console.cloud.google.com/apis/credentials/serviceaccountkey).\n",
+        "\n",
+        "2. Click **Create service account**.\n",
+        "\n",
+        "3. In the **Service account name** field, enter a name, and\n",
+        "   click **Create**.\n",
+        "\n",
+        "4. In the **Grant this service account access to project** section, click the **Role** drop-down list. Type \"Vertex AI\"\n",
+        "into the filter box, and select\n",
+        "   **Vertex AI Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "5. Click *Create*. A JSON file that contains your key downloads to your\n",
+        "local environment.\n",
+        "\n",
+        "6. Enter the path to your service account key as the\n",
+        "`GOOGLE_APPLICATION_CREDENTIALS` variable in the cell below and run the cell."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "535223fa4b84"
+      },
+      "outputs": [],
+      "source": [
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
+        "IS_COLAB = False\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
+        "    \"DL_ANACONDA_HOME\"\n",
+        "):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        IS_COLAB = True\n",
+        "        from google.colab import auth as google_auth\n",
+        "\n",
+        "        google_auth.authenticate_user()\n",
+        "\n",
+        "    # If you are running this notebook locally, replace the string below with the\n",
+        "    # path to your service account key and run this cell to authenticate your GCP\n",
+        "    # account.\n",
+        "    elif not os.getenv(\"IS_TESTING\"):\n",
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -283,7 +417,7 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
+        "BUCKET_URI = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
       ]
     },
     {
@@ -294,8 +428,8 @@
       },
       "outputs": [],
       "source": [
-        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"gs://[your-bucket-name]\":\n",
-        "    BUCKET_NAME = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
+        "if BUCKET_URI == \"\" or BUCKET_URI is None or BUCKET_URI == \"gs://[your-bucket-name]\":\n",
+        "    BUCKET_URI = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
       ]
     },
     {
@@ -315,7 +449,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION $BUCKET_NAME"
+        "! gsutil mb -l $REGION $BUCKET_URI"
       ]
     },
     {
@@ -335,7 +469,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil ls -al $BUCKET_NAME"
+        "! gsutil ls -al $BUCKET_URI"
       ]
     },
     {
@@ -346,7 +480,9 @@
       "source": [
         "#### Service Account\n",
         "\n",
-        "**If you don't know your service account**, try to get your service account using `gcloud` command by executing the second cell below."
+        "**If you don't know your service account**, try to get your service account using `gcloud` command by executing the second cell below.\n",
+        "\n",
+        "*Note:* The code for automatically finding your service account works on a user-managed Workbench AI noteboook. If you are using a fully-managed notebook or colab, you will need to manually enter your service account."
       ]
     },
     {
@@ -373,9 +509,16 @@
         "    or SERVICE_ACCOUNT is None\n",
         "    or SERVICE_ACCOUNT == \"[your-service-account]\"\n",
         "):\n",
-        "    # Get your GCP project id from gcloud\n",
-        "    shell_output = !gcloud auth list 2>/dev/null\n",
-        "    SERVICE_ACCOUNT = shell_output[2].strip()\n",
+        "    # Get your service account from gcloud\n",
+        "    if not IS_COLAB:\n",
+        "        shell_output = !gcloud auth list 2>/dev/null\n",
+        "        SERVICE_ACCOUNT = shell_output[2].replace(\"*\", \"\").strip()\n",
+        "\n",
+        "    if IS_COLAB:\n",
+        "        shell_output = ! gcloud projects describe  $PROJECT_ID\n",
+        "        project_number = shell_output[-1].split(\":\")[1].strip().replace(\"'\", \"\")\n",
+        "        SERVICE_ACCOUNT = f\"{project_number}-compute@developer.gserviceaccount.com\"\n",
+        "\n",
         "    print(\"Service Account:\", SERVICE_ACCOUNT)"
       ]
     },
@@ -398,9 +541,9 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectCreator $BUCKET_NAME\n",
+        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectCreator $BUCKET_URI\n",
         "\n",
-        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectViewer $BUCKET_NAME"
+        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectViewer $BUCKET_URI"
       ]
     },
     {
@@ -482,7 +625,7 @@
       },
       "outputs": [],
       "source": [
-        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_NAME)"
+        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_URI)"
       ]
     },
     {
@@ -597,7 +740,7 @@
         "    return dataset.column_names\n",
         "\n",
         "\n",
-        "PIPELINE_ROOT = \"{}/pipeline_root/dataset_bq\".format(BUCKET_NAME)\n",
+        "PIPELINE_ROOT = \"{}/pipeline_root/dataset_bq\".format(BUCKET_URI)\n",
         "\n",
         "\n",
         "@dsl.pipeline(\n",
@@ -610,9 +753,9 @@
         "):\n",
         "    create_op = create_dataset_bq(bq_table, display_name, project)\n",
         "\n",
-        "    source_op = get_dataset_source(create_op.output)\n",
+        "    _ = get_dataset_source(create_op.output)\n",
         "\n",
-        "    column_names_op = get_column_names(create_op.output)\n",
+        "    _ = get_column_names(create_op.output)\n",
         "\n",
         "\n",
         "compiler.Compiler().compile(pipeline_func=pipeline, package_path=\"dataset_bq.json\")\n",
@@ -811,7 +954,7 @@
         "    return (stats_file, schema_file)\n",
         "\n",
         "\n",
-        "PIPELINE_ROOT = \"{}/pipeline_root/dataset_stats\".format(BUCKET_NAME)\n",
+        "PIPELINE_ROOT = \"{}/pipeline_root/dataset_stats\".format(BUCKET_URI)\n",
         "\n",
         "\n",
         "@dsl.pipeline(\n",
@@ -819,7 +962,7 @@
         ")\n",
         "def pipeline(dataset_id: str, label: str, bucket: str):\n",
         "\n",
-        "    stats_op = statistics(dataset_id, label, bucket)\n",
+        "    _ = statistics(dataset_id, label, bucket)\n",
         "\n",
         "\n",
         "compiler.Compiler().compile(pipeline_func=pipeline, package_path=\"dataset_stats.json\")\n",
@@ -831,7 +974,7 @@
         "    parameter_values={\n",
         "        \"dataset_id\": dataset_id,\n",
         "        \"label\": \"mean_temp\",\n",
-        "        \"bucket\": BUCKET_NAME,\n",
+        "        \"bucket\": BUCKET_URI,\n",
         "    },\n",
         ")\n",
         "\n",
@@ -901,14 +1044,7 @@
         "\n",
         "Otherwise, you can delete the individual resources you created in this tutorial:\n",
         "\n",
-        "- Dataset\n",
-        "- Pipeline\n",
-        "- Model\n",
-        "- Endpoint\n",
-        "- AutoML Training Job\n",
-        "- Batch Job\n",
-        "- Custom Job\n",
-        "- Hyperparameter Tuning Job\n",
+        "- Vertex AI dataset\n",
         "- Cloud Storage Bucket"
       ]
     },
@@ -920,61 +1056,17 @@
       },
       "outputs": [],
       "source": [
-        "delete_all = True\n",
+        "# Set this to true only if you'd like to delete your bucket\n",
+        "delete_bucket = False\n",
         "\n",
-        "if delete_all:\n",
-        "    # Delete the dataset using the Vertex dataset object\n",
-        "    try:\n",
-        "        if \"dataset\" in globals():\n",
-        "            dataset.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
+        "# Create reference to Vertex AI dataset created in pipeline\n",
+        "dataset = aip.TabularDataset(dataset_id)\n",
         "\n",
-        "    # Delete the model using the Vertex model object\n",
-        "    try:\n",
-        "        if \"model\" in globals():\n",
-        "            model.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
+        "# delete Vertex AI dataset\n",
+        "dataset.delete()\n",
         "\n",
-        "    # Delete the endpoint using the Vertex endpoint object\n",
-        "    try:\n",
-        "        if \"endpoint\" in globals():\n",
-        "            endpoint.undeploy_all()\n",
-        "            endpoint.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the AutoML or Pipeline training job\n",
-        "    try:\n",
-        "        if \"dag\" in globals():\n",
-        "            dag.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the custom training job\n",
-        "    try:\n",
-        "        if \"job\" in globals():\n",
-        "            job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the batch prediction job using the Vertex batch prediction object\n",
-        "    try:\n",
-        "        if \"batch_predict_job\" in globals():\n",
-        "            batch_predict_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the hyperparameter tuning job using the Vertex hyperparameter tuning object\n",
-        "    try:\n",
-        "        if \"hpt_job\" in globals():\n",
-        "            hpt_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    if \"BUCKET_NAME\" in globals():\n",
-        "        ! gsutil rm -r $BUCKET_NAME"
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil rm -r $BUCKET_URI"
       ]
     }
   ],

notebooks/community/ml_ops/stage3/get_started_with_bqml_pipeline_components.ipynb

@@ -33,14 +33,20 @@
         "\n",
         "<table align=\"left\">\n",
         "  <td>\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage3/get_started_with_bqml_pipeline_components.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "    </a>\n",
+        "  </td>  \n",
+        "  <td>\n",
         "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage3/get_started_with_bqml_pipeline_components.ipynb\">\n",
         "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
         "      View on GitHub\n",
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://console.cloud.google.com/ai/platform/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage3/get_started_with_bqml_pipeline_components.ipynb\">\n",
-        "      Open in Google Cloud Notebooks\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/ml_ops/stage3/get_started_with_bqml_pipeline_components.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "      Open in Vertex AI Workbench\n",
         "    </a>\n",
         "  </td>\n",
         "</table>\n",
@@ -99,6 +105,28 @@
         "- Make a prediction with the deployed Vertex AI model."
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0c997d8d92ce"
+      },
+      "source": [
+        "### Costs \n",
+        "\n",
+        "\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "* Vertex AI\n",
+        "* Cloud Storage\n",
+        "\n",
+        "\n",
+        "Learn about [Vertex AI\n",
+        "pricing](https://cloud.google.com/vertex-ai/pricing) and [Cloud Storage\n",
+        "pricing](https://cloud.google.com/storage/pricing), and use the [Pricing\n",
+        "Calculator](https://cloud.google.com/products/calculator/)\n",
+        "to generate a cost estimate based on your projected usage."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -107,35 +135,35 @@
       "source": [
         "## Installations\n",
         "\n",
-        "Install *one time* the packages for executing the MLOps notebooks."
+        "Install the packages required for executing the notebook."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "install_mlops"
+        "id": "1fd00fa70a2a"
       },
       "outputs": [],
       "source": [
-        "ONCE_ONLY = False\n",
-        "if ONCE_ONLY:\n",
-        "    ! pip3 install -U tensorflow==2.5 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-data-validation==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-transform==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-io==0.18 $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-aiplatform[tensorboard] $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-pipeline-components $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-bigquery $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-logging $USER_FLAG\n",
-        "    ! pip3 install --upgrade apache-beam[gcp] $USER_FLAG\n",
-        "    ! pip3 install --upgrade pyarrow $USER_FLAG\n",
-        "    ! pip3 install --upgrade cloudml-hypertune $USER_FLAG\n",
-        "    ! pip3 install --upgrade kfp $USER_FLAG\n",
-        "    ! pip3 install --upgrade torchvision $USER_FLAG\n",
-        "    ! pip3 install --upgrade rpy2 $USER_FLAG\n",
-        "    ! pip3 install --upgrade python-tabulate $USER_FLAG\n",
-        "    ! pip3 install -U opencv-python-headless==4.5.2.52 $USER_FLAG"
+        "import os\n",
+        "\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\") and not os.getenv(\"VIRTUAL_ENV\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
+        "\n",
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
+        "USER_FLAG = \"\"\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "\n",
+        "! pip3 install -U tensorflow $USER_FLAG -q\n",
+        "! pip3 install --upgrade google-cloud-aiplatform[tensorboard] $USER_FLAG -q\n",
+        "! pip3 install --upgrade google-cloud-pipeline-components $USER_FLAG -q\n",
+        "! pip3 install --upgrade google-cloud-bigquery $USER_FLAG -q\n",
+        "! pip3 install --upgrade kfp $USER_FLAG -q"
       ]
     },
     {
@@ -153,7 +181,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "restart"
+        "id": "fIuF_ZjxJ39h"
       },
       "outputs": [],
       "source": [
@@ -167,6 +195,30 @@
         "    app.kernel.do_shutdown(True)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "BF1j6f9HApxa"
+      },
+      "source": [
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,dataflow.googleapis.com).\n",
+        "\n",
+        "1. If you are running this notebook locally, you will need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+        "\n",
+        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -186,6 +238,8 @@
       },
       "outputs": [],
       "source": [
+        "import os\n",
+        "\n",
         "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
       ]
     },
@@ -239,11 +293,13 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "region"
+        "id": "c1Rim3ogJ39j"
       },
       "outputs": [],
       "source": [
-        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+        "REGION = \"[your-region]\"  # @param {type:\"string\"}\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
       ]
     },
     {
@@ -261,7 +317,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "timestamp"
+        "id": "hdkr5x2jJ39k"
       },
       "outputs": [],
       "source": [
@@ -270,6 +326,82 @@
         "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "UG2SHSlTJ39k"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "ETQR4H1HJ39k"
+      },
+      "source": [
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already\n",
+        "authenticated. Skip this step.\n",
+        "\n",
+        "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "1. In the Cloud Console, go to the [**Create service account key**\n",
+        "   page](https://console.cloud.google.com/apis/credentials/serviceaccountkey).\n",
+        "\n",
+        "2. Click **Create service account**.\n",
+        "\n",
+        "3. In the **Service account name** field, enter a name, and\n",
+        "   click **Create**.\n",
+        "\n",
+        "4. In the **Grant this service account access to project** section, click the **Role** drop-down list. Type \"Vertex AI\"\n",
+        "into the filter box, and select\n",
+        "   **Vertex AI Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "5. Click *Create*. A JSON file that contains your key downloads to your\n",
+        "local environment.\n",
+        "\n",
+        "6. Enter the path to your service account key as the\n",
+        "`GOOGLE_APPLICATION_CREDENTIALS` variable in the cell below and run the cell."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "9M66jv07J39l"
+      },
+      "outputs": [],
+      "source": [
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
+        "IS_COLAB = False\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
+        "    \"DL_ANACONDA_HOME\"\n",
+        "):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        IS_COLAB = True\n",
+        "        from google.colab import auth as google_auth\n",
+        "\n",
+        "        google_auth.authenticate_user()\n",
+        "\n",
+        "    # If you are running this notebook locally, replace the string below with the\n",
+        "    # path to your service account key and run this cell to authenticate your GCP\n",
+        "    # account.\n",
+        "    elif not os.getenv(\"IS_TESTING\"):\n",
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -322,7 +454,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "create_bucket"
+        "id": "V97jQQuiJ39m"
       },
       "outputs": [],
       "source": [
@@ -342,7 +474,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "validate_bucket"
+        "id": "7PN6kSQtJ39m"
       },
       "outputs": [],
       "source": [
@@ -366,7 +498,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "set_service_account"
+        "id": "M4WZi4CDJ39n"
       },
       "outputs": [],
       "source": [
@@ -386,9 +518,17 @@
         "    or SERVICE_ACCOUNT is None\n",
         "    or SERVICE_ACCOUNT == \"[your-service-account]\"\n",
         "):\n",
-        "    # Get your GCP project id from gcloud\n",
-        "    shell_output = !gcloud auth list 2>/dev/null\n",
-        "    SERVICE_ACCOUNT = shell_output[2].replace(\"*\", \"\").strip()\n",
+        "    # Get your service account from gcloud\n",
+        "    if not IS_COLAB:\n",
+        "        shell_output = !gcloud auth list 2>/dev/null\n",
+        "        SERVICE_ACCOUNT = shell_output[2].replace(\"*\", \"\").strip()\n",
+        "\n",
+        "    if IS_COLAB:\n",
+        "        shell_output = ! gcloud projects describe  $PROJECT_ID\n",
+        "        # print(\"shell_output=\", shell_output)\n",
+        "        project_number = shell_output[-1].split(\":\")[1].strip().replace(\"'\", \"\")\n",
+        "        SERVICE_ACCOUNT = f\"{project_number}-compute@developer.gserviceaccount.com\"\n",
+        "\n",
         "    print(\"Service Account:\", SERVICE_ACCOUNT)"
       ]
     },
@@ -407,7 +547,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "set_service_account:pipelines"
+        "id": "mI3IJONMJ39n"
       },
       "outputs": [],
       "source": [
@@ -450,8 +590,7 @@
         "import json\n",
         "\n",
         "from kfp import dsl\n",
-        "from kfp.v2 import compiler\n",
-        "from kfp.v2.dsl import component"
+        "from kfp.v2 import compiler"
       ]
     },
     {
@@ -469,7 +608,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "import_bq"
+        "id": "r7p4Iv8_J39o"
       },
       "outputs": [],
       "source": [
@@ -491,7 +630,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "import_tf"
+        "id": "_K5tP8oJJ39p"
       },
       "outputs": [],
       "source": [
@@ -513,7 +652,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "init_aip:mbsdk,all"
+        "id": "uAnLpS9cJ39p"
       },
       "outputs": [],
       "source": [
@@ -535,7 +674,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "init_bq"
+        "id": "I9RloZo9J39p"
       },
       "outputs": [],
       "source": [
@@ -565,7 +704,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "accelerators:prediction,mbsdk"
+        "id": "1-mE_7kXJ39p"
       },
       "outputs": [],
       "source": [
@@ -598,7 +737,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "container:prediction"
+        "id": "AmHM8whxJ39q"
       },
       "outputs": [],
       "source": [
@@ -671,7 +810,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "create_bqml_pipeline:tabular"
+        "id": "LvND7iTpJ39r"
       },
       "outputs": [],
       "source": [
@@ -717,11 +856,11 @@
         "        query=f\"CREATE OR REPLACE MODEL {dataset}.{model} OPTIONS (model_type='dnn_classifier', labels=['{label}'], num_trials={num_trials}) AS SELECT * FROM `{bq_table}` WHERE body_mass_g IS NOT NULL AND sex IS NOT NULL\",\n",
         "    ).after(bq_dataset)\n",
         "\n",
-        "    bq_eval = BigqueryEvaluateModelJobOp(\n",
+        "    _ = BigqueryEvaluateModelJobOp(\n",
         "        project=PROJECT_ID, location=\"US\", model=bq_model.outputs[\"model\"]\n",
         "    ).after(bq_model)\n",
         "\n",
-        "    bq_predict = BigqueryPredictModelJobOp(\n",
+        "    _ = BigqueryPredictModelJobOp(\n",
         "        project=project,\n",
         "        location=location,\n",
         "        model=bq_model.outputs[\"model\"],\n",
@@ -765,7 +904,7 @@
         "        display_name=display_name,\n",
         "    ).after(model_upload)\n",
         "\n",
-        "    deploy_model = ModelDeployOp(\n",
+        "    _ = ModelDeployOp(\n",
         "        model=model_upload.outputs[\"model\"],\n",
         "        endpoint=endpoint.outputs[\"endpoint\"],\n",
         "        dedicated_resources_min_replica_count=min_replica_count,\n",
@@ -807,10 +946,22 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "run_pipeline:bqml"
+        "id": "l2FMs74-J39r"
       },
       "outputs": [],
       "source": [
+        "# If DEPLOY_GPU is None, keeping gpu as no accelerator and accelerator_count as 0\n",
+        "accelerator_count = 0\n",
+        "if DEPLOY_GPU:\n",
+        "    gpu = DEPLOY_GPU.name\n",
+        "    accelerator_count = 1\n",
+        "else:\n",
+        "    gpu = \"ACCELERATOR_TYPE_UNSPECIFIED\"  # Unspecified accelerator type, which means no accelerator.\n",
+        "    accelerator_count = 0\n",
+        "\n",
+        "print(\"gpu=\", gpu)\n",
+        "print(\"accelerator_count=\", accelerator_count)\n",
+        "\n",
         "MODEL_DIR = BUCKET_URI + \"/bqmodel\"\n",
         "\n",
         "compiler.Compiler().compile(pipeline_func=pipeline, package_path=\"bqml.json\")\n",
@@ -831,8 +982,8 @@
         "        \"machine_type\": \"n1-standard-4\",\n",
         "        \"min_replica_count\": 1,\n",
         "        \"max_replica_count\": 1,\n",
-        "        \"accelerator_type\": DEPLOY_GPU.name,\n",
-        "        \"accelerator_count\": DEPLOY_NGPU,\n",
+        "        \"accelerator_type\": gpu,\n",
+        "        \"accelerator_count\": accelerator_count,\n",
         "        \"project\": PROJECT_ID,\n",
         "        \"location\": \"US\",\n",
         "    },\n",
@@ -857,7 +1008,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "view_pipleline_results:bqml"
+        "id": "2OM8zzJXJ39s"
       },
       "outputs": [],
       "source": [
@@ -971,7 +1122,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "delete_pipeline"
+        "id": "1UTEiNi9J39s"
       },
       "outputs": [],
       "source": [
@@ -993,7 +1144,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "endpoint_load:mbsdk"
+        "id": "gPEt5GMAJ39s"
       },
       "outputs": [],
       "source": [
@@ -1040,7 +1191,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "make_test_items:bqml,penguins"
+        "id": "sesK_MSdJ39t"
       },
       "outputs": [],
       "source": [
@@ -1086,7 +1237,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "endpoint_predict:mbsdk"
+        "id": "u5_cgdKQJ39t"
       },
       "outputs": [],
       "source": [
@@ -1114,15 +1265,15 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "delete:bqml,penguins"
+        "id": "W0rhdoHmJ39t"
       },
       "outputs": [],
       "source": [
         "try:\n",
-        "    job = bqclient.delete_model(\"bqml_tutorial.penguins_model\")\n",
+        "    job = bqclient.delete_model(f\"{PROJECT_ID}.bqml_tutorial.penguins_model\")\n",
         "except:\n",
         "    pass\n",
-        "job = bqclient.delete_dataset(\"bqml_tutorial\", delete_contents=True)"
+        "job = bqclient.delete_dataset(f\"{PROJECT_ID}.bqml_tutorial\", delete_contents=True)"
       ]
     },
     {
@@ -1169,15 +1320,15 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "cleanup:mbsdk"
+        "id": "ufWUEbnZJ39u"
       },
       "outputs": [],
       "source": [
-        "delete_all = True\n",
+        "# Set this to true only if you'd like to delete your bucket\n",
+        "delete_bucket = False\n",
         "\n",
-        "if delete_all:\n",
-        "    if \"BUCKET_URI\" in globals():\n",
-        "        ! gsutil rm -r $BUCKET_URI"
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil rm -r $BUCKET_URI"
       ]
     }
   ],

notebooks/community/ml_ops/stage3/get_started_with_custom_training_pipeline_components.ipynb

@@ -8,7 +8,7 @@
       },
       "outputs": [],
       "source": [
-        "# Copyright 2021 Google LLC\n",
+        "# Copyright 2022 Google LLC\n",
         "#\n",
         "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
         "# you may not use this file except in compliance with the License.\n",
@@ -33,14 +33,20 @@
         "\n",
         "<table align=\"left\">\n",
         "  <td>\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage3/get_started_with_custom_training_pipeline_components.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "    </a>\n",
+        "  </td>  \n",
+        "  <td>\n",
         "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage3/get_started_with_custom_training_pipeline_components.ipynb\">\n",
         "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
         "      View on GitHub\n",
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://console.cloud.google.com/ai/platform/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage3/get_started_with_custom_training_pipeline_components.ipynb\">\n",
-        "      Open in Google Cloud Notebooks\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/ml_ops/stage3/get_started_with_custom_training_pipeline_components.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "      Open in Vertex AI Workbench\n",
         "    </a>\n",
         "  </td>\n",
         "</table>\n",
@@ -103,6 +109,28 @@
         "- Execute a Vertex AI pipeline."
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0c997d8d92ce"
+      },
+      "source": [
+        "### Costs \n",
+        "\n",
+        "\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "* Vertex AI\n",
+        "* Cloud Storage\n",
+        "\n",
+        "\n",
+        "Learn about [Vertex AI\n",
+        "pricing](https://cloud.google.com/vertex-ai/pricing) and [Cloud Storage\n",
+        "pricing](https://cloud.google.com/storage/pricing), and use the [Pricing\n",
+        "Calculator](https://cloud.google.com/products/calculator/)\n",
+        "to generate a cost estimate based on your projected usage."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -111,35 +139,34 @@
       "source": [
         "## Installations\n",
         "\n",
-        "Install *one time* the packages for executing the MLOps notebooks."
+        "Install the required packages for executing the notebook."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "install_mlops"
+        "id": "1fd00fa70a2a"
       },
       "outputs": [],
       "source": [
-        "ONCE_ONLY = False\n",
-        "if ONCE_ONLY:\n",
-        "    ! pip3 install -U tensorflow==2.5 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-data-validation==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-transform==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-io==0.18 $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-aiplatform[tensorboard] $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-pipeline-components $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-bigquery $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-logging $USER_FLAG\n",
-        "    ! pip3 install --upgrade apache-beam[gcp] $USER_FLAG\n",
-        "    ! pip3 install --upgrade pyarrow $USER_FLAG\n",
-        "    ! pip3 install --upgrade cloudml-hypertune $USER_FLAG\n",
-        "    ! pip3 install --upgrade kfp $USER_FLAG\n",
-        "    ! pip3 install --upgrade torchvision $USER_FLAG\n",
-        "    ! pip3 install --upgrade rpy2 $USER_FLAG\n",
-        "    ! pip3 install --upgrade python-tabulate $USER_FLAG\n",
-        "    ! pip3 install -U opencv-python-headless==4.5.2.52 $USER_FLAG"
+        "import os\n",
+        "\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\") and not os.getenv(\"VIRTUAL_ENV\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
+        "\n",
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
+        "USER_FLAG = \"\"\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "\n",
+        "! pip3 install -U tensorflow $USER_FLAG -q\n",
+        "! pip3 install --upgrade google-cloud-aiplatform[tensorboard] $USER_FLAG -q\n",
+        "! pip3 install --upgrade google-cloud-pipeline-components $USER_FLAG -q\n",
+        "! pip3 install --upgrade kfp $USER_FLAG -q"
       ]
     },
     {
@@ -171,6 +198,30 @@
         "    app.kernel.do_shutdown(True)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "BF1j6f9HApxa"
+      },
+      "source": [
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,dataflow.googleapis.com).\n",
+        "\n",
+        "1. If you are running this notebook locally, you will need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+        "\n",
+        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -190,6 +241,8 @@
       },
       "outputs": [],
       "source": [
+        "import os\n",
+        "\n",
         "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
       ]
     },
@@ -247,7 +300,9 @@
       },
       "outputs": [],
       "source": [
-        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+        "REGION = \"[your-region]\"  # @param {type:\"string\"}\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
       ]
     },
     {
@@ -274,6 +329,81 @@
         "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "648aa9824ac6"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "fc52bba17ee3"
+      },
+      "source": [
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already\n",
+        "authenticated. Skip this step.\n",
+        "\n",
+        "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "1. In the Cloud Console, go to the [**Create service account key**\n",
+        "   page](https://console.cloud.google.com/apis/credentials/serviceaccountkey).\n",
+        "\n",
+        "2. Click **Create service account**.\n",
+        "\n",
+        "3. In the **Service account name** field, enter a name, and\n",
+        "   click **Create**.\n",
+        "\n",
+        "4. In the **Grant this service account access to project** section, click the **Role** drop-down list. Type \"Vertex AI\"\n",
+        "into the filter box, and select\n",
+        "   **Vertex AI Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "5. Click *Create*. A JSON file that contains your key downloads to your\n",
+        "local environment.\n",
+        "\n",
+        "6. Enter the path to your service account key as the\n",
+        "`GOOGLE_APPLICATION_CREDENTIALS` variable in the cell below and run the cell."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "535223fa4b84"
+      },
+      "outputs": [],
+      "source": [
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
+        "IS_COLAB = False\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
+        "    \"DL_ANACONDA_HOME\"\n",
+        "):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        IS_COLAB = True\n",
+        "        from google.colab import auth as google_auth\n",
+        "\n",
+        "        google_auth.authenticate_user()\n",
+        "\n",
+        "    # If you are running this notebook locally, replace the string below with the\n",
+        "    # path to your service account key and run this cell to authenticate your GCP\n",
+        "    # account.\n",
+        "    elif not os.getenv(\"IS_TESTING\"):\n",
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -388,9 +518,17 @@
         "    or SERVICE_ACCOUNT is None\n",
         "    or SERVICE_ACCOUNT == \"[your-service-account]\"\n",
         "):\n",
-        "    # Get your GCP project id from gcloud\n",
-        "    shell_output = !gcloud auth list 2>/dev/null\n",
-        "    SERVICE_ACCOUNT = shell_output[2].replace(\"*\", \"\").strip()\n",
+        "    # Get your service account from gcloud\n",
+        "    if not IS_COLAB:\n",
+        "        shell_output = !gcloud auth list 2>/dev/null\n",
+        "        SERVICE_ACCOUNT = shell_output[2].replace(\"*\", \"\").strip()\n",
+        "\n",
+        "    if IS_COLAB:\n",
+        "        shell_output = ! gcloud projects describe  $PROJECT_ID\n",
+        "        # print(\"shell_output=\", shell_output)\n",
+        "        project_number = shell_output[-1].split(\":\")[1].strip().replace(\"'\", \"\")\n",
+        "        SERVICE_ACCOUNT = f\"{project_number}-compute@developer.gserviceaccount.com\"\n",
+        "\n",
         "    print(\"Service Account:\", SERVICE_ACCOUNT)"
       ]
     },
@@ -413,9 +551,9 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectCreator $BUCKET_NAME\n",
+        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectCreator $BUCKET_URI\n",
         "\n",
-        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectViewer $BUCKET_NAME"
+        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectViewer $BUCKET_URI"
       ]
     },
     {
@@ -536,7 +674,7 @@
         "        int(os.getenv(\"IS_TESTING_TRAIN_GPU\")),\n",
         "    )\n",
         "else:\n",
-        "    TRAIN_GPU, TRAIN_NGPU = (aip.gapic.AcceleratorType.NVIDIA_TESLA_K80, 1)\n",
+        "    TRAIN_GPU, TRAIN_NGPU = (None, None)\n",
         "\n",
         "if os.getenv(\"IS_TESTING_DEPLOY_GPU\"):\n",
         "    DEPLOY_GPU, DEPLOY_NGPU = (\n",
@@ -1087,6 +1225,17 @@
         "PIPELINE_ROOT = \"{}/pipeline_root/custom_icn_training\".format(BUCKET_URI)\n",
         "DEPLOY_COMPUTE = \"n1-standard-4\"\n",
         "\n",
+        "# If TRAIN_GPU is None, keeping gpu as no accelerator and accelerator_count as 0\n",
+        "gpu = \"ACCELERATOR_TYPE_UNSPECIFIED\"\n",
+        "accelerator_count = 0\n",
+        "\n",
+        "if TRAIN_GPU:\n",
+        "    gpu = TRAIN_GPU.name\n",
+        "    accelerator_count = 1\n",
+        "else:\n",
+        "    gpu = \"ACCELERATOR_TYPE_UNSPECIFIED\"  # Unspecified accelerator type, which means no accelerator.\n",
+        "    accelerator_count = 0\n",
+        "\n",
         "\n",
         "@dsl.pipeline(\n",
         "    name=\"flowers-custom-training\",\n",
@@ -1128,8 +1277,8 @@
         "        args=[\"--epochs\", \"50\", \"--image-width\", \"32\", \"--image-height\", \"32\"],\n",
         "        replica_count=1,\n",
         "        machine_type=TRAIN_COMPUTE,\n",
-        "        accelerator_type=TRAIN_GPU.name,\n",
-        "        accelerator_count=TRAIN_NGPU,\n",
+        "        accelerator_type=gpu,\n",
+        "        accelerator_count=accelerator_count,\n",
         "        # Serving - As part of this operation, the model is registered to Vertex AI\n",
         "        model_serving_container_image_uri=DEPLOY_IMAGE,\n",
         "        model_display_name=display_name,\n",
@@ -1155,7 +1304,7 @@
         "        display_name=display_name,\n",
         "    ).after(batch_op)\n",
         "\n",
-        "    deploy_op = ModelDeployOp(\n",
+        "    _ = ModelDeployOp(\n",
         "        model=training_op.outputs[\"model\"],\n",
         "        endpoint=endpoint_op.outputs[\"endpoint\"],\n",
         "        dedicated_resources_min_replica_count=1,\n",
@@ -1250,10 +1399,6 @@
       },
       "outputs": [],
       "source": [
-        "import json\n",
-        "\n",
-        "import tensorflow as tf\n",
-        "\n",
         "gcs_input_uri = BUCKET_URI + \"/test.jsonl\"\n",
         "with tf.io.gfile.GFile(gcs_input_uri, \"w\") as f:\n",
         "    data = {\"content\": test_item_1, \"mime_type\": \"image/jpeg\"}\n",
@@ -1396,6 +1541,10 @@
         "print(\"image-dataset-create\")\n",
         "artifacts = print_pipeline_output(pipeline, \"image-dataset-create\")\n",
         "print(\"\\n\\n\")\n",
+        "output = !gsutil cat $artifacts\n",
+        "output = json.loads(output[0])\n",
+        "dataset_id = output[\"artifacts\"][\"dataset\"][\"artifacts\"][0][\"metadata\"][\"resourceName\"]\n",
+        "print(\"\\n\\n\")\n",
         "print(\"custompythonpackagetrainingjob-run\")\n",
         "artifacts = print_pipeline_output(pipeline, \"custompythonpackagetrainingjob-run\")\n",
         "print(\"\\n\\n\")\n",
@@ -1462,7 +1611,7 @@
       "source": [
         "#### Delete the Vertex AI Model, Endpoint and BatchPredictionJob resources\n",
         "\n",
-        "Next, undelpoy and delete the Vertex AI Model, Endpoint and BathPredictionJob resources."
+        "Next, delete the daatset, undelpoy and delete the Vertex AI Model, Endpoint and BathPredictionJob resources."
       ]
     },
     {
@@ -1473,6 +1622,13 @@
       },
       "outputs": [],
       "source": [
+        "dataset = aip.ImageDataset(dataset_id)\n",
+        "try:\n",
+        "    dataset.delete()\n",
+        "except:\n",
+        "    pass\n",
+        "\n",
+        "\n",
         "endpoint = aip.Endpoint(endpoint_id)\n",
         "endpoint.undeploy_all()\n",
         "try:\n",
@@ -1532,7 +1688,6 @@
       "outputs": [],
       "source": [
         "from google_cloud_pipeline_components.v1.custom_job import utils\n",
-        "from kfp.v2.dsl import Artifact\n",
         "\n",
         "\n",
         "@component(\n",
@@ -1730,7 +1885,7 @@
         "        display_name=display_name,\n",
         "    ).after(model_upload_op)\n",
         "\n",
-        "    deploy_op = gcc_aip.ModelDeployOp(\n",
+        "    _ = gcc_aip.ModelDeployOp(\n",
         "        model=model_upload_op.outputs[\"model\"],\n",
         "        endpoint=endpoint_op.outputs[\"endpoint\"],\n",
         "        dedicated_resources_min_replica_count=1,\n",
@@ -1920,11 +2075,10 @@
       },
       "outputs": [],
       "source": [
-        "delete_all = True\n",
+        "delete_bucket = False\n",
         "\n",
-        "if delete_all:\n",
-        "    if \"BUCKET_URI\" in globals():\n",
-        "        ! gsutil rm -r $BUCKET_URI"
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil rm -r $BUCKET_URI"
       ]
     }
   ],

notebooks/community/ml_ops/stage3/get_started_with_dataflow_pipeline_components.ipynb

@@ -40,9 +40,17 @@
         "  </td>\n",
         "  <td>\n",
         "    <a href=\"https://console.cloud.google.com/ai/platform/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage3/get_started_with_dataflow_pipeline_components.ipynb\">\n",
-        "      Open in Google Cloud Notebooks\n",
+        "<img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> \n",
+        "        Colab logo Run in Colab\n",
         "    </a>\n",
         "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/ml_ops/stage3/get_started_with_dataflow_pipeline_components.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "      Open in Vertex AI Workbench\n",
+        "    </a>\n",
+        "  </td>   \n",
+        "    \n",
         "</table>\n",
         "<br/><br/><br/>"
       ]
@@ -101,7 +109,7 @@
       "source": [
         "## Installations\n",
         "\n",
-        "Install *one time* the packages for executing the MLOps notebooks."
+        "Install the required packages for executing the notebook."
       ]
     },
     {
@@ -112,24 +120,25 @@
       },
       "outputs": [],
       "source": [
-        "ONCE_ONLY = False\n",
-        "if ONCE_ONLY:\n",
-        "    ! pip3 install -U tensorflow==2.5 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-data-validation==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-transform==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-io==0.18 $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-aiplatform[tensorboard] $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-pipeline-components $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-bigquery $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-logging $USER_FLAG\n",
-        "    ! pip3 install --upgrade apache-beam[gcp] $USER_FLAG\n",
-        "    ! pip3 install --upgrade pyarrow $USER_FLAG\n",
-        "    ! pip3 install --upgrade cloudml-hypertune $USER_FLAG\n",
-        "    ! pip3 install --upgrade kfp $USER_FLAG\n",
-        "    ! pip3 install --upgrade torchvision $USER_FLAG\n",
-        "    ! pip3 install --upgrade rpy2 $USER_FLAG\n",
-        "    ! pip3 install --upgrade python-tabulate $USER_FLAG\n",
-        "    ! pip3 install -U opencv-python-headless==4.5.2.52 $USER_FLAG"
+        "import os\n",
+        "\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
+        "\n",
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
+        "USER_FLAG = \"\"\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "\n",
+        "! pip3 install -U tensorflow $USER_FLAG -q\n",
+        "! pip3 install -U tensorflow-data-validation $USER_FLAG -q\n",
+        "! pip3 install -U tensorflow-transform $USER_FLAG -q\n",
+        "! pip3 install -U tensorflow-io $USER_FLAG -q\n",
+        "! pip3 install --upgrade google-cloud-aiplatform[tensorboard] $USER_FLAG -q\n",
+        "! pip3 install --upgrade google-cloud-pipeline-components $USER_FLAG -q"
       ]
     },
     {
@@ -161,6 +170,30 @@
         "    app.kernel.do_shutdown(True)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "BF1j6f9HApxa"
+      },
+      "source": [
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI API and Dataflow API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,dataflow.googleapis.com).\n",
+        "\n",
+        "1. If you are running this notebook locally, you will need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+        "\n",
+        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -180,7 +213,24 @@
       },
       "outputs": [],
       "source": [
-        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
+        "import os\n",
+        "\n",
+        "PROJECT_ID = \"\"\n",
+        "\n",
+        "if not os.getenv(\"IS_TESTING\"):\n",
+        "    # Get your Google Cloud project ID from gcloud\n",
+        "    shell_output = !gcloud config list --format 'value(core.project)' 2>/dev/null\n",
+        "    PROJECT_ID = shell_output[0]\n",
+        "    print(\"Project ID: \", PROJECT_ID)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "37c0a68ff20d"
+      },
+      "source": [
+        "Otherwise, set your project ID here."
       ]
     },
     {
@@ -191,22 +241,8 @@
       },
       "outputs": [],
       "source": [
-        "if PROJECT_ID == \"\" or PROJECT_ID is None or PROJECT_ID == \"[your-project-id]\":\n",
-        "    # Get your GCP project id from gcloud\n",
-        "    shell_output = ! gcloud config list --format 'value(core.project)' 2>/dev/null\n",
-        "    PROJECT_ID = shell_output[0]\n",
-        "    print(\"Project ID:\", PROJECT_ID)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "set_gcloud_project_id"
-      },
-      "outputs": [],
-      "source": [
-        "! gcloud config set project $PROJECT_ID"
+        "if PROJECT_ID == \"\" or PROJECT_ID is None:\n",
+        "    PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
       ]
     },
     {
@@ -237,7 +273,10 @@
       },
       "outputs": [],
       "source": [
-        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
+        "\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
       ]
     },
     {
@@ -264,6 +303,89 @@
         "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "927085b84a07"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already authenticated. Skip this step.\n",
+        "\n",
+        "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\n",
+        "\n",
+        "**Click Create service account**.\n",
+        "\n",
+        "In the **Service account name** field, enter a name, and click **Create**.\n",
+        "\n",
+        "In the **Grant this service account access to project** section, click the Role drop-down list. Type \"Vertex\" into the filter box, and select **Vertex Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "Click Create. A JSON file that contains your key downloads to your local environment.\n",
+        "\n",
+        "Enter the path to your service account key as the GOOGLE_APPLICATION_CREDENTIALS variable in the cell below and run the cell."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "89788a802687"
+      },
+      "outputs": [],
+      "source": [
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
+        "IS_COLAB = False\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
+        "    \"DL_ANACONDA_HOME\"\n",
+        "):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        IS_COLAB = True\n",
+        "        from google.colab import auth as google_auth\n",
+        "\n",
+        "        google_auth.authenticate_user()\n",
+        "\n",
+        "    # If you are running this notebook locally, replace the string below with the\n",
+        "    # path to your service account key and run this cell to authenticate your GCP\n",
+        "    # account.\n",
+        "    elif not os.getenv(\"IS_TESTING\"):\n",
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "40ed98f5cc48"
+      },
+      "source": [
+        "#### If you are using Colab Notebooks, set the project using gcloud config."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "fde1a355f1e9"
+      },
+      "outputs": [],
+      "source": [
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\"):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        ! gcloud config set project $PROJECT_ID"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -287,7 +409,7 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
+        "BUCKET_URI = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
       ]
     },
     {
@@ -298,8 +420,8 @@
       },
       "outputs": [],
       "source": [
-        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"gs://[your-bucket-name]\":\n",
-        "    BUCKET_NAME = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
+        "if BUCKET_URI == \"\" or BUCKET_URI is None or BUCKET_URI == \"gs://[your-bucket-name]\":\n",
+        "    BUCKET_URI = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
       ]
     },
     {
@@ -319,7 +441,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION $BUCKET_NAME"
+        "! gsutil mb -l $REGION $BUCKET_URI"
       ]
     },
     {
@@ -339,7 +461,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil ls -al $BUCKET_NAME"
+        "! gsutil ls -al $BUCKET_URI"
       ]
     },
     {
@@ -377,9 +499,16 @@
         "    or SERVICE_ACCOUNT is None\n",
         "    or SERVICE_ACCOUNT == \"[your-service-account]\"\n",
         "):\n",
-        "    # Get your GCP project id from gcloud\n",
-        "    shell_output = !gcloud auth list 2>/dev/null\n",
-        "    SERVICE_ACCOUNT = shell_output[2].replace(\"*\", \"\").strip()\n",
+        "    # Get your service account from gcloud\n",
+        "    if not IS_COLAB:\n",
+        "        shell_output = !gcloud auth list 2>/dev/null\n",
+        "        SERVICE_ACCOUNT = shell_output[2].replace(\"*\", \"\").strip()\n",
+        "\n",
+        "    if IS_COLAB:\n",
+        "        shell_output = ! gcloud projects describe  $PROJECT_ID\n",
+        "        project_number = shell_output[-1].split(\":\")[1].strip().replace(\"'\", \"\")\n",
+        "        SERVICE_ACCOUNT = f\"{project_number}-compute@developer.gserviceaccount.com\"\n",
+        "\n",
         "    print(\"Service Account:\", SERVICE_ACCOUNT)"
       ]
     },
@@ -402,9 +531,9 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectCreator $BUCKET_NAME\n",
+        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectCreator $BUCKET_URI\n",
         "\n",
-        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectViewer $BUCKET_NAME"
+        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectViewer $BUCKET_URI"
       ]
     },
     {
@@ -427,35 +556,12 @@
       },
       "outputs": [],
       "source": [
-        "import google.cloud.aiplatform as aip"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "import_kfp"
-      },
-      "outputs": [],
-      "source": [
-        "import json\n",
-        "\n",
-        "from kfp import dsl\n",
-        "from kfp.v2 import compiler\n",
-        "from kfp.v2.dsl import component"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "import_gcpc:dataflow"
-      },
-      "outputs": [],
-      "source": [
+        "import google.cloud.aiplatform as aip\n",
         "from google_cloud_pipeline_components.v1.dataflow import DataflowPythonJobOp\n",
         "from google_cloud_pipeline_components.v1.wait_gcp_resources import \\\n",
-        "    WaitGcpResourcesOp"
+        "    WaitGcpResourcesOp\n",
+        "from kfp import dsl\n",
+        "from kfp.v2 import compiler"
       ]
     },
     {
@@ -477,7 +583,7 @@
       },
       "outputs": [],
       "source": [
-        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_NAME)"
+        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_URI)"
       ]
     },
     {
@@ -673,12 +779,12 @@
       },
       "outputs": [],
       "source": [
-        "GCS_WC_PY = BUCKET_NAME + \"/wc.py\"\n",
+        "GCS_WC_PY = BUCKET_URI + \"/wc.py\"\n",
         "! gsutil cp wc.py $GCS_WC_PY\n",
-        "GCS_REQUIREMENTS_TXT = BUCKET_NAME + \"/requirements.txt\"\n",
+        "GCS_REQUIREMENTS_TXT = BUCKET_URI + \"/requirements.txt\"\n",
         "! gsutil cp requirements.txt $GCS_REQUIREMENTS_TXT\n",
         "\n",
-        "GCS_WC_OUT = BUCKET_NAME + \"/wc_out.txt\""
+        "GCS_WC_OUT = BUCKET_URI + \"/wc_out.txt\""
       ]
     },
     {
@@ -709,9 +815,7 @@
       },
       "outputs": [],
       "source": [
-        "import json\n",
-        "\n",
-        "PIPELINE_ROOT = \"{}/pipeline_root/dataflow_wc\".format(BUCKET_NAME)\n",
+        "PIPELINE_ROOT = \"{}/pipeline_root/dataflow_wc\".format(BUCKET_URI)\n",
         "\n",
         "\n",
         "@dsl.pipeline(name=\"dataflow-wc\", description=\"Dataflow word count component pipeline\")\n",
@@ -733,9 +837,7 @@
         "        args=args,\n",
         "    )\n",
         "\n",
-        "    dataflow_wait_op = WaitGcpResourcesOp(\n",
-        "        gcp_resources=dataflow_python_op.outputs[\"gcp_resources\"]\n",
-        "    )\n",
+        "    _ = WaitGcpResourcesOp(gcp_resources=dataflow_python_op.outputs[\"gcp_resources\"])\n",
         "\n",
         "\n",
         "compiler.Compiler().compile(pipeline_func=pipeline, package_path=\"dataflow_wc.json\")\n",
@@ -813,82 +915,80 @@
         "from apache_beam.options.pipeline_options import SetupOptions\n",
         "\n",
         "def run(argv=None):\n",
-        "  \"\"\"Main entry point; defines and runs the wordcount pipeline.\"\"\"\n",
+        "    \"\"\"Main entry point; defines and runs the wordcount pipeline.\"\"\"\n",
         "\n",
-        "  parser = argparse.ArgumentParser()\n",
-        "  parser.add_argument('--bq_table',\n",
+        "    parser = argparse.ArgumentParser()\n",
+        "    parser.add_argument('--bq_table',\n",
         "                      dest='bq_table')\n",
-        "  parser.add_argument('--bucket',\n",
+        "    parser.add_argument('--bucket',\n",
         "                      dest='bucket')\n",
-        "  args, pipeline_args = parser.parse_known_args(argv)\n",
-        "  logging.info(\"ARGS\")\n",
-        "  logging.info(args)\n",
-        "  logging.info(\"PIPELINE ARGS\")\n",
-        "  logging.info(pipeline_args)\n",
-        "  for i in range(0, len(pipeline_args), 2):\n",
+        "    args, pipeline_args = parser.parse_known_args(argv)\n",
+        "    logging.info(\"ARGS\")\n",
+        "    logging.info(args)\n",
+        "    logging.info(\"PIPELINE ARGS\")\n",
+        "    logging.info(pipeline_args)\n",
+        "    for i in range(0, len(pipeline_args), 2):\n",
         "        if \"--temp_location\" == pipeline_args[i]:\n",
         "            temp_location = pipeline_args[i+1]\n",
         "        elif \"--project\" == pipeline_args[i]:\n",
         "            project = pipeline_args[i+1]\n",
         "\n",
-        "  exported_train = args.bucket + '/exported_data/train'\n",
-        "  exported_eval  = args.bucket + '/exported_data/eval'\n",
+        "    exported_train = args.bucket + '/exported_data/train'\n",
+        "    exported_eval  = args.bucket + '/exported_data/eval'\n",
         "\n",
+        "    pipeline_options = PipelineOptions(pipeline_args)\n",
+        "    pipeline_options.view_as(SetupOptions).save_main_session = True\n",
+        "    with beam.Pipeline(options=pipeline_options) as pipeline:\n",
+        "        with tft_beam.Context(temp_location):\n",
+        "            raw_data_query = \"SELECT {0},{1} FROM {2} LIMIT 500\".format(\"CAST(station_number as STRING) AS station_number,year,month,day\",\"mean_temp\", args.bq_table)\n",
         "\n",
-        "  pipeline_options = PipelineOptions(pipeline_args)\n",
-        "  pipeline_options.view_as(SetupOptions).save_main_session = True\n",
-        "  with beam.Pipeline(options=pipeline_options) as pipeline:\n",
-        "    with tft_beam.Context(temp_location):\n",
+        "            def parse_bq_record(bq_record):\n",
+        "                \"\"\"Parses a bq_record to a dictionary.\"\"\"\n",
+        "                output = {}\n",
+        "                for key in bq_record:\n",
+        "                    output[key] = [bq_record[key]]\n",
+        "                return output\n",
         "\n",
-        "        raw_data_query = \"SELECT {0},{1} FROM {2} LIMIT 500\".format(\"CAST(station_number as STRING) AS station_number,year,month,day\",\"mean_temp\", args.bq_table)\n",
+        "            def split_dataset(bq_row, num_partitions, ratio):\n",
+        "                \"\"\"Returns a partition number for a given bq_row.\"\"\"\n",
+        "                import json\n",
         "\n",
-        "        def parse_bq_record(bq_record):\n",
-        "            \"\"\"Parses a bq_record to a dictionary.\"\"\"\n",
-        "            output = {}\n",
-        "            for key in bq_record:\n",
-        "                output[key] = [bq_record[key]]\n",
-        "            return output\n",
+        "                assert num_partitions == len(ratio)\n",
+        "                bucket = sum(map(ord, json.dumps(bq_row))) % sum(ratio)\n",
+        "                total = 0\n",
+        "                for i, part in enumerate(ratio):\n",
+        "                    total += part\n",
+        "                    if bucket < total:\n",
+        "                        return i\n",
+        "                return len(ratio) - 1\n",
         "\n",
-        "        def split_dataset(bq_row, num_partitions, ratio):\n",
-        "            \"\"\"Returns a partition number for a given bq_row.\"\"\"\n",
-        "            import json\n",
-        "\n",
-        "            assert num_partitions == len(ratio)\n",
-        "            bucket = sum(map(ord, json.dumps(bq_row))) % sum(ratio)\n",
-        "            total = 0\n",
-        "            for i, part in enumerate(ratio):\n",
-        "                total += part\n",
-        "                if bucket < total:\n",
-        "                    return i\n",
-        "            return len(ratio) - 1\n",
-        "\n",
-        "        # Read raw BigQuery data.\n",
-        "        raw_train_data, raw_eval_data = (\n",
-        "            pipeline\n",
-        "            | \"Read Raw Data\"\n",
-        "            >> beam.io.ReadFromBigQuery(\n",
-        "                query=raw_data_query,\n",
-        "                project=project,\n",
-        "                use_standard_sql=True,\n",
+        "            # Read raw BigQuery data.\n",
+        "            raw_train_data, raw_eval_data = (\n",
+        "                pipeline\n",
+        "                | \"Read Raw Data\"\n",
+        "                >> beam.io.ReadFromBigQuery(\n",
+        "                    query=raw_data_query,\n",
+        "                    project=project,\n",
+        "                    use_standard_sql=True,\n",
+        "                )\n",
+        "                | \"Parse Data\" >> beam.Map(parse_bq_record)\n",
+        "                | \"Split\" >> beam.Partition(split_dataset, 2, ratio=[8, 2])\n",
         "            )\n",
-        "            | \"Parse Data\" >> beam.Map(parse_bq_record)\n",
-        "            | \"Split\" >> beam.Partition(split_dataset, 2, ratio=[8, 2])\n",
-        "        )\n",
         "\n",
-        "        # Write raw train data to GCS .\n",
-        "        _ = raw_train_data | \"Write Raw Train Data\" >> beam.io.WriteToText(\n",
-        "            file_path_prefix=exported_train, file_name_suffix=\".csv\"\n",
-        "        )\n",
+        "            # Write raw train data to GCS .\n",
+        "            _ = raw_train_data | \"Write Raw Train Data\" >> beam.io.WriteToText(\n",
+        "                file_path_prefix=exported_train, file_name_suffix=\".csv\"\n",
+        "            )\n",
         "\n",
-        "        # Write raw eval data to GCS .\n",
-        "        _ = raw_eval_data | \"Write Raw Eval Data\" >> beam.io.WriteToText(\n",
-        "            file_path_prefix=exported_eval, file_name_suffix=\".csv\"\n",
-        "        )\n",
+        "            # Write raw eval data to GCS .\n",
+        "            _ = raw_eval_data | \"Write Raw Eval Data\" >> beam.io.WriteToText(\n",
+        "                file_path_prefix=exported_eval, file_name_suffix=\".csv\"\n",
+        "            )\n",
         "\n",
         "\n",
         "if __name__ == '__main__':\n",
-        "  logging.getLogger().setLevel(logging.INFO)\n",
-        "  run()"
+        "    logging.getLogger().setLevel(logging.INFO)\n",
+        "    run()"
       ]
     },
     {
@@ -975,11 +1075,11 @@
       },
       "outputs": [],
       "source": [
-        "GCS_SPLIT_PY = BUCKET_NAME + \"/split.py\"\n",
+        "GCS_SPLIT_PY = BUCKET_URI + \"/split.py\"\n",
         "! gsutil cp split.py $GCS_SPLIT_PY\n",
-        "GCS_REQUIREMENTS_TXT = BUCKET_NAME + \"/requirements.txt\"\n",
+        "GCS_REQUIREMENTS_TXT = BUCKET_URI + \"/requirements.txt\"\n",
         "! gsutil cp requirements.txt $GCS_REQUIREMENTS_TXT\n",
-        "GCS_SETUP_PY = BUCKET_NAME + \"/setup.py\"\n",
+        "GCS_SETUP_PY = BUCKET_URI + \"/setup.py\"\n",
         "! gsutil cp setup.py $GCS_SETUP_PY"
       ]
     },
@@ -1036,7 +1136,7 @@
       },
       "outputs": [],
       "source": [
-        "PIPELINE_ROOT = \"{}/pipeline_root/dataflow_split\".format(BUCKET_NAME)\n",
+        "PIPELINE_ROOT = \"{}/pipeline_root/dataflow_split\".format(BUCKET_URI)\n",
         "\n",
         "\n",
         "@dsl.pipeline(name=\"dataflow-split\", description=\"Dataflow split dataset\")\n",
@@ -1047,7 +1147,7 @@
         "    staging_dir: str = PIPELINE_ROOT,\n",
         "    args: list = [\n",
         "        \"--bucket\",\n",
-        "        BUCKET_NAME,\n",
+        "        BUCKET_URI,\n",
         "        \"--bq_table\",\n",
         "        BQ_TABLE,\n",
         "        \"--runner\",\n",
@@ -1067,9 +1167,7 @@
         "        args=args,\n",
         "    )\n",
         "\n",
-        "    dataflow_wait_op = WaitGcpResourcesOp(\n",
-        "        gcp_resources=dataflow_python_op.outputs[\"gcp_resources\"]\n",
-        "    )\n",
+        "    _ = WaitGcpResourcesOp(gcp_resources=dataflow_python_op.outputs[\"gcp_resources\"])\n",
         "\n",
         "\n",
         "compiler.Compiler().compile(pipeline_func=pipeline, package_path=\"dataflow_split.json\")\n",
@@ -1083,7 +1181,7 @@
         "\n",
         "pipeline.run()\n",
         "\n",
-        "! gsutil ls {BUCKET_NAME}/exported_data\n",
+        "! gsutil ls {BUCKET_URI}/exported_data\n",
         "\n",
         "! rm -f dataflow_split.json split.py requirements.txt"
       ]
@@ -1124,13 +1222,6 @@
         "Otherwise, you can delete the individual resources you created in this tutorial:\n",
         "\n",
         "- Dataset\n",
-        "- Pipeline\n",
-        "- Model\n",
-        "- Endpoint\n",
-        "- AutoML Training Job\n",
-        "- Batch Job\n",
-        "- Custom Job\n",
-        "- Hyperparameter Tuning Job\n",
         "- Cloud Storage Bucket"
       ]
     },
@@ -1142,61 +1233,11 @@
       },
       "outputs": [],
       "source": [
-        "delete_all = True\n",
+        "# Warning: Setting this to true will delete everything in your bucket\n",
+        "delete_bucket = False\n",
         "\n",
-        "if delete_all:\n",
-        "    # Delete the dataset using the Vertex dataset object\n",
-        "    try:\n",
-        "        if \"dataset\" in globals():\n",
-        "            dataset.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the model using the Vertex model object\n",
-        "    try:\n",
-        "        if \"model\" in globals():\n",
-        "            model.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the endpoint using the Vertex endpoint object\n",
-        "    try:\n",
-        "        if \"endpoint\" in globals():\n",
-        "            endpoint.undeploy_all()\n",
-        "            endpoint.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the AutoML or Pipeline training job\n",
-        "    try:\n",
-        "        if \"dag\" in globals():\n",
-        "            dag.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the custom training job\n",
-        "    try:\n",
-        "        if \"job\" in globals():\n",
-        "            job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the batch prediction job using the Vertex batch prediction object\n",
-        "    try:\n",
-        "        if \"batch_predict_job\" in globals():\n",
-        "            batch_predict_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the hyperparameter tuning job using the Vertex hyperparameter tuning object\n",
-        "    try:\n",
-        "        if \"hpt_job\" in globals():\n",
-        "            hpt_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    if \"BUCKET_NAME\" in globals():\n",
-        "        ! gsutil rm -r $BUCKET_NAME"
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil rm -r $BUCKET_URI"
       ]
     }
   ],

notebooks/community/ml_ops/stage3/get_started_with_dataproc_serverless_pipeline_components.ipynb

@@ -29,7 +29,7 @@
         "id": "title:generic,gcp"
       },
       "source": [
-        "# E2E ML on GCP: MLOps stage 3 : formalization: get started with Dataproc Serverless pipeline components\n",
+        "# E2E ML on GCP: MLOps stage 3 : formalization: get started with Datproc Serverless pipeline components\n",
         "\n",
         "<table align=\"left\">\n",
         "  <td>\n",
@@ -38,9 +38,15 @@
         "      View on GitHub\n",
         "    </a>\n",
         "  </td>\n",
+        "    <td>\n",
+        "        <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage3/get_started_with_dataproc_serverless_pipeline_components.ipynb\">\n",
+        "        <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\\\" alt=\"Colab logo\"> Run in Colab\n",
+        "        </a>\n",
+        "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://console.cloud.google.com/ai/platform/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage3/get_started_with_dataproc_serverless_pipeline_components.ipynb\">\n",
-        "      Open in Google Cloud Notebooks\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/ml_ops/stage3/get_started_with_dataproc_serverless_pipeline_components.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "      Open in Vertex AI Workbench\n",
         "    </a>\n",
         "  </td>\n",
         "</table>\n",
@@ -66,7 +72,7 @@
       "source": [
         "### Objective\n",
         "\n",
-        "In this tutorial, you learn how to use prebuilt `Google Cloud Pipeline Components` for `Dataproc Serverless`. The documentation for the components are found [here](https://google-cloud-pipeline-components.readthedocs.io/en/google-cloud-pipeline-components-1.0.0/google_cloud_pipeline_components.experimental.dataproc.html).\n",
+        "In this tutorial, you learn how to use prebuilt `Google Cloud Pipeline Components` for `Dataproc Serverless` service. The documentation for the components can be found [here](https://google-cloud-pipeline-components.readthedocs.io/en/google-cloud-pipeline-components-1.0.0/google_cloud_pipeline_components.experimental.dataproc.html).\n",
         "\n",
         "This tutorial uses the following Google Cloud ML services:\n",
         "\n",
@@ -75,10 +81,19 @@
         "- `Dataproc Serverless`\n",
         "\n",
         "An example pipeline is provided for each Dataproc Serverless component, which includes:\n",
-        "- `DataprocPySparkBatchOp` for PySpark batch workloads.\n",
-        "- `DataprocSparkBatchOp` for Spark batch workloads.\n",
+        "- `DataprocPySparkBatchOp` for running PySpark batch workloads.\n",
+        "- `DataprocSparkBatchOp` for running Spark batch workloads.\n",
         "- `DataprocSparkSqlBatchOp` for running Spark SQL batch workloads.\n",
-        "- `DataprocSparkRBatchOp` for running SparkR batch workloads."
+        "- `DataprocSparkRBatchOp` for running SparkR batch workloads.\n",
+        "\n",
+        "### Costs\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "- Vertex AI\n",
+        "- Dataproc Serverless\n",
+        "- Cloud Storage\n",
+        "\n",
+        "Learn about [Vertex AI pricing](https://cloud.google.com/vertex-ai/pricing), [Dataproc Serverless pricing](https://cloud.google.com/dataproc-serverless/pricing) and [Cloud Storage pricing](https://cloud.google.com/storage/pricing) and use the [Pricing Calculator](https://cloud.google.com/products/calculator/) to generate a cost estimate based on your projected usage."
       ]
     },
     {
@@ -106,7 +121,7 @@
       "source": [
         "## Installations\n",
         "\n",
-        "Install *one time* the packages for executing the MLOps notebooks."
+        "Install the following packages for executing this MLOps notebook."
       ]
     },
     {
@@ -117,11 +132,22 @@
       },
       "outputs": [],
       "source": [
-        "USER_FLAG = \"--user\"\n",
-        "ONCE_ONLY = True\n",
-        "if ONCE_ONLY:\n",
-        "    ! pip3 install --upgrade google-cloud-pipeline-components $USER_FLAG\n",
-        "    ! pip3 install --upgrade kfp $USER_FLAG"
+        "import os\n",
+        "\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
+        "\n",
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
+        "USER_FLAG = \"\"\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "\n",
+        "# Install the required packages\n",
+        "! pip3 install tensorflow-io $USER_FLAG -q\n",
+        "! pip3 install --upgrade google-cloud-pipeline-components kfp $USER_FLAG -q"
       ]
     },
     {
@@ -153,6 +179,32 @@
         "    app.kernel.do_shutdown(True)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "1df9ff75fa88"
+      },
+      "source": [
+        "## Before you begin\n",
+        "\n",
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com).\n",
+        "\n",
+        "1. If you are running this notebook locally, you will need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+        "\n",
+        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -229,7 +281,10 @@
       },
       "outputs": [],
       "source": [
-        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
+        "\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
       ]
     },
     {
@@ -256,6 +311,67 @@
         "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "c38be665ca50"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already authenticated. Skip this step.\n",
+        "\n",
+        "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\n",
+        "\n",
+        "1. **Click Create service account**.\n",
+        "\n",
+        "2. In the **Service account name** field, enter a name, and click **Create**.\n",
+        "\n",
+        "3. In the **Grant this service account access to project** section, click the Role drop-down list. Type \"Vertex\" into the filter box, and select **Vertex Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "4. Click Create. A JSON file that contains your key downloads to your local environment.\n",
+        "\n",
+        "5. Enter the path to your service account key as the GOOGLE_APPLICATION_CREDENTIALS variable in the cell below and run the cell."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "e0953a00668e"
+      },
+      "outputs": [],
+      "source": [
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
+        "IS_COLAB = False\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
+        "    \"DL_ANACONDA_HOME\"\n",
+        "):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        IS_COLAB = True\n",
+        "        from google.colab import auth as google_auth\n",
+        "\n",
+        "        google_auth.authenticate_user()\n",
+        "\n",
+        "    # If you are running this notebook locally, replace the string below with the\n",
+        "    # path to your service account key and run this cell to authenticate your GCP\n",
+        "    # account.\n",
+        "    elif not os.getenv(\"IS_TESTING\"):\n",
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -367,15 +483,20 @@
       "source": [
         "if (\n",
         "    SERVICE_ACCOUNT == \"\"\n",
-        "    or SERVICE_ACCOUNT == \"[your-service-account]\"\n",
         "    or SERVICE_ACCOUNT is None\n",
+        "    or SERVICE_ACCOUNT == \"[your-service-account]\"\n",
         "):\n",
-        "    shell_output = ! gcloud projects describe $PROJECT_ID | sed -nre 's:.*projectNumber\\: (.*):\\1:p'\n",
-        "    SERVICE_ACCOUNT = (\n",
-        "        shell_output[0].replace(\"'\", \"\") + \"-compute@developer.gserviceaccount.com\"\n",
-        "    )\n",
+        "    # Get your service account from gcloud\n",
+        "    if not IS_COLAB:\n",
+        "        shell_output = !gcloud auth list 2>/dev/null\n",
+        "        SERVICE_ACCOUNT = shell_output[2].replace(\"*\", \"\").strip()\n",
         "\n",
-        "print(\"Service Account:\", SERVICE_ACCOUNT)"
+        "    if IS_COLAB:\n",
+        "        shell_output = ! gcloud projects describe  $PROJECT_ID\n",
+        "        project_number = shell_output[-1].split(\":\")[1].strip().replace(\"'\", \"\")\n",
+        "        SERVICE_ACCOUNT = f\"{project_number}-compute@developer.gserviceaccount.com\"\n",
+        "\n",
+        "    print(\"Service Account:\", SERVICE_ACCOUNT)"
       ]
     },
     {
@@ -489,17 +610,7 @@
       },
       "outputs": [],
       "source": [
-        "import google.cloud.aiplatform as aip"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "import_kfp"
-      },
-      "outputs": [],
-      "source": [
+        "import google.cloud.aiplatform as aiplatform\n",
         "from kfp import dsl\n",
         "from kfp.v2 import compiler"
       ]
@@ -523,7 +634,7 @@
       },
       "outputs": [],
       "source": [
-        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_URI)"
+        "aiplatform.init(project=PROJECT_ID, staging_bucket=BUCKET_URI)"
       ]
     },
     {
@@ -695,7 +806,7 @@
         "\n",
         "compiler.Compiler().compile(pipeline_func=pipeline, package_path=\"pipeline.json\")\n",
         "\n",
-        "pipeline = aip.PipelineJob(\n",
+        "pipeline = aiplatform.PipelineJob(\n",
         "    display_name=\"pipeline\",\n",
         "    template_path=\"pipeline.json\",\n",
         "    pipeline_root=PIPELINE_ROOT,\n",
@@ -776,6 +887,7 @@
         "            + \"/evaluation_metrics\"\n",
         "        )\n",
         "        if tf.io.gfile.exists(EXECUTE_OUTPUT):\n",
+        "            print(EXECUTE_OUTPUT, \"EXECUTE_OUTPUT\")\n",
         "            ! gsutil cat $EXECUTE_OUTPUT\n",
         "            return EXECUTE_OUTPUT\n",
         "        elif tf.io.gfile.exists(GCP_RESOURCES):\n",
@@ -815,6 +927,28 @@
         "pipeline.delete()"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "1b88bebd6e4f"
+      },
+      "source": [
+        "### Delete the batch\n",
+        "\n",
+        "You can delete the created batch in Dataproc serverless using the following `gcloud` command."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "1c21bcd1293e"
+      },
+      "outputs": [],
+      "source": [
+        "! gcloud dataproc batches delete $BATCH_ID --region=$REGION --quiet"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -893,7 +1027,7 @@
         "\n",
         "compiler.Compiler().compile(pipeline_func=pipeline, package_path=\"pipeline.json\")\n",
         "\n",
-        "pipeline = aip.PipelineJob(\n",
+        "pipeline = aiplatform.PipelineJob(\n",
         "    display_name=\"pipeline\",\n",
         "    template_path=\"pipeline.json\",\n",
         "    pipeline_root=PIPELINE_ROOT,\n",
@@ -982,6 +1116,28 @@
         "pipeline.delete()"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "8a204485faa5"
+      },
+      "source": [
+        "### Delete the batch\n",
+        "\n",
+        "You can delete the created batch in Dataproc serverless using the following `gcloud` command."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "3347ac71dcca"
+      },
+      "outputs": [],
+      "source": [
+        "! gcloud dataproc batches delete $BATCH_ID --region=$REGION --quiet"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -989,7 +1145,7 @@
       },
       "source": [
         "## Running a Spark SQL workload\n",
-        "This section shows you how to create a Spark SQL batch workload from Vertex Pipelines. The pipeline uses `DataprocSparkSqlBatchOp` to run Spark SQL queries on a public sample dataset. The sample dataset is provided by the US Social Security Adminstration and contains approximately 7 MB of data about popular baby names."
+        "This section shows you how to create a Spark SQL batch workload from Vertex Pipelines. The pipeline uses `DataprocSparkSqlBatchOp` component to run Spark SQL queries on a public sample dataset. The sample dataset is provided by the US Social Security Adminstration and contains approximately 7 MB of data about popular baby names."
       ]
     },
     {
@@ -1093,7 +1249,7 @@
         "id": "bb07db26ae1e"
       },
       "source": [
-        "Copy the query file to Cloud Storage:"
+        "Copy the query file to Cloud Storage."
       ]
     },
     {
@@ -1177,7 +1333,7 @@
         "\n",
         "compiler.Compiler().compile(pipeline_func=pipeline, package_path=\"pipeline.json\")\n",
         "\n",
-        "pipeline = aip.PipelineJob(\n",
+        "pipeline = aiplatform.PipelineJob(\n",
         "    display_name=\"pipeline\",\n",
         "    template_path=\"pipeline.json\",\n",
         "    pipeline_root=PIPELINE_ROOT,\n",
@@ -1189,28 +1345,6 @@
         "! gsutil cat $OUTPUT_LOCATION/*.csv"
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "ac01bfa0f7cc"
-      },
-      "source": [
-        "### Delete the pipeline job\n",
-        "\n",
-        "After a pipeline job is completed, you can delete the pipeline job with the method `delete()`.  Prior to completion, a pipeline job can be canceled with the method `cancel()`."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "e24a24370a8a"
-      },
-      "outputs": [],
-      "source": [
-        "pipeline.delete()"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -1238,6 +1372,50 @@
         "print(\"\\n\\n\")"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "ac01bfa0f7cc"
+      },
+      "source": [
+        "### Delete the pipeline job\n",
+        "\n",
+        "After a pipeline job is completed, you can delete the pipeline job with the method `delete()`.  Prior to completion, a pipeline job can be canceled with the method `cancel()`."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "e24a24370a8a"
+      },
+      "outputs": [],
+      "source": [
+        "pipeline.delete()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "261ead937f4c"
+      },
+      "source": [
+        "### Delete the batch\n",
+        "\n",
+        "You can delete the created batch in Dataproc serverless using the following `gcloud` command."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "01f828745b4e"
+      },
+      "outputs": [],
+      "source": [
+        "! gcloud dataproc batches delete $BATCH_ID --region=$REGION --quiet"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -1245,7 +1423,7 @@
       },
       "source": [
         "## Running a SparkR workload\n",
-        "This section shows you how to create a SparkR batch workload from Vertex AI Pipelines. The pipeline uses `DataprocSparkRBatchOp` to run a simple R script  that counts the frequency of words used in Shakespeare.\n",
+        "This section shows you how to create a SparkR batch workload from Vertex AI Pipelines. The pipeline uses `DataprocSparkRBatchOp` component to run a simple R script  that counts the frequency of words used in Shakespeare.\n",
         "\n",
         "### Write the PySpark word count program.\n",
         "\n",
@@ -1288,7 +1466,7 @@
         "\n",
         "Next, you copy `wordcount.R` to your Cloud Storage bucket.\n",
         "\n",
-        "Additional, you set the Cloud Storage locations for the input and output of the script."
+        "Additionally, you set the Cloud Storage locations for the input and output of the script."
       ]
     },
     {
@@ -1367,7 +1545,7 @@
         "\n",
         "compiler.Compiler().compile(pipeline_func=pipeline, package_path=\"pipeline.json\")\n",
         "\n",
-        "pipeline = aip.PipelineJob(\n",
+        "pipeline = aiplatform.PipelineJob(\n",
         "    display_name=\"pipeline\",\n",
         "    template_path=\"pipeline.json\",\n",
         "    pipeline_root=PIPELINE_ROOT,\n",
@@ -1430,6 +1608,28 @@
         "pipeline.delete()"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "40234ba85e4d"
+      },
+      "source": [
+        "### Delete the batch\n",
+        "\n",
+        "You can delete the created batch in Dataproc serverless using the following `gcloud` command."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "f9f5ad4e43a8"
+      },
+      "outputs": [],
+      "source": [
+        "! gcloud dataproc batches delete $BATCH_ID --region=$REGION --quiet"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -1441,7 +1641,10 @@
         "To clean up all Google Cloud resources used in this project, you can [delete the Google Cloud\n",
         "project](https://cloud.google.com/resource-manager/docs/creating-managing-projects#shutting_down_projects) you used for the tutorial.\n",
         "\n",
-        "Otherwise, you can delete the individual resources you created in this tutorial."
+        "Otherwise, you can delete the individual resources you created in this tutorial.\n",
+        "\n",
+        "### Delete Cloud Storage bucket\n",
+        "Set `delete_bucket` to `True` to delete the Cloud Storage bucket."
       ]
     },
     {
@@ -1452,12 +1655,11 @@
       },
       "outputs": [],
       "source": [
-        "delete_all = True\n",
+        "delete_bucket = False\n",
         "\n",
-        "if delete_all:\n",
-        "\n",
-        "    if \"BUCKET_URI\" in globals():\n",
-        "        ! gsutil rm -r $BUCKET_URI"
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "    # Delete the Cloud storage bucket\n",
+        "    ! gsutil rm -r $BUCKET_URI"
       ]
     }
   ],

notebooks/community/ml_ops/stage3/get_started_with_hpt_pipeline_components.ipynb

@@ -32,6 +32,11 @@
         "# E2E ML on GCP: MLOps stage 3 : formalization: get started with Hyperparameter Tuning pipeline components\n",
         "\n",
         "<table align=\"left\">\n",
+        "    <td>\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage3/get_started_with_hpt_pipeline_components.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "    </a>\n",
+        "  </td>\n",
         "  <td>\n",
         "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage3/get_started_with_hpt_pipeline_components.ipynb\">\n",
         "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
@@ -39,7 +44,8 @@
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://console.cloud.google.com/ai/platform/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage3/get_started_with_hpt_pipeline_components.ipynb\">\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/ml_ops/stage3/get_started_with_hpt_pipeline_components.ipynb\">\n",
+        "        <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
         "      Open in Google Cloud Notebooks\n",
         "    </a>\n",
         "  </td>\n",
@@ -94,7 +100,20 @@
         "    - If the metrics exceed a specified threshold.\n",
         "      - Get the location of the model artifacts for the best tuned model.\n",
         "      - Upload the model artifacts to a `Vertex AI Model` resource.\n",
-        "- Execute a Vertex AI pipeline."
+        "- Execute a Vertex AI pipeline.\n",
+        "\n",
+        "### Costs \n",
+        "\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "* Vertex AI\n",
+        "* Cloud Storage\n",
+        "\n",
+        "Learn about [Vertex AI\n",
+        "pricing](https://cloud.google.com/vertex-ai/pricing) and [Cloud Storage\n",
+        "pricing](https://cloud.google.com/storage/pricing), and use the [Pricing\n",
+        "Calculator](https://cloud.google.com/products/calculator/)\n",
+        "to generate a cost estimate based on your projected usage."
       ]
     },
     {
@@ -105,35 +124,37 @@
       "source": [
         "## Installations\n",
         "\n",
-        "Install *one time* the packages for executing the MLOps notebooks."
+        "Install the required packages for executing the notebook."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "install_mlops"
+        "id": "LR9HQnyiMoT5"
       },
       "outputs": [],
       "source": [
-        "ONCE_ONLY = False\n",
-        "if ONCE_ONLY:\n",
-        "    ! pip3 install -U tensorflow==2.5 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-data-validation==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-transform==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-io==0.18 $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-aiplatform[tensorboard] $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-pipeline-components $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-bigquery $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-logging $USER_FLAG\n",
-        "    ! pip3 install --upgrade apache-beam[gcp] $USER_FLAG\n",
-        "    ! pip3 install --upgrade pyarrow $USER_FLAG\n",
-        "    ! pip3 install --upgrade cloudml-hypertune $USER_FLAG\n",
-        "    ! pip3 install --upgrade kfp $USER_FLAG\n",
-        "    ! pip3 install --upgrade torchvision $USER_FLAG\n",
-        "    ! pip3 install --upgrade rpy2 $USER_FLAG\n",
-        "    ! pip3 install --upgrade python-tabulate $USER_FLAG\n",
-        "    ! pip3 install -U opencv-python-headless==4.5.2.52 $USER_FLAG"
+        "import os\n",
+        "\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
+        "\n",
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
+        "USER_FLAG = \"\"\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "\n",
+        "! pip3 install -U tensorflow==2.5 $USER_FLAG -q\n",
+        "! pip3 install -U tensorflow-data-validation==1.2 $USER_FLAG -q\n",
+        "! pip3 install -U tensorflow-transform==1.2 $USER_FLAG -q\n",
+        "! pip3 install -U tensorflow-io==0.18 $USER_FLAG -q\n",
+        "! pip3 install --upgrade google-cloud-aiplatform[tensorboard] $USER_FLAG -q\n",
+        "! pip3 install --upgrade google-cloud-pipeline-components $USER_FLAG -q\n",
+        "! pip3 install --upgrade kfp $USER_FLAG -q"
       ]
     },
     {
@@ -151,7 +172,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "restart"
+        "id": "VeBfL2pmMoT7"
       },
       "outputs": [],
       "source": [
@@ -165,6 +186,32 @@
         "    app.kernel.do_shutdown(True)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "1df9ff75fa88"
+      },
+      "source": [
+        "## Before you begin\n",
+        "\n",
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com).\n",
+        "\n",
+        "1. If you are running this notebook locally, you will need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+        "\n",
+        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -237,11 +284,14 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "region"
+        "id": "7iewOt9NMoT8"
       },
       "outputs": [],
       "source": [
-        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+        "REGION = \"[your-region]\"  # @param {type:\"string\"}\n",
+        "\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\"  # @param {type: \"string\"}"
       ]
     },
     {
@@ -259,7 +309,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "timestamp"
+        "id": "Y-vhpfibMoT9"
       },
       "outputs": [],
       "source": [
@@ -268,6 +318,67 @@
         "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "gcp_authenticate"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already authenticated. Skip this step.\n",
+        "\n",
+        "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\n",
+        "\n",
+        "**Click Create service account**.\n",
+        "\n",
+        "In the **Service account name** field, enter a name, and click **Create**.\n",
+        "\n",
+        "In the **Grant this service account access to project** section, click the Role drop-down list. Type \"Vertex\" into the filter box, and select **Vertex Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "Click Create. A JSON file that contains your key downloads to your local environment.\n",
+        "\n",
+        "Enter the path to your service account key as the GOOGLE_APPLICATION_CREDENTIALS variable in the cell below and run the cell."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "-V_6SvMUNUa1"
+      },
+      "outputs": [],
+      "source": [
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
+        "IS_COLAB = False\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
+        "    \"DL_ANACONDA_HOME\"\n",
+        "):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        IS_COLAB = True\n",
+        "        from google.colab import auth as google_auth\n",
+        "\n",
+        "        google_auth.authenticate_user()\n",
+        "\n",
+        "    # If you are running this notebook locally, replace the string below with the\n",
+        "    # path to your service account key and run this cell to authenticate your GCP\n",
+        "    # account.\n",
+        "    elif not os.getenv(\"IS_TESTING\"):\n",
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -291,7 +402,7 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
+        "BUCKET_URI = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
       ]
     },
     {
@@ -302,8 +413,8 @@
       },
       "outputs": [],
       "source": [
-        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"gs://[your-bucket-name]\":\n",
-        "    BUCKET_NAME = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
+        "if BUCKET_URI == \"\" or BUCKET_URI is None or BUCKET_URI == \"gs://[your-bucket-name]\":\n",
+        "    BUCKET_URI = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
       ]
     },
     {
@@ -319,11 +430,11 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "create_bucket"
+        "id": "2smRgc53MoT-"
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION $BUCKET_NAME"
+        "! gsutil mb -l $REGION $BUCKET_URI"
       ]
     },
     {
@@ -339,11 +450,11 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "validate_bucket"
+        "id": "ME1Tr9j_MoT-"
       },
       "outputs": [],
       "source": [
-        "! gsutil ls -al $BUCKET_NAME"
+        "! gsutil ls -al $BUCKET_URI"
       ]
     },
     {
@@ -361,7 +472,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "set_service_account"
+        "id": "EIivrR-3MoT-"
       },
       "outputs": [],
       "source": [
@@ -381,9 +492,16 @@
         "    or SERVICE_ACCOUNT is None\n",
         "    or SERVICE_ACCOUNT == \"[your-service-account]\"\n",
         "):\n",
-        "    # Get your GCP project id from gcloud\n",
-        "    shell_output = !gcloud auth list 2>/dev/null\n",
-        "    SERVICE_ACCOUNT = shell_output[2].replace(\"*\", \"\").strip()\n",
+        "    # Get your service account from gcloud\n",
+        "    if not IS_COLAB:\n",
+        "        shell_output = !gcloud auth list 2>/dev/null\n",
+        "        SERVICE_ACCOUNT = shell_output[2].replace(\"*\", \"\").strip()\n",
+        "\n",
+        "    if IS_COLAB:\n",
+        "        shell_output = ! gcloud projects describe  $PROJECT_ID\n",
+        "        project_number = shell_output[-1].split(\":\")[1].strip().replace(\"'\", \"\")\n",
+        "        SERVICE_ACCOUNT = f\"{project_number}-compute@developer.gserviceaccount.com\"\n",
+        "\n",
         "    print(\"Service Account:\", SERVICE_ACCOUNT)"
       ]
     },
@@ -402,13 +520,13 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "set_service_account:pipelines"
+        "id": "mtwsjYnIMoT_"
       },
       "outputs": [],
       "source": [
-        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectCreator $BUCKET_NAME\n",
+        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectCreator $BUCKET_URI\n",
         "\n",
-        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectViewer $BUCKET_NAME"
+        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectViewer $BUCKET_URI"
       ]
     },
     {
@@ -464,7 +582,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "import_tf"
+        "id": "DtTIHh_KMoUA"
       },
       "outputs": [],
       "source": [
@@ -486,11 +604,11 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "init_aip:mbsdk"
+        "id": "sUFJPDW0MoUA"
       },
       "outputs": [],
       "source": [
-        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_NAME)"
+        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_URI)"
       ]
     },
     {
@@ -519,17 +637,19 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "accelerators:training,prediction,ngpu,mbsdk"
+        "id": "A6dzi4cXMoUA"
       },
       "outputs": [],
       "source": [
+        "import os\n",
+        "\n",
         "if os.getenv(\"IS_TESTING_TRAIN_GPU\"):\n",
         "    TRAIN_GPU, TRAIN_NGPU = (\n",
         "        aip.gapic.AcceleratorType.NVIDIA_TESLA_K80,\n",
         "        int(os.getenv(\"IS_TESTING_TRAIN_GPU\")),\n",
         "    )\n",
         "else:\n",
-        "    TRAIN_GPU, TRAIN_NGPU = (aip.gapic.AcceleratorType.NVIDIA_TESLA_K80, 1)\n",
+        "    TRAIN_GPU, TRAIN_NGPU = (None, None)\n",
         "\n",
         "if os.getenv(\"IS_TESTING_DEPLOY_GPU\"):\n",
         "    DEPLOY_GPU, DEPLOY_NGPU = (\n",
@@ -560,7 +680,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "container:prediction"
+        "id": "gxai072KMoUB"
       },
       "outputs": [],
       "source": [
@@ -616,7 +736,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "machine:training,prediction"
+        "id": "LEYjL1ojMoUB"
       },
       "outputs": [],
       "source": [
@@ -672,7 +792,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "examine_training_package"
+        "id": "UIoZdxPqMoUC"
       },
       "outputs": [],
       "source": [
@@ -735,7 +855,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "taskpy_contents:dataset,horses_or_humans"
+        "id": "uk4MAGErMoUC"
       },
       "outputs": [],
       "source": [
@@ -872,14 +992,14 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "tarball_training_script"
+        "id": "bHcLQLGkMoUD"
       },
       "outputs": [],
       "source": [
         "! rm -f custom.tar custom.tar.gz\n",
         "! tar cvf custom.tar custom\n",
         "! gzip custom.tar\n",
-        "! gsutil cp custom.tar.gz $BUCKET_NAME/trainer_horses_or_humans.tar.gz"
+        "! gsutil cp custom.tar.gz $BUCKET_URI/trainer_horses_or_humans.tar.gz"
       ]
     },
     {
@@ -912,7 +1032,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "write_docker_file:training,tf-dlvm"
+        "id": "MaMK4AoBMoUE"
       },
       "outputs": [],
       "source": [
@@ -945,7 +1065,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "name_container:training"
+        "id": "9qVJGXT2MoUE"
       },
       "outputs": [],
       "source": [
@@ -965,7 +1085,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "build_container:training"
+        "id": "7-dkQP8hMoUE"
       },
       "outputs": [],
       "source": [
@@ -987,7 +1107,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "register_container:training"
+        "id": "7-kh6QBLMoUF"
       },
       "outputs": [],
       "source": [
@@ -1017,11 +1137,11 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "create_hpt_pipeline:icn"
+        "id": "Epzlh8M-MoUF"
       },
       "outputs": [],
       "source": [
-        "PIPELINE_ROOT = \"{}/pipeline_root/custom_icn_tuning\".format(BUCKET_NAME)\n",
+        "PIPELINE_ROOT = \"{}/pipeline_root/custom_icn_tuning\".format(BUCKET_URI)\n",
         "\n",
         "\n",
         "@component(packages_to_install=[\"google-cloud-aiplatform\"])\n",
@@ -1089,9 +1209,7 @@
         "        threshold_op.output == \"true\",\n",
         "        name=\"deploy_decision\",\n",
         "    ):\n",
-        "        best_hyperparameters_op = hyperparameter_tuning_job.GetHyperparametersOp(\n",
-        "            trial=best_trial_op.output\n",
-        "        )\n",
+        "        _ = hyperparameter_tuning_job.GetHyperparametersOp(trial=best_trial_op.output)\n",
         "\n",
         "        model_dir_op = model_dir(base_output_directory, best_trial_op.output)\n",
         "\n",
@@ -1105,7 +1223,7 @@
         "            },\n",
         "        ).after(model_dir_op)\n",
         "\n",
-        "        model_upload_op = ModelUploadOp(\n",
+        "        _ = ModelUploadOp(\n",
         "            project=project,\n",
         "            display_name=display_name,\n",
         "            unmanaged_container_model=import_unmanaged_model_op.outputs[\"artifact\"],\n",
@@ -1139,13 +1257,26 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "create_hpt_specs"
+        "id": "aEm7RuwMMoUG"
       },
       "outputs": [],
       "source": [
         "from google_cloud_pipeline_components.experimental import \\\n",
         "    hyperparameter_tuning_job\n",
         "\n",
+        "gpu = \"ACCELERATOR_TYPE_UNSPECIFIED\"\n",
+        "accelerator_count = 0\n",
+        "\n",
+        "if TRAIN_GPU:\n",
+        "    gpu = TRAIN_GPU.name\n",
+        "    accelerator_count = 1\n",
+        "\n",
+        "else:\n",
+        "    gpu = \"ACCELERATOR_TYPE_UNSPECIFIED\"\n",
+        "    accelerator_count = (\n",
+        "        0  # same problem with accelerator_count, if we keep is as \"None\" its not\n",
+        "    )\n",
+        "\n",
         "CMDARGS = [\n",
         "    \"--epochs=10\",\n",
         "]\n",
@@ -1155,8 +1286,8 @@
         "    {\n",
         "        \"machine_spec\": {\n",
         "            \"machine_type\": TRAIN_COMPUTE,\n",
-        "            \"accelerator_type\": TRAIN_GPU.name,\n",
-        "            \"accelerator_count\": TRAIN_NGPU,\n",
+        "            \"accelerator_type\": gpu,\n",
+        "            \"accelerator_count\": accelerator_count,\n",
         "        },\n",
         "        \"replica_count\": 1,\n",
         "        \"container_spec\": {\"image_uri\": TRAIN_IMAGE, \"args\": CMDARGS},\n",
@@ -1205,7 +1336,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "run_pipeline:hpt"
+        "id": "42YNp9Y9MoUG"
       },
       "outputs": [],
       "source": [
@@ -1246,7 +1377,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "view_pipleline_results:hpt,horses_or_humans"
+        "id": "4X3jrdX1MoUH"
       },
       "outputs": [],
       "source": [
@@ -1358,7 +1489,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "delete_pipeline"
+        "id": "hS53o3FcMoUH"
       },
       "outputs": [],
       "source": [
@@ -1378,14 +1509,6 @@
         "\n",
         "Otherwise, you can delete the individual resources you created in this tutorial:\n",
         "\n",
-        "- Dataset\n",
-        "- Pipeline\n",
-        "- Model\n",
-        "- Endpoint\n",
-        "- AutoML Training Job\n",
-        "- Batch Job\n",
-        "- Custom Job\n",
-        "- Hyperparameter Tuning Job\n",
         "- Cloud Storage Bucket"
       ]
     },
@@ -1393,70 +1516,20 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "cleanup:mbsdk"
+        "id": "laAQFM4aoBm3"
       },
       "outputs": [],
       "source": [
-        "delete_all = True\n",
+        "delete_bucket = False\n",
         "\n",
-        "if delete_all:\n",
-        "    # Delete the dataset using the Vertex dataset object\n",
-        "    try:\n",
-        "        if \"dataset\" in globals():\n",
-        "            dataset.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the model using the Vertex model object\n",
-        "    try:\n",
-        "        if \"model\" in globals():\n",
-        "            model.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the endpoint using the Vertex endpoint object\n",
-        "    try:\n",
-        "        if \"endpoint\" in globals():\n",
-        "            endpoint.undeploy_all()\n",
-        "            endpoint.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the AutoML or Pipeline training job\n",
-        "    try:\n",
-        "        if \"dag\" in globals():\n",
-        "            dag.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the custom training job\n",
-        "    try:\n",
-        "        if \"job\" in globals():\n",
-        "            job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the batch prediction job using the Vertex batch prediction object\n",
-        "    try:\n",
-        "        if \"batch_predict_job\" in globals():\n",
-        "            batch_predict_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the hyperparameter tuning job using the Vertex hyperparameter tuning object\n",
-        "    try:\n",
-        "        if \"hpt_job\" in globals():\n",
-        "            hpt_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    if \"BUCKET_NAME\" in globals():\n",
-        "        ! gsutil rm -r $BUCKET_NAME"
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil rm -r $BUCKET_URI"
       ]
     }
   ],
   "metadata": {
     "colab": {
+      "collapsed_sections": [],
       "name": "get_started_with_hpt_pipeline_components.ipynb",
       "toc_visible": true
     },

notebooks/community/ml_ops/stage3/get_started_with_kubeflow_pipelines.ipynb

@@ -38,9 +38,16 @@
         "      View on GitHub\n",
         "    </a>\n",
         "  </td>\n",
+        "    <td>\n",
+        "        <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage3/get_started_with_kubeflow_pipelines.ipynb\">\n",
+        "        <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\\\" alt=\"Colab logo\"> Run in Colab\n",
+        "        </a>\n",
+        "  </td>\n",
+        "    \n",
         "  <td>\n",
-        "    <a href=\"https://console.cloud.google.com/ai/platform/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage3/get_started_with_kubeflow_pipelines.ipynb\">\n",
-        "      Open in Google Cloud Notebooks\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/ml_ops/stage3/get_started_with_kubeflow_pipelines.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "      Open in Vertex AI Workbench\n",
         "    </a>\n",
         "  </td>\n",
         "</table>\n",
@@ -67,7 +74,7 @@
       "source": [
         "### Objective\n",
         "\n",
-        "In this tutorial, you learn how to use `Kubeflow Pipelines`.\n",
+        "In this tutorial, you learn how to use `Kubeflow Pipelines`(KFP).\n",
         "\n",
         "This tutorial uses the following Google Cloud ML services:\n",
         "\n",
@@ -80,7 +87,15 @@
         "- Executing a KFP pipeline using Vertex AI Pipelines.\n",
         "- Loading component and pipeline definitions from a source code repository.\n",
         "- Building sequential, parallel, multiple output components.\n",
-        "- Building control flow into pipelines."
+        "- Building control flow into pipelines.\n",
+        "\n",
+        "### Costs\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "- Vertex AI\n",
+        "- Cloud Storage\n",
+        "\n",
+        "Learn about [Vertex AI pricing](https://cloud.google.com/vertex-ai/pricing) and [Cloud Storage pricing](https://cloud.google.com/storage/pricing) and use the [Pricing Calculator](https://cloud.google.com/products/calculator/) to generate a cost estimate based on your projected usage."
       ]
     },
     {
@@ -91,7 +106,7 @@
       "source": [
         "## Installations\n",
         "\n",
-        "Install *one time* the packages for executing the MLOps notebooks."
+        "Install the required packages for executing this MLOps notebook."
       ]
     },
     {
@@ -102,24 +117,21 @@
       },
       "outputs": [],
       "source": [
-        "ONCE_ONLY = False\n",
-        "if ONCE_ONLY:\n",
-        "    ! pip3 install -U tensorflow==2.5 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-data-validation==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-transform==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-io==0.18 $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-aiplatform[tensorboard] $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-pipeline-components $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-bigquery $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-logging $USER_FLAG\n",
-        "    ! pip3 install --upgrade apache-beam[gcp] $USER_FLAG\n",
-        "    ! pip3 install --upgrade pyarrow $USER_FLAG\n",
-        "    ! pip3 install --upgrade cloudml-hypertune $USER_FLAG\n",
-        "    ! pip3 install --upgrade kfp $USER_FLAG\n",
-        "    ! pip3 install --upgrade torchvision $USER_FLAG\n",
-        "    ! pip3 install --upgrade rpy2 $USER_FLAG\n",
-        "    ! pip3 install --upgrade python-tabulate $USER_FLAG\n",
-        "    ! pip3 install -U opencv-python-headless==4.5.2.52 $USER_FLAG"
+        "import os\n",
+        "\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\"/opt/deeplearning/metadata/env_version\")\n",
+        "\n",
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
+        "USER_FLAG = \"\"\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "    \n",
+        "! pip3 install tensorflow-io==0.18 $USER_FLAG -q\n",
+        "! pip3 install --upgrade google-cloud-aiplatform \\\n",
+        "                        pyarrow \\\n",
+        "                        kfp $USER_FLAG -q"
       ]
     },
     {
@@ -151,6 +163,32 @@
         "    app.kernel.do_shutdown(True)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "e56d698e5d52"
+      },
+      "source": [
+        "## Before you begin\n",
+        "\n",
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com).\n",
+        "\n",
+        "1. If you are running this notebook locally, you will need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+        "\n",
+        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -227,7 +265,10 @@
       },
       "outputs": [],
       "source": [
-        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
+        "\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
       ]
     },
     {
@@ -254,6 +295,67 @@
         "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "b5627478895e"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already authenticated. Skip this step.\n",
+        "\n",
+        "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\n",
+        "\n",
+        "1. **Click Create service account**.\n",
+        "\n",
+        "2. In the **Service account name** field, enter a name, and click **Create**.\n",
+        "\n",
+        "3. In the **Grant this service account access to project** section, click the Role drop-down list. Type \"Vertex\" into the filter box, and select **Vertex Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "4. Click Create. A JSON file that contains your key downloads to your local environment.\n",
+        "\n",
+        "5. Enter the path to your service account key as the GOOGLE_APPLICATION_CREDENTIALS variable in the cell below and run the cell."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "49ee8894d674"
+      },
+      "outputs": [],
+      "source": [
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
+        "IS_COLAB = False\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
+        "    \"DL_ANACONDA_HOME\"\n",
+        "):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        IS_COLAB = True\n",
+        "        from google.colab import auth as google_auth\n",
+        "\n",
+        "        google_auth.authenticate_user()\n",
+        "\n",
+        "    # If you are running this notebook locally, replace the string below with the\n",
+        "    # path to your service account key and run this cell to authenticate your GCP\n",
+        "    # account.\n",
+        "    elif not os.getenv(\"IS_TESTING\"):\n",
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -277,7 +379,8 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
+        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
+        "BUCKET_URI = \"gs://{}\".format(BUCKET_NAME)"
       ]
     },
     {
@@ -288,8 +391,8 @@
       },
       "outputs": [],
       "source": [
-        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"gs://[your-bucket-name]\":\n",
-        "    BUCKET_NAME = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
+        "if BUCKET_URI == \"\" or BUCKET_URI is None or BUCKET_URI == \"gs://[your-bucket-name]\":\n",
+        "    BUCKET_URI = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
       ]
     },
     {
@@ -309,7 +412,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION $BUCKET_NAME"
+        "! gsutil mb -l $REGION $BUCKET_URI"
       ]
     },
     {
@@ -329,7 +432,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil ls -al $BUCKET_NAME"
+        "! gsutil ls -al $BUCKET_URI"
       ]
     },
     {
@@ -340,7 +443,7 @@
       "source": [
         "#### Service Account\n",
         "\n",
-        "**If you don't know your service account**, try to get your service account using `gcloud` command by executing the second cell below."
+        "You use a service account to create Vertex AI Pipeline jobs. If you do not want to use your project's Compute Engine service account, set `SERVICE_ACCOUNT` to another service account ID."
       ]
     },
     {
@@ -367,9 +470,16 @@
         "    or SERVICE_ACCOUNT is None\n",
         "    or SERVICE_ACCOUNT == \"[your-service-account]\"\n",
         "):\n",
-        "    # Get your GCP project id from gcloud\n",
-        "    shell_output = !gcloud auth list 2>/dev/null\n",
-        "    SERVICE_ACCOUNT = shell_output[2].replace(\"*\", \"\").strip()\n",
+        "    # Get your service account from gcloud\n",
+        "    if not IS_COLAB:\n",
+        "        shell_output = !gcloud auth list 2>/dev/null\n",
+        "        SERVICE_ACCOUNT = shell_output[2].replace(\"*\", \"\").strip()\n",
+        "\n",
+        "    if IS_COLAB:\n",
+        "        shell_output = ! gcloud projects describe  $PROJECT_ID\n",
+        "        project_number = shell_output[-1].split(\":\")[1].strip().replace(\"'\", \"\")\n",
+        "        SERVICE_ACCOUNT = f\"{project_number}-compute@developer.gserviceaccount.com\"\n",
+        "\n",
         "    print(\"Service Account:\", SERVICE_ACCOUNT)"
       ]
     },
@@ -381,7 +491,7 @@
       "source": [
         "#### Set service account access for Vertex AI Pipelines\n",
         "\n",
-        "Run the following commands to grant your service account access to read and write pipeline artifacts in the bucket that you created in the previous step -- you only need to run these once per service account."
+        "Run the following commands to grant your service account access to read and write pipeline artifacts in the bucket that you created in the previous step. You only need to run this step once per service account."
       ]
     },
     {
@@ -392,9 +502,9 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectCreator $BUCKET_NAME\n",
+        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectCreator $BUCKET_URI\n",
         "\n",
-        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectViewer $BUCKET_NAME"
+        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectViewer $BUCKET_URI"
       ]
     },
     {
@@ -403,10 +513,7 @@
         "id": "setup_vars"
       },
       "source": [
-        "### Set up variables\n",
-        "\n",
-        "Next, set up some variables used throughout the tutorial.\n",
-        "### Import libraries and define constants"
+        "### Import libraries"
       ]
     },
     {
@@ -416,42 +523,11 @@
         "id": "import_aip:mbsdk"
       },
       "outputs": [],
-      "source": [
-        "import google.cloud.aiplatform as aip"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "import_tf"
-      },
-      "source": [
-        "#### Import TensorFlow\n",
-        "\n",
-        "Import the TensorFlow package into your Python environment."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "import_tf"
-      },
-      "outputs": [],
-      "source": [
-        "import tensorflow as tf"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "import_kfp:namedtuple"
-      },
-      "outputs": [],
       "source": [
         "from typing import NamedTuple\n",
         "\n",
+        "import google.cloud.aiplatform as aiplatform\n",
+        "import tensorflow as tf\n",
         "from kfp import dsl\n",
         "from kfp.v2 import compiler\n",
         "from kfp.v2.dsl import component"
@@ -476,7 +552,7 @@
       },
       "outputs": [],
       "source": [
-        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_NAME)"
+        "aiplatform.init(project=PROJECT_ID, staging_bucket=BUCKET_URI)"
       ]
     },
     {
@@ -491,14 +567,14 @@
         "\n",
         "    1. Design the pipeline workflow.\n",
         "    2. Compile the pipeline.\n",
-        "    3. Schedule execution (or run now) the pipeline.\n",
+        "    3. Schedule pipeline execution (or run now).\n",
         "    4. Get the pipeline results.\n",
         "\n",
-        "Pipelines are designed using language specific domain specific language (DSL). Vertex AI Pipelines support both KFP DSL and TFX DSL for designing pipelines.\n",
+        "Pipelines are designed using domain specific language (DSL). Vertex AI Pipelines support both KFP DSL and TFX DSL for designing pipelines.\n",
         "\n",
         "In addition to designing components, you can use a wide variety of pre-built Google Cloud Pipeline Components for Vertex AI services.\n",
         "\n",
-        "Learn more about [Building a pipeline](https://cloud.google.com/vertex-ai/docs/pipelines/build-pipeline)"
+        "Learn more about [Building a pipeline](https://cloud.google.com/vertex-ai/docs/pipelines/build-pipeline)."
       ]
     },
     {
@@ -507,9 +583,9 @@
         "id": "pipelines_intro:helloworld"
       },
       "source": [
-        "## Basic pipeline introduction\n",
+        "## Basic pipeline\n",
         "\n",
-        "This demonstrates the basics of constructing and executing a pipeline. You do the following:\n",
+        "This step demonstrates the basics of constructing and executing a pipeline. You do the following:\n",
         "\n",
         "1. Design a simple Python function based component to output the input string.\n",
         "2. Construct a pipeline that uses the component.\n",
@@ -527,8 +603,8 @@
         "\n",
         "To create a KFP component from a Python function, you add the KFP DSL decorator `@component` to the function. In this example, the decorator takes the following parameters:\n",
         "\n",
-        "- `output_component_file`: (optional) write the component description to a YAML file such that the component is portable.\n",
-        "- `base_image`: (optional): The interpreter for executing the Python function. By default it is Python 3.7"
+        "- `output_component_file`(optional): write the component description to a YAML file such that the component is portable.\n",
+        "- `base_image`(optional): The interpreter for executing the Python function. By default it is Python 3.7"
       ]
     },
     {
@@ -571,7 +647,7 @@
       },
       "outputs": [],
       "source": [
-        "PIPELINE_ROOT = \"{}/pipeline_root/hello_world\".format(BUCKET_NAME)\n",
+        "PIPELINE_ROOT = \"{}/pipeline_root/hello_world\".format(BUCKET_URI)\n",
         "\n",
         "\n",
         "@dsl.pipeline(\n",
@@ -580,7 +656,8 @@
         "    pipeline_root=PIPELINE_ROOT,\n",
         ")\n",
         "def pipeline(text: str = \"hi there\"):\n",
-        "    hello_world_task = hello_world(text)"
+        "    hello_world_task = hello_world(text)\n",
+        "    return hello_world_task"
       ]
     },
     {
@@ -593,7 +670,7 @@
         "\n",
         "Once the design of the pipeline is completed, the next step is to compile it. The pipeline definition is compiled into a JSON formatted file, which is transportable and can be interpreted by both KFP and Vertex AI Pipelines.\n",
         "\n",
-        "You compile the pipeline with the method Compiler().compile(), with the following parameters:\n",
+        "Compile the pipeline with the Compiler().compile() method using the following parameters:\n",
         "\n",
         "- `pipeline_func`: The corresponding DSL function that defines the pipeline.\n",
         "- `package_path`: The JSON file to write the transportable compiled pipeline to."
@@ -620,14 +697,14 @@
       "source": [
         "### Execute the hello world pipeline\n",
         "\n",
-        "Now that the pipeline is compiled, you can execute by:\n",
+        "Now that the pipeline is compiled, you can execute it by:\n",
         "\n",
-        "- Create a Vertex AI PipelineJob, with the following parameters:\n",
+        "- Creating a Vertex AI PipelineJob with the following parameters:\n",
         "    - `display_name`: The human readable name for the job.\n",
-        "    - `template_path`: Thee compiled JSON pipeline definition.\n",
+        "    - `template_path`: The compiled JSON pipeline definition.\n",
         "    - `pipeline_root`: Where to write output artifacts to.\n",
         "\n",
-        "Click on the generated link below `INFO:google.cloud.aiplatform.pipeline_jobs:View Pipeline Job:` to see your run in the Cloud Console."
+        "Click on the generated link below `INFO:google.cloud.aiplatform.pipeline_jobs:View Pipeline Job:` to see your job run in the Cloud Console."
       ]
     },
     {
@@ -638,7 +715,7 @@
       },
       "outputs": [],
       "source": [
-        "pipeline = aip.PipelineJob(\n",
+        "pipeline = aiplatform.PipelineJob(\n",
         "    display_name=\"hello_world\",\n",
         "    template_path=\"hello_world.json\",\n",
         "    pipeline_root=PIPELINE_ROOT,\n",
@@ -735,7 +812,7 @@
       "source": [
         "### Delete a pipeline job\n",
         "\n",
-        "After a pipeline job is completed, you can delete the pipeline job with the method `delete()`.  Prior to completion, a pipeline job can be canceled with the method `cancel()`."
+        "After a pipeline job is completed, you can delete the pipeline job with the `delete()` method. Prior to completion, a pipeline job can be canceled with the method `cancel()`."
       ]
     },
     {
@@ -761,7 +838,7 @@
         "\n",
         "    hello_world_op = components.load_component_from_file('./hello_world.yaml').\n",
         "\n",
-        "You can also use the load_component_from_url method, if your component YAML file is stored online, such as if in a git repo."
+        "You can also use the `load_component_from_url` method, if your component YAML file is stored online, such as in a git repository."
       ]
     },
     {
@@ -774,7 +851,7 @@
       "source": [
         "from kfp import components\n",
         "\n",
-        "PIPELINE_ROOT = \"{}/pipeline_root/hello_world-v2\".format(BUCKET_NAME)\n",
+        "PIPELINE_ROOT = \"{}/pipeline_root/hello_world-v2\".format(BUCKET_URI)\n",
         "\n",
         "hello_world_op = components.load_component_from_file(\"./hello_world.yaml\")\n",
         "\n",
@@ -785,12 +862,13 @@
         "    pipeline_root=PIPELINE_ROOT,\n",
         ")\n",
         "def pipeline(text: str = \"hi there\"):\n",
-        "    hellow_world_task = hello_world_op(text)\n",
+        "    hello_world_task = hello_world_op(text)\n",
+        "    return hello_world_task\n",
         "\n",
         "\n",
         "compiler.Compiler().compile(pipeline_func=pipeline, package_path=\"hello_world-v2.json\")\n",
         "\n",
-        "pipeline = aip.PipelineJob(\n",
+        "pipeline = aiplatform.PipelineJob(\n",
         "    display_name=\"hello_world-v2\",\n",
         "    template_path=\"hello_world-v2.json\",\n",
         "    pipeline_root=PIPELINE_ROOT,\n",
@@ -809,7 +887,7 @@
       "source": [
         "### Delete a pipeline job\n",
         "\n",
-        "After a pipeline job is completed, you can delete the pipeline job with the method `delete()`.  Prior to completion, a pipeline job can be canceled with the method `cancel()`."
+        "After a pipeline job is completed, you can delete the pipeline job with the `delete()` method. Prior to completion, a pipeline job can be canceled with the method `cancel()`."
       ]
     },
     {
@@ -837,7 +915,7 @@
         "\n",
         "- Pull the raw file format version from the repo. For github, that will be in the form of:\n",
         "\n",
-        "    https://raw.githubusercontent.com/\n",
+        "    https://raw.githubusercontent.com/....\n",
         "\n",
         "- Specify the version of the component/pipeline. For github, that will be the branch."
       ]
@@ -857,7 +935,7 @@
         "\n",
         "! wget https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/{VERSION}/notebooks/community/ml_ops/stage3/src/hello_world.json -O hello_git_example.json\n",
         "\n",
-        "pipeline = aip.PipelineJob(\n",
+        "pipeline = aiplatform.PipelineJob(\n",
         "    display_name=\"hello_world-git\",\n",
         "    template_path=\"hello_git_example.json\",\n",
         "    pipeline_root=PIPELINE_ROOT,\n",
@@ -876,7 +954,7 @@
       "source": [
         "### Delete a pipeline job\n",
         "\n",
-        "After a pipeline job is completed, you can delete the pipeline job with the method `delete()`.  Prior to completion, a pipeline job can be canceled with the method `cancel()`."
+        "After a pipeline job is completed, you can delete the pipeline job with the `delete()` method. Prior to completion, a pipeline job can be canceled with the method `cancel()`."
       ]
     },
     {
@@ -916,7 +994,7 @@
         "    return np.mean(values)\n",
         "\n",
         "\n",
-        "PIPELINE_ROOT = \"{}/pipeline_root/numpy_mean\".format(BUCKET_NAME)\n",
+        "PIPELINE_ROOT = \"{}/pipeline_root/numpy_mean\".format(BUCKET_URI)\n",
         "\n",
         "\n",
         "@dsl.pipeline(\n",
@@ -924,11 +1002,12 @@
         ")\n",
         "def pipeline(values: list = [2, 3]):\n",
         "    numpy_task = numpy_mean(values)\n",
+        "    return numpy_task\n",
         "\n",
         "\n",
         "compiler.Compiler().compile(pipeline_func=pipeline, package_path=\"numpy_mean.json\")\n",
         "\n",
-        "pipeline = aip.PipelineJob(\n",
+        "pipeline = aiplatform.PipelineJob(\n",
         "    display_name=\"numpy_mean\",\n",
         "    template_path=\"numpy_mean.json\",\n",
         "    pipeline_root=PIPELINE_ROOT,\n",
@@ -949,7 +1028,7 @@
       "source": [
         "### Delete a pipeline job\n",
         "\n",
-        "After a pipeline job is completed, you can delete the pipeline job with the method `delete()`.  Prior to completion, a pipeline job can be canceled with the method `cancel()`."
+        "After a pipeline job is completed, you can delete the pipeline job with the `delete()` method. Prior to completion, a pipeline job can be canceled with the method `cancel()`."
       ]
     },
     {
@@ -984,7 +1063,7 @@
       },
       "outputs": [],
       "source": [
-        "PIPELINE_ROOT = \"{}/pipeline_root/add_div2\".format(BUCKET_NAME)\n",
+        "PIPELINE_ROOT = \"{}/pipeline_root/add_div2\".format(BUCKET_URI)\n",
         "\n",
         "\n",
         "@component(output_component_file=\"add.yaml\", base_image=\"python:3.9\")\n",
@@ -1003,11 +1082,12 @@
         "def pipeline(v1: int = 4, v2: int = 5):\n",
         "    add_task = add(v1, v2)\n",
         "    div2_task = div_by_2(add_task.output)\n",
+        "    return div2_task\n",
         "\n",
         "\n",
         "compiler.Compiler().compile(pipeline_func=pipeline, package_path=\"add_div2.json\")\n",
         "\n",
-        "pipeline = aip.PipelineJob(\n",
+        "pipeline = aiplatform.PipelineJob(\n",
         "    display_name=\"add_div2\",\n",
         "    template_path=\"add_div2.json\",\n",
         "    pipeline_root=PIPELINE_ROOT,\n",
@@ -1028,7 +1108,7 @@
       "source": [
         "### Delete a pipeline job\n",
         "\n",
-        "After a pipeline job is completed, you can delete the pipeline job with the method `delete()`.  Prior to completion, a pipeline job can be canceled with the method `cancel()`."
+        "After a pipeline job is completed, you can delete the pipeline job with the `delete()` method. Prior to completion, a pipeline job can be canceled with the method `cancel()`."
       ]
     },
     {
@@ -1050,7 +1130,7 @@
       "source": [
         "### Multiple output pipeline\n",
         "\n",
-        "Next, you design and execute a pipeline where a first component has multiple outputs, which are then used as inputs to the next component. To distinquish between the outputs, when used as inputs to the next component, you do:\n",
+        "Next, you design and execute a pipeline where a first component has multiple outputs, which are then used as inputs to the next component. To distinguish between the outputs, when used as inputs to the next component, you follow:\n",
         "\n",
         "1. Set the function return type to `NamedTuple`.\n",
         "2. In NamedTuple, specify a name and type for each output, in the specified order.\n",
@@ -1065,7 +1145,7 @@
       },
       "outputs": [],
       "source": [
-        "PIPELINE_ROOT = \"{}/pipeline_root/multi_output\".format(BUCKET_NAME)\n",
+        "PIPELINE_ROOT = \"{}/pipeline_root/multi_output\".format(BUCKET_URI)\n",
         "\n",
         "\n",
         "@component()\n",
@@ -1099,11 +1179,12 @@
         "        multi_output_task.outputs[\"output_1\"],\n",
         "        multi_output_task.outputs[\"output_2\"],\n",
         "    )\n",
+        "    return concat_task\n",
         "\n",
         "\n",
         "compiler.Compiler().compile(pipeline_func=pipeline, package_path=\"multi_output.json\")\n",
         "\n",
-        "pipeline = aip.PipelineJob(\n",
+        "pipeline = aiplatform.PipelineJob(\n",
         "    display_name=\"multi-output\",\n",
         "    template_path=\"multi_output.json\",\n",
         "    pipeline_root=PIPELINE_ROOT,\n",
@@ -1124,7 +1205,7 @@
       "source": [
         "### Delete a pipeline job\n",
         "\n",
-        "After a pipeline job is completed, you can delete the pipeline job with the method `delete()`.  Prior to completion, a pipeline job can be canceled with the method `cancel()`."
+        "After a pipeline job is completed, you can delete the pipeline job with the `delete()` method. Prior to completion, a pipeline job can be canceled with the method `cancel()`."
       ]
     },
     {
@@ -1146,9 +1227,9 @@
       "source": [
         "## Parallel tasks in component\n",
         "\n",
-        "Next, you design and execute a pipeline with parallel tasks. In this example, one parallel task adds up a list of integers and another substracts them. Note that the compiler knows these two tasks can be ran in parallel, because their input is not dependent on the output of the other task.\n",
+        "Next, you design and execute a pipeline with parallel tasks. In this example, one parallel task adds up a list of integers and another substracts them. Note that the compiler knows these two tasks can be run in parallel, because their input is not dependent on the output of the other task.\n",
         "\n",
-        "Finally, the add task waits on the two parallel tasks to complete, and then adds together the two outputs."
+        "Finally, the `add_int` task waits on the two parallel tasks to complete, and then adds together the two outputs."
       ]
     },
     {
@@ -1159,14 +1240,14 @@
       },
       "outputs": [],
       "source": [
-        "PIPELINE_ROOT = \"{}/pipeline_root/parallel\".format(BUCKET_NAME)\n",
+        "PIPELINE_ROOT = \"{}/pipeline_root/parallel\".format(BUCKET_URI)\n",
         "\n",
         "\n",
         "@component()\n",
         "def add_list(values: list) -> int:\n",
         "    ret = 0\n",
         "    for value in values:\n",
-        "        ret += 1\n",
+        "        ret = value + ret\n",
         "    return ret\n",
         "\n",
         "\n",
@@ -1174,12 +1255,12 @@
         "def sub_list(values: list) -> int:\n",
         "    ret = 0\n",
         "    for value in values:\n",
-        "        ret -= 1\n",
+        "        ret = value - ret\n",
         "    return ret\n",
         "\n",
         "\n",
         "@component()\n",
-        "def add(value1: int, value2: int) -> int:\n",
+        "def add_int(value1: int, value2: int) -> int:\n",
         "    return value1 + value2\n",
         "\n",
         "\n",
@@ -1189,12 +1270,13 @@
         "def pipeline(values: list = [1, 2, 3]):\n",
         "    add_list_task = add_list(values)\n",
         "    sub_list_task = sub_list(values)\n",
-        "    add_task = add(add_list_task.output, sub_list_task.output)\n",
+        "    add_task = add_int(add_list_task.output, sub_list_task.output)\n",
+        "    return add_task\n",
         "\n",
         "\n",
         "compiler.Compiler().compile(pipeline_func=pipeline, package_path=\"parallel.json\")\n",
         "\n",
-        "pipeline = aip.PipelineJob(\n",
+        "pipeline = aiplatform.PipelineJob(\n",
         "    display_name=\"parallel\",\n",
         "    template_path=\"parallel.json\",\n",
         "    pipeline_root=PIPELINE_ROOT,\n",
@@ -1215,7 +1297,7 @@
       "source": [
         "### Delete a pipeline job\n",
         "\n",
-        "After a pipeline job is completed, you can delete the pipeline job with the method `delete()`.  Prior to completion, a pipeline job can be canceled with the method `cancel()`."
+        "After a pipeline job is completed, you can delete the pipeline job with the `delete()` method. Prior to completion, a pipeline job can be canceled with the method `cancel()`."
       ]
     },
     {
@@ -1237,7 +1319,7 @@
       "source": [
         "## Control flow in pipeline\n",
         "\n",
-        "While Python control statements, e.g., if/else, for, can be used in a component, they cannot be used in the pipeline function. Each task in the pipeline function runs as a node in a graph. Thus a control flow statement also has to run as a graph node. To support this, KFP provides a set of DSL statements that implement control flow as a graph node."
+        "While Python control statements(e.g., if/else, for) can be used in a component, they cannot be used in a pipeline function. Each task in a pipeline function runs as a node in a graph. Thus a control flow statement also has to run as a graph node. To support this, KFP provides a set of DSL statements that implement control flow as a graph node."
       ]
     },
     {
@@ -1248,7 +1330,7 @@
       "source": [
         "### dsl.ParallelFor\n",
         "\n",
-        "The statement `dsl.ParallelFor()` implements a for loop, where each iteration in the for loop runs in parallel."
+        "The statement `dsl.ParallelFor()` implements a `for` loop, where each iteration in the `for` loop runs in parallel."
       ]
     },
     {
@@ -1259,7 +1341,7 @@
       },
       "outputs": [],
       "source": [
-        "PIPELINE_ROOT = \"{}/pipeline_root/parallel_for\".format(BUCKET_NAME)\n",
+        "PIPELINE_ROOT = \"{}/pipeline_root/parallel_for\".format(BUCKET_URI)\n",
         "\n",
         "\n",
         "@component()\n",
@@ -1281,11 +1363,12 @@
         "    with dsl.ParallelFor(values) as item:\n",
         "        output = double(item).output\n",
         "        echo_task = echo(output)\n",
+        "    return echo_task\n",
         "\n",
         "\n",
         "compiler.Compiler().compile(pipeline_func=pipeline, package_path=\"parallel_for.json\")\n",
         "\n",
-        "pipeline = aip.PipelineJob(\n",
+        "pipeline = aiplatform.PipelineJob(\n",
         "    display_name=\"parallel-for\",\n",
         "    template_path=\"parallel_for.json\",\n",
         "    pipeline_root=PIPELINE_ROOT,\n",
@@ -1306,7 +1389,7 @@
       "source": [
         "### Delete a pipeline job\n",
         "\n",
-        "After a pipeline job is completed, you can delete the pipeline job with the method `delete()`.  Prior to completion, a pipeline job can be canceled with the method `cancel()`."
+        "After a pipeline job is completed, you can delete the pipeline job with the `delete()` method. Prior to completion, a pipeline job can be canceled with the method `cancel()`."
       ]
     },
     {
@@ -1330,11 +1413,13 @@
         "\n",
         "The statement `dsl.Condition()` implements an `if` statement. There is no support for an `else` or `elif` statement. You use a separate `dsl.Condition()` for each value you want to test for. For example, if the output from a task is `1` or `0`, you will have two `dsl.Condition()` statements, one for 1 and one for 0.\n",
         "\n",
-        "The condition in `dsl.Condition()` is evaluated at run-time, not compile time. As such it is not Python code anymore.  The condition is of type `ConditionOperator`. This operator takes three parts:\n",
+        "The condition in `dsl.Condition()` is evaluated at run-time, not compile time. As such it is not Python code anymore.  The condition is of type `ConditionOperator`. This operator has three parts:\n",
         "\n",
-        "- PipelineParam or task output\n",
-        "- == or !=\n",
-        "- string or integer value"
+        "1. PipelineParam or task output\n",
+        "2. == or !=\n",
+        "3. string or integer value\n",
+        "\n",
+        "A `dsl.Condition()` can be named using the `name` parameter while defining the condition."
       ]
     },
     {
@@ -1373,11 +1458,12 @@
         "        task = heads()\n",
         "    with dsl.Condition(flip_task.output == 0, name=\"false_clause\"):\n",
         "        task = tails()\n",
+        "    return task\n",
         "\n",
         "\n",
         "compiler.Compiler().compile(pipeline_func=pipeline, package_path=\"condition.json\")\n",
         "\n",
-        "pipeline = aip.PipelineJob(\n",
+        "pipeline = aiplatform.PipelineJob(\n",
         "    display_name=\"condition\",\n",
         "    template_path=\"condition.json\",\n",
         "    pipeline_root=PIPELINE_ROOT,\n",
@@ -1398,7 +1484,7 @@
       "source": [
         "### Delete a pipeline job\n",
         "\n",
-        "After a pipeline job is completed, you can delete the pipeline job with the method `delete()`.  Prior to completion, a pipeline job can be canceled with the method `cancel()`."
+        "After a pipeline job is completed, you can delete the pipeline job with the `delete()` method. Prior to completion, a pipeline job can be canceled with the method `cancel()`."
       ]
     },
     {
@@ -1418,16 +1504,14 @@
         "id": "pipeline_errata"
       },
       "source": [
-        "## Errata\n",
-        "\n",
         "### Caching in pipeline components\n",
         "\n",
-        "When running a pipeline with Vertex AI Pipelines, the outcome state of each task is cached. With caching, if the pipeline is ran again, and the compiled definition of the task and state has not changed, the cached output will be used instead of running the task again.\n",
+        "When running a pipeline with Vertex AI Pipelines, the outcome state of each task is cached. With caching, if the pipeline is run again, and the compiled definition of the task and state has not changed, the cached output will be used instead of running the task again.\n",
         "\n",
-        "To override caching, i.e., forceable run the task, you set the parameter `enable_caching` to `False` when creating the Vertex AI Pipeline job.\n",
+        "To override caching, i.e., force run the task, you set the parameter `enable_caching` to `False` when creating the Vertex AI Pipeline job.\n",
         "\n",
         "```\n",
-        "pipeline = aip.PipelineJob(\n",
+        "pipeline = aiplatform.PipelineJob(\n",
         "    display_name=\"example\",\n",
         "    template_path=\"example.json\",\n",
         "    pipeline_root=PIPELINE_ROOT,\n",
@@ -1437,11 +1521,11 @@
         "\n",
         "### Asynchronous execution of pipeline\n",
         "\n",
-        "When running a pipeline with the method `run()`, the pipeline is ran synchronously. To run asynchronously, you use the method `submit()`. Once the job has started, your Python script can continue to execute. Then when you need to block execution using the method `wait()`.\n",
+        "When running a pipeline with the method `run()`, the pipeline is run synchronously. To run asynchronously, you use the method `submit()`. Once the job has started, your Python script can continue to execute. To block execution, you can use the method `wait()`.\n",
         "\n",
         "### Setting machine resources for pipeline steps\n",
         "\n",
-        "By default, Vertex AI Pipelines will automatically find the best matching machine type to run the component. You can override and specify the machine resources on a per component basis, when you invoke the component in a pipeline, as follows:\n",
+        "By default, Vertex AI Pipelines automatically finds the best matching machine type to run the component. You can override and specify the machine resources on a per component basis, when you invoke the component in a pipeline, as follows:\n",
         "\n",
         "```\n",
         "@dsl.pipeline(name='my-pipeline')\n",
@@ -1469,15 +1553,9 @@
         "\n",
         "Otherwise, you can delete the individual resources you created in this tutorial:\n",
         "\n",
-        "- Dataset\n",
-        "- Pipeline\n",
-        "- Model\n",
-        "- Endpoint\n",
-        "- AutoML Training Job\n",
-        "- Batch Job\n",
-        "- Custom Job\n",
-        "- Hyperparameter Tuning Job\n",
-        "- Cloud Storage Bucket"
+        "### Cloud Storage Bucket\n",
+        "\n",
+        "Set `delete_bucket` to True to delete the Cloud storage bucket used in this notebook."
       ]
     },
     {
@@ -1488,61 +1566,10 @@
       },
       "outputs": [],
       "source": [
-        "delete_all = True\n",
+        "delete_bucket = False\n",
         "\n",
-        "if delete_all:\n",
-        "    # Delete the dataset using the Vertex dataset object\n",
-        "    try:\n",
-        "        if \"dataset\" in globals():\n",
-        "            dataset.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the model using the Vertex model object\n",
-        "    try:\n",
-        "        if \"model\" in globals():\n",
-        "            model.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the endpoint using the Vertex endpoint object\n",
-        "    try:\n",
-        "        if \"endpoint\" in globals():\n",
-        "            endpoint.undeploy_all()\n",
-        "            endpoint.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the AutoML or Pipeline training job\n",
-        "    try:\n",
-        "        if \"dag\" in globals():\n",
-        "            dag.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the custom training job\n",
-        "    try:\n",
-        "        if \"job\" in globals():\n",
-        "            job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the batch prediction job using the Vertex batch prediction object\n",
-        "    try:\n",
-        "        if \"batch_predict_job\" in globals():\n",
-        "            batch_predict_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the hyperparameter tuning job using the Vertex hyperparameter tuning object\n",
-        "    try:\n",
-        "        if \"hpt_job\" in globals():\n",
-        "            hpt_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    if \"BUCKET_NAME\" in globals():\n",
-        "        ! gsutil rm -r $BUCKET_NAME"
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil rm -r $BUCKET_URI"
       ]
     }
   ],

notebooks/community/ml_ops/stage3/get_started_with_rapid_prototyping_bqml_automl.ipynb

@@ -32,14 +32,20 @@
         "# E2E ML on GCP: MLOps stage 3 : Get started with rapid prototyping with AutoML and BQML\n",
         "<table align=\"left\">\n",
         "  <td>\n",
-        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage6/get_started_with_rapid_prototyping.ipynb\">\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage3/get_started_with_rapid_prototyping_bqml_automl.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage3/get_started_with_rapid_prototyping_bqml_automl.ipynb\">\n",
         "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
         "      View on GitHub\n",
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://console.cloud.google.com/ai/platform/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage6/get_started_with_rapid_prototyping.ipynb\">\n",
-        "      Open in Vertex Workbench\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/ml_ops/stage3/get_started_with_rapid_prototyping_bqml_automl.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "      Open in Vertex AI Workbench\n",
         "    </a>\n",
         "  </td>\n",
         "</table>\n",
@@ -235,7 +241,7 @@
       "source": [
         "## Installation\n",
         "\n",
-        "Install the latest version of Vertex AI SDK for Python."
+        "Install the packages required for executing this notebook."
       ]
     },
     {
@@ -248,34 +254,20 @@
       "source": [
         "import os\n",
         "\n",
-        "# Google Cloud Notebook\n",
-        "if os.path.exists(\"/opt/deeplearning/metadata/env_version\"):\n",
-        "    USER_FLAG = \"--user\"\n",
-        "else:\n",
-        "    USER_FLAG = \"\"\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
         "\n",
-        "! pip3 install --quiet --upgrade google-cloud-aiplatform {USER_FLAG}"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "eeba891a06fc"
-      },
-      "source": [
-        "Install additional packages used in this tutorial."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "739011eb"
-      },
-      "outputs": [],
-      "source": [
-        "! pip3 install {USER_FLAG} --quiet -U google-cloud-pipeline-components==1.0 kfp\n",
-        "! pip3 install {USER_FLAG} --quiet --upgrade google-cloud-bigquery"
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
+        "USER_FLAG = \"\"\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "\n",
+        "! pip3 install --quiet --upgrade google-cloud-aiplatform {USER_FLAG} -q\n",
+        "! pip3 install {USER_FLAG} --quiet -U google-cloud-pipeline-components==1.0 kfp -q\n",
+        "! pip3 install {USER_FLAG} --quiet --upgrade google-cloud-bigquery -q"
       ]
     },
     {
@@ -316,10 +308,12 @@
       "source": [
         "### Authenticate your Google Cloud account\n",
         "\n",
-        "**If you are using Google Cloud Notebooks**, your environment is already authenticated. Skip this step.\n",
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already\n",
+        "authenticated. Skip this step.\n",
         "\n",
         "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
         "\n",
+        "\n",
         "**Otherwise**, follow these steps:\n",
         "\n",
         "In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\n",
@@ -351,9 +345,13 @@
         "import os\n",
         "import sys\n",
         "\n",
-        "# If on Google Cloud Notebook, then don't execute this code\n",
-        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\"):\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
+        "IS_COLAB = \"google.colab\" in sys.modules\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
+        "    \"DL_ANACONDA_HOME\"\n",
+        "):\n",
         "    if \"google.colab\" in sys.modules:\n",
+        "        IS_COLAB = True\n",
         "        from google.colab import auth as google_auth\n",
         "\n",
         "        google_auth.authenticate_user()\n",
@@ -385,7 +383,7 @@
         "\n",
         "2. [Make sure that billing is enabled for your project.](https://cloud.google.com/billing/docs/how-to/modify-project)\n",
         "\n",
-        "3. [Enable the following APIs: Vertex AI APIs, Compute Engine APIs, and Cloud Storage.](https://console.cloud.google.com/flows/enableapi?apiid=ml.googleapis.com,compute_component,storage-component.googleapis.com)\n",
+        "3. [Enable the following APIs: Vertex AI APIs, Compute Engine APIs, and Cloud Storage.](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,compute_component,storage-component.googleapis.com)\n",
         "\n",
         "4. If you are running this notebook locally, you will need to install the [Cloud SDK]((https://cloud.google.com/sdk)).\n",
         "\n",
@@ -414,6 +412,8 @@
       },
       "outputs": [],
       "source": [
+        "import os\n",
+        "\n",
         "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
       ]
     },
@@ -471,7 +471,9 @@
       },
       "outputs": [],
       "source": [
-        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+        "REGION = \"[your-region]\"  # @param {type:\"string\"}\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
       ]
     },
     {
@@ -612,9 +614,17 @@
         "    or SERVICE_ACCOUNT is None\n",
         "    or SERVICE_ACCOUNT == \"[your-service-account]\"\n",
         "):\n",
-        "    # Get your GCP project id from gcloud\n",
-        "    shell_output = !gcloud auth list 2>/dev/null\n",
-        "    SERVICE_ACCOUNT = shell_output[2].replace(\"*\", \"\").strip()\n",
+        "    # Get your service account from gcloud\n",
+        "    if not IS_COLAB:\n",
+        "        shell_output = !gcloud auth list 2>/dev/null\n",
+        "        SERVICE_ACCOUNT = shell_output[2].replace(\"*\", \"\").strip()\n",
+        "\n",
+        "    if IS_COLAB:\n",
+        "        shell_output = ! gcloud projects describe  $PROJECT_ID\n",
+        "        # print(\"shell_output=\", shell_output)\n",
+        "        project_number = shell_output[-1].split(\":\")[1].strip().replace(\"'\", \"\")\n",
+        "        SERVICE_ACCOUNT = f\"{project_number}-compute@developer.gserviceaccount.com\"\n",
+        "\n",
         "    print(\"Service Account:\", SERVICE_ACCOUNT)"
       ]
     },
@@ -667,6 +677,7 @@
         "from typing import NamedTuple\n",
         "\n",
         "import google.cloud.aiplatform as aip\n",
+        "from google.cloud import bigquery\n",
         "from kfp import dsl\n",
         "from kfp.v2 import compiler\n",
         "from kfp.v2.dsl import Artifact, Input, Metrics, Output, component"
@@ -1429,6 +1440,17 @@
         "- `validate_infrastructure`: Validate the deployed model serving infrastructure."
       ]
     },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "040e82bc1646"
+      },
+      "outputs": [],
+      "source": [
+        "DISPLAY_NAME = \"rapid-prototyping\""
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -1453,8 +1475,7 @@
         "    from google_cloud_pipeline_components.types import artifact_types\n",
         "    from google_cloud_pipeline_components.v1.bigquery import (\n",
         "        BigqueryCreateModelJobOp, BigqueryEvaluateModelJobOp,\n",
-        "        BigqueryExportModelJobOp, BigqueryPredictModelJobOp,\n",
-        "        BigqueryQueryJobOp)\n",
+        "        BigqueryExportModelJobOp)\n",
         "    from google_cloud_pipeline_components.v1.endpoint import (EndpointCreateOp,\n",
         "                                                              ModelDeployOp)\n",
         "    from google_cloud_pipeline_components.v1.model import ModelUploadOp\n",
@@ -1670,7 +1691,7 @@
         "PIPELINE_ROOT = f\"{BUCKET_URI}/pipeline_root\"\n",
         "image_prefix = REGION.split(\"-\")[0]\n",
         "BQML_SERVING_CONTAINER_IMAGE_URI = (\n",
-        "    f\"{image_prefix}-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-6:latest\"\n",
+        "    f\"{image_prefix}-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-8:latest\"\n",
         ")\n",
         "\n",
         "BQ_DATASET = \"rapid_prototype\"  # j90wipxexhrgq3cquanc5\"  # @param {type:\"string\"}\n",
@@ -1678,7 +1699,6 @@
         "BQ_LOCATION = BQ_LOCATION.upper()\n",
         "BQML_EXPORT_LOCATION = f\"{BUCKET_URI}/artifacts/bqml\"\n",
         "\n",
-        "DISPLAY_NAME = \"rapid-prototyping\"\n",
         "ENDPOINT_DISPLAY_NAME = f\"{DISPLAY_NAME}_endpoint\"\n",
         "\n",
         "compiler.Compiler().compile(\n",
@@ -1706,7 +1726,7 @@
         "    template_path=PIPELINE_JSON_PKG_PATH,\n",
         "    pipeline_root=PIPELINE_ROOT,\n",
         "    parameter_values=pipeline_params,\n",
-        "    enable_caching=True,\n",
+        "    enable_caching=False,\n",
         ")\n",
         "\n",
         "response = pipeline_job.submit()"
@@ -1758,96 +1778,72 @@
       },
       "outputs": [],
       "source": [
-        "delete = True  # set to True if you want to delete resources created in this tutorial.\n",
+        "delete_bucket = True\n",
         "\n",
+        "print(\"Will delete endpoint\")\n",
         "\n",
-        "delete_vertex_dataset = True and delete\n",
-        "delete_pipeline = True and delete\n",
-        "delete_model = True and delete\n",
-        "delete_endpoint = True and delete\n",
-        "delete_batchjob = True and delete\n",
-        "delete_bucket = True and delete\n",
-        "delete_bq_dataset = True and delete\n",
+        "endpoints = aip.Endpoint.list(\n",
+        "    filter=f\"display_name={DISPLAY_NAME}_endpoint\", order_by=\"create_time\"\n",
+        ")\n",
+        "endpoint = endpoints[0]\n",
+        "endpoint.undeploy_all()\n",
+        "aip.Endpoint.delete(endpoint.resource_name)\n",
+        "print(\"Deleted endpoint:\", endpoint)\n",
         "\n",
-        "try:\n",
-        "    if delete_endpoint and \"DISPLAY_NAME\" in globals():\n",
-        "        print(\"Will delete endpoint\")\n",
-        "        endpoints = aip.Endpoint.list(\n",
-        "            filter=f\"display_name={DISPLAY_NAME}_endpoint\", order_by=\"create_time\"\n",
-        "        )\n",
-        "        endpoint = endpoints[0]\n",
-        "        endpoint.undeploy_all()\n",
-        "        aip.Endpoint.delete(endpoint.resource_name)\n",
-        "        print(\"Deleted endpoint:\", endpoint)\n",
-        "except Exception as e:\n",
-        "    print(e)\n",
-        "\n",
-        "if delete_model and \"DISPLAY_NAME\" in globals():\n",
-        "    print(\"Will delete models\")\n",
-        "    suffix_list = [\"bqml\", \"automl\", \"best\"]\n",
-        "    for suffix in suffix_list:\n",
-        "        try:\n",
-        "            model_display_name = f\"{DISPLAY_NAME}_{suffix}\"\n",
-        "            print(\"Will delete model with name \" + model_display_name)\n",
-        "            models = aip.Model.list(\n",
-        "                filter=f\"display_name={model_display_name}\", order_by=\"create_time\"\n",
-        "            )\n",
-        "\n",
-        "            model = models[0]\n",
-        "            aip.Model.delete(model)\n",
-        "            print(\"Deleted model:\", model)\n",
-        "        except Exception as e:\n",
-        "            print(e)\n",
-        "\n",
-        "if delete_vertex_dataset and \"DISPLAY_NAME\" in globals():\n",
-        "    print(\"Will delete Vertex dataset\")\n",
+        "print(\"Will delete models\")\n",
+        "suffix_list = [\"bqml\", \"automl\", \"best\"]\n",
+        "for suffix in suffix_list:\n",
         "    try:\n",
-        "        datasets = aip.TabularDataset.list(\n",
-        "            filter=f\"display_name={DISPLAY_NAME}\", order_by=\"create_time\"\n",
+        "        model_display_name = f\"{DISPLAY_NAME}_{suffix}\"\n",
+        "        print(\"Will delete model with name \" + model_display_name)\n",
+        "        models = aip.Model.list(\n",
+        "            filter=f\"display_name={model_display_name}\", order_by=\"create_time\"\n",
         "        )\n",
         "\n",
-        "        dataset = datasets[0]\n",
-        "        aip.TabularDataset.delete(dataset)\n",
-        "        print(\"Deleted Vertex dataset:\", dataset)\n",
+        "        model = models[0]\n",
+        "        aip.Model.delete(model)\n",
+        "        print(\"Deleted model:\", model)\n",
         "    except Exception as e:\n",
         "        print(e)\n",
         "\n",
         "\n",
-        "try:\n",
-        "    if delete_pipeline and \"DISPLAY_NAME\" in globals():\n",
-        "        pipelines = aip.PipelineJob.list(\n",
-        "            filter=f\"pipeline_name={DISPLAY_NAME}\", order_by=\"create_time\"\n",
-        "        )\n",
-        "        pipeline = pipelines[0]\n",
-        "        aip.PipelineJob.delete(pipeline)\n",
-        "        print(\"Deleted pipeline:\", pipeline)\n",
-        "except Exception as e:\n",
-        "    print(e)\n",
+        "print(\"Will delete Vertex dataset\")\n",
         "\n",
-        "if delete_bq_dataset and \"DISPLAY_NAME\" in globals():\n",
-        "    from google.cloud import bigquery\n",
+        "datasets = aip.TabularDataset.list(\n",
+        "    filter=f\"display_name={DISPLAY_NAME}\", order_by=\"create_time\"\n",
+        ")\n",
         "\n",
-        "    try:\n",
-        "        # Construct a BigQuery client object.\n",
-        "\n",
-        "        bq_client = bigquery.Client(project=PROJECT_ID, location=BQ_LOCATION)\n",
-        "\n",
-        "        # TODO(developer): Set model_id to the ID of the model to fetch.\n",
-        "        dataset_id = f\"{PROJECT_ID}.{BQ_DATASET}\"\n",
-        "\n",
-        "        print(f\"Will delete BQ dataset '{dataset_id}' from location {BQ_LOCATION}.\")\n",
-        "        # Use the delete_contents parameter to delete a dataset and its contents.\n",
-        "        # Use the not_found_ok parameter to not receive an error if the dataset has already been deleted.\n",
-        "        bq_client.delete_dataset(\n",
-        "            dataset_id, delete_contents=True, not_found_ok=True\n",
-        "        )  # Make an API request.\n",
-        "\n",
-        "        print(f\"Deleted BQ dataset '{dataset_id}' from location {BQ_LOCATION}.\")\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
+        "dataset = datasets[0]\n",
+        "aip.TabularDataset.delete(dataset)\n",
+        "print(\"Deleted Vertex dataset:\", dataset)\n",
         "\n",
         "\n",
-        "if delete_bucket and \"BUCKET_URI\" in globals():\n",
+        "pipelines = aip.PipelineJob.list(\n",
+        "    filter=f\"pipeline_name={DISPLAY_NAME}\", order_by=\"create_time\"\n",
+        ")\n",
+        "pipeline = pipelines[0]\n",
+        "aip.PipelineJob.delete(pipeline)\n",
+        "print(\"Deleted pipeline:\", pipeline)\n",
+        "\n",
+        "\n",
+        "# Construct a BigQuery client object.\n",
+        "\n",
+        "bq_client = bigquery.Client(project=PROJECT_ID, location=BQ_LOCATION)\n",
+        "\n",
+        "# TODO(developer): Set dataset_id to the ID of the dataset to fetch.\n",
+        "dataset_id = f\"{PROJECT_ID}.{BQ_DATASET}\"\n",
+        "\n",
+        "print(f\"Will delete BQ dataset '{dataset_id}' from location {BQ_LOCATION}.\")\n",
+        "# Use the delete_contents parameter to delete a dataset and its contents.\n",
+        "# Use the not_found_ok parameter to not receive an error if the dataset has already been deleted.\n",
+        "bq_client.delete_dataset(\n",
+        "    dataset_id, delete_contents=True, not_found_ok=True\n",
+        ")  # Make an API request.\n",
+        "\n",
+        "print(f\"Deleted BQ dataset '{dataset_id}' from location {BQ_LOCATION}.\")\n",
+        "\n",
+        "\n",
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
         "    ! gsutil rm -r $BUCKET_URI"
       ]
     }

notebooks/community/ml_ops/stage3/mlops_formalization.ipynb

@@ -32,17 +32,23 @@
         "# E2E ML on GCP: MLOps stage 3 : formalization\n",
         "\n",
         "<table align=\"left\">\n",
+        "   <td>\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage3/mlops_formalization.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "    </a>\n",
+        "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage3/mlops_formalization.ipynb\">\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samplestree/main/notebooks/community/ml_ops/stage3/mlops_formalization.ipynb\">\n",
         "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
         "      View on GitHub\n",
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://console.cloud.google.com/ai/platform/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage3/mlops_formalization.ipynb\">\n",
-        "      Open in Google Cloud Notebooks\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/ml_ops/stage3/mlops_formalization.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "      Open in Vertex AI Workbench\n",
         "    </a>\n",
-        "  </td>\n",
+        "  </td>           \n",
         "</table>\n",
         "<br/><br/><br/>"
       ]
@@ -182,6 +188,19 @@
       },
       "outputs": [],
       "source": [
+        "import os\n",
+        "\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
+        "\n",
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
+        "USER_FLAG = \"\"\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "\n",
         "ONCE_ONLY = False\n",
         "if ONCE_ONLY:\n",
         "    ! pip3 install -U tensorflow==2.5 $USER_FLAG\n",
@@ -231,6 +250,32 @@
         "    app.kernel.do_shutdown(True)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "BF1j6f9HApxa"
+      },
+      "source": [
+        "## Before you begin\n",
+        "\n",
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI API and Dataflow API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,dataflow.googleapis.com).\n",
+        "\n",
+        "1. If you are running this notebook locally, you will need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+        "\n",
+        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -334,6 +379,67 @@
         "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "gcp_authenticate"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already authenticated. Skip this step.\n",
+        "\n",
+        "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\n",
+        "\n",
+        "**Click Create service account**.\n",
+        "\n",
+        "In the **Service account name** field, enter a name, and click **Create**.\n",
+        "\n",
+        "In the **Grant this service account access to project** section, click the Role drop-down list. Type \"Vertex\" into the filter box, and select **Vertex Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "Click Create. A JSON file that contains your key downloads to your local environment.\n",
+        "\n",
+        "Enter the path to your service account key as the GOOGLE_APPLICATION_CREDENTIALS variable in the cell below and run the cell."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "gcp_authenticate"
+      },
+      "outputs": [],
+      "source": [
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
+        "IS_COLAB = \"google.colab\" in sys.modules\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
+        "    \"DL_ANACONDA_HOME\"\n",
+        "):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        IS_COLAB = True\n",
+        "        from google.colab import auth as google_auth\n",
+        "\n",
+        "        google_auth.authenticate_user()\n",
+        "\n",
+        "    # If you are running this notebook locally, replace the string below with the\n",
+        "    # path to your service account key and run this cell to authenticate your GCP\n",
+        "    # account.\n",
+        "    elif not os.getenv(\"IS_TESTING\"):\n",
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {

notebooks/community/ml_ops/stage4/README.md

@@ -36,7 +36,7 @@ This stage may be done entirely by MLOps. We recommend:
 
 
 
-<img src='stage4.png'>
+<img src='stage4v3.png'>
 
 ## Notebooks
 
@@ -75,6 +75,25 @@ The steps performed include:
     - Query your pipeline run metadata.
 ```
 
+[Get started with Vertex ML Metadata and AutoML](get_started_with_vertex_ml_metadata_and_automl.ipynb)
+
+```
+The steps performed include:
+
+- Create a `Dataset` resource.
+- Create a corresponding `google.VertexDataset` artifact.
+- Train a model using `AutoML`.
+- Create a corresponding `google.VertexModel` artifact.
+- Create an `Endpoint` resource.
+- Create a corresponding `google.Endpoint` artifact.
+- Deploy the train model to the `Endpoint`.
+- Create an execution and context for the `AutoML` training job and deployment.
+- Add the corresponding artifacts and context to the execution.
+- Add artifact links (event) to the execution.
+- Display the execution graph.
+```
+
+
 Get started with custom model evaluation
 
 Get started with A/B Testing

notebooks/community/ml_ops/stage4/get_started_with_google_artifact_registry.ipynb

@@ -33,16 +33,22 @@
         "\n",
         "<table align=\"left\">\n",
         "  <td>\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage4/get_started_with_google_artifact_registry.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
         "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage4/get_started_with_google_artifact_registry.ipynb\">\n",
         "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
         "      View on GitHub\n",
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://console.cloud.google.com/ai/platform/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage4/get_started_with_google_artifact_registry.ipynb\">\n",
-        "      Open in Google Cloud Notebooks\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/ml_ops/stage4/get_started_with_google_artifact_registry.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "      Open in Vertex AI Workbench\n",
         "    </a>\n",
-        "  </td>\n",
+        "  </td>                               \n",
         "</table>\n",
         "<br/><br/><br/>"
       ]
@@ -90,7 +96,7 @@
       "source": [
         "## Installations\n",
         "\n",
-        "Install *one time* the packages for executing the MLOps notebooks."
+        "Install the packages required for executing the notebook."
       ]
     },
     {
@@ -101,22 +107,20 @@
       },
       "outputs": [],
       "source": [
-        "ONCE_ONLY = False\n",
-        "if ONCE_ONLY:\n",
-        "    ! pip3 install -U tensorflow==2.5 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-data-validation==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-transform==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-io==0.18 $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-aiplatform[tensorboard] $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-pipeline-components $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-bigquery $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-logging $USER_FLAG\n",
-        "    ! pip3 install --upgrade apache-beam[gcp] $USER_FLAG\n",
-        "    ! pip3 install --upgrade pyarrow $USER_FLAG\n",
-        "    ! pip3 install --upgrade cloudml-hypertune $USER_FLAG\n",
-        "    ! pip3 install --upgrade kfp $USER_FLAG\n",
-        "    ! pip3 install --upgrade torchvision $USER_FLAG\n",
-        "    ! pip3 install --upgrade rpy2 $USER_FLAG"
+        "import os\n",
+        "\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
+        "\n",
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
+        "USER_FLAG = \"\"\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "\n",
+        "! pip3 install --upgrade google-cloud-aiplatform $USER_FLAG -q"
       ]
     },
     {
@@ -148,6 +152,36 @@
         "    app.kernel.do_shutdown(True)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "before_you_begin"
+      },
+      "source": [
+        "## Before you begin\n",
+        "\n",
+        "### GPU runtime\n",
+        "\n",
+        "*Make sure you're running this notebook in a GPU runtime if you have that option. In Colab, select* **Runtime > Change Runtime Type > GPU**\n",
+        "\n",
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "2. [Make sure that billing is enabled for your project.](https://cloud.google.com/billing/docs/how-to/modify-project)\n",
+        "\n",
+        "3. [Enable the following APIs: Vertex AI APIs, Compute Engine APIs, and Cloud Storage.](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,compute_component,storage-component.googleapis.com)\n",
+        "\n",
+        "4. If you are running this notebook locally, you will need to install the [Cloud SDK]((https://cloud.google.com/sdk)).\n",
+        "\n",
+        "5. Enter your project ID in the cell below. Then run the  cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$`."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -224,7 +258,10 @@
       },
       "outputs": [],
       "source": [
-        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
+        "\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
       ]
     },
     {
@@ -251,6 +288,67 @@
         "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "gcp_authenticate"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already authenticated. Skip this step.\n",
+        "\n",
+        "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\n",
+        "\n",
+        "**Click Create service account**.\n",
+        "\n",
+        "In the **Service account name** field, enter a name, and click **Create**.\n",
+        "\n",
+        "In the **Grant this service account access to project** section, click the Role drop-down list. Type \"Vertex\" into the filter box, and select **Vertex Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "Click Create. A JSON file that contains your key downloads to your local environment.\n",
+        "\n",
+        "Enter the path to your service account key as the GOOGLE_APPLICATION_CREDENTIALS variable in the cell below and run the cell."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "gcp_authenticate"
+      },
+      "outputs": [],
+      "source": [
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
+        "IS_COLAB = False\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
+        "    \"DL_ANACONDA_HOME\"\n",
+        "):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        IS_COLAB = True\n",
+        "        from google.colab import auth as google_auth\n",
+        "\n",
+        "        google_auth.authenticate_user()\n",
+        "\n",
+        "    # If you are running this notebook locally, replace the string below with the\n",
+        "    # path to your service account key and run this cell to authenticate your GCP\n",
+        "    # account.\n",
+        "    elif not os.getenv(\"IS_TESTING\"):\n",
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {