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
@@ -20,4 +21,6 @@
 /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/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/feature_store/mobile_gaming/mobile_gaming_feature_store.ipynb

@@ -32,18 +32,18 @@
         "<table align=\"left\">\n",
         "\n",
         "  <td>\n",
-        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/notebook_template.ipynb\">\n",
+        "    <a href=\"https://colab.research.google.com/github/vertex-ai-samples/blob/main/notebooks/community/feature_store/mobile_gaming/mobile_gaming_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",
         "  <td>\n",
-        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/notebook_template.ipynb\">\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/feature_store/mobile_gaming/mobile_gaming_feature_store.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/blob/main/notebooks/community/feature_store/mobile_gaming/mobile_gaming_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",
@@ -54,52 +54,52 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "7FZeBEwdXS4d"
+        "id": "tvgnzT1CKxrO"
       },
       "source": [
         "## Overview\n",
-        "\n",
-        "Imagine you are a member of the Data Science team working on the same Mobile Gaming application reported in the [Churn prediction for game developers using Google Analytics 4 (GA4) and BigQuery ML](https://cloud.google.com/blog/topics/developers-practitioners/churn-prediction-game-developers-using-google-analytics-4-ga4-and-bigquery-ml) blog post. \n",
-        "\n",
-        "Business wants to use that information in real-time to take immediate intervention actions in-game to prevent churn. In particular, for each player, they want to provide gaming incentives like new items or bonus packs depending on the customer demographic,  behavioral information and the resulting propensity of return. \n",
-        "\n",
-        "Last year, Google Cloud announced Vertex AI, a managed machine learning (ML) platform that allows data science teams to accelerate the deployment and maintenance of ML models. One of the platform building blocks is Vertex AI Feature store which provides a managed service for low latency scalable feature serving. Also it is a centralized feature repository with easy APIs to search & discover features and feature monitoring capabilities to track drift and other quality issues. \n",
-        "\n",
-        "In this notebook, we will show how the role of Vertex AI Feature Store in a ready to production scenario when the user's activities within the first 24 hours of last engagment and the gaming platform would consume in order to improver UX. Below you can find the high level picture of the system\n",
-        "\n",
+        " \n",
+        "Imagine you are a member of the Data Science team working on the same Mobile Gaming application reported in the [Churn prediction for game developers using Google Analytics 4 (GA4) and BigQuery ML](https://cloud.google.com/blog/topics/developers-practitioners/churn-prediction-game-developers-using-google-analytics-4-ga4-and-bigquery-ml) blog post.\n",
+        " \n",
+        "Business wants to use that information in real-time to take immediate intervention actions in-game to prevent churn. In particular, for each player, they want to provide gaming incentives like new items or bonus packs depending on the customer demographic,  behavioral information and the resulting propensity of return.\n",
+        " \n",
+        "Last year, Google Cloud announced Vertex AI, a managed machine learning (ML) platform that allows data science teams to accelerate the deployment and maintenance of ML models. One of the platform building blocks is Vertex AI Feature store which provides a managed service for low latency scalable feature serving. Also it is a centralized feature repository with easy APIs to search & discover features and feature monitoring capabilities to track drift and other quality issues.\n",
+        " \n",
+        "In this notebook, we will show how the role of Vertex AI Feature Store in a ready to production scenario when the user's activities within the first 24 hours of last engagement and the gaming platform would consume in order to improve UX. Below you can find the high level picture of the system\n",
+        " \n",
         "<img src=\"./assets/mobile_gaming_architecture_1.png\">\n",
-        "\n",
-        "\n",
+        " \n",
+        " \n",
         "### Dataset\n",
-        "\n",
+        " \n",
         "The dataset is the public sample export data from an actual mobile game app called \"Flood It!\" (Android, iOS)\n",
-        "\n",
+        " \n",
         "### Objective\n",
-        "\n",
+        " \n",
         "In the following notebook, you will learn how Vertex AI Feature store\n",
-        "\n",
-        "1.   Provide a centralized feature repository with easy APIs to search & discover features and fetch them for training/serving. \n",
-        "\n",
-        "2.   Simplify deployments of models for Online Prediction, via low latency scalable feature serving.\n",
-        "\n",
-        "3.   Mitigate training serving skew and data leakage by performing point in time lookups to fetch historical data for training.\n",
-        "\n",
+        " \n",
+        "1.  Provide a centralized feature repository with easy APIs to search & discover features and fetch them for training/serving.\n",
+        " \n",
+        "2.  Simplify deployments of models for Online Prediction, via low latency scalable feature serving.\n",
+        " \n",
+        "3.  Mitigate training serving skew and data leakage by performing point in time lookups to fetch historical data for training.\n",
+        " \n",
         "**Notice that we assume that already know how to set up a Vertex AI Feature store. In case you are not, please check out [this detailed notebook](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/feature_store/gapic-feature-store.ipynb).**\n",
-        "\n",
-        "\n",
-        "### Costs \n",
-        "\n",
+        " \n",
+        " \n",
+        "### Costs\n",
+        " \n",
         "This tutorial uses billable components of Google Cloud:\n",
-        "\n",
+        " \n",
         "* Vertex AI\n",
         "* BigQuery\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."
+        "to generate a cost estimate based on your projected usage.\n"
       ]
     },
     {
@@ -110,7 +110,7 @@
       "source": [
         "### Set up your local development environment\n",
         "\n",
-        "**If you are using Colab or Google Cloud Notebooks**, your environment already meets\n",
+        "**If you are using Colab or Vertex AI Workbench Notebooks**, your environment already meets\n",
         "all the requirements to run this notebook. You can skip this step."
       ]
     },
@@ -159,7 +159,7 @@
       "source": [
         "### Install additional packages\n",
         "\n",
-        "Install additional package dependencies not installed in your notebook environment, such as {XGBoost, AdaNet, or TensorFlow Hub TODO: Replace with relevant packages for the tutorial}. Use the latest major GA version of each package."
+        "Install additional package dependencies not installed in your notebook environment, such as XGBoost. Use the latest major GA version of each package."
       ]
     },
     {
@@ -172,12 +172,15 @@
       "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\")\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\""
       ]
     },
@@ -185,11 +188,11 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "SzEo6DeE2GOP"
+        "id": "_vr6BYED_5my"
       },
       "outputs": [],
       "source": [
-        "! pip3 install {USER_FLAG} --upgrade pip\n",
+        "! pip3 install {USER_FLAG} --upgrade pip -q\n",
         "! pip3 install {USER_FLAG} --upgrade google-cloud-aiplatform==1.11.0 -q --no-warn-conflicts\n",
         "! pip3 install {USER_FLAG} git+https://github.com/googleapis/python-aiplatform.git@main # For features monitoring\n",
         "! pip3 install {USER_FLAG} --upgrade google-cloud-bigquery==2.24.0 -q --no-warn-conflicts\n",
@@ -249,7 +252,7 @@
         "\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 and Compute Engine API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,compute_component). \n",
+        "1. [Enable the APIs](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,notebooks.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",
@@ -307,18 +310,76 @@
       "outputs": [],
       "source": [
         "if PROJECT_ID == \"\" or PROJECT_ID is None:\n",
-        "    PROJECT_ID = \"\"  # @param {type:\"string\"}"
+        "    PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "dEjRdjxBuDsi"
+        "id": "set_gcloud_project_id"
       },
       "outputs": [],
       "source": [
-        "!gcloud config set project $PROJECT_ID #change it"
+        "! gcloud config set project $PROJECT_ID"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "23988890fef6"
+      },
+      "source": [
+        "#### Get your project number (Optional)\n",
+        "\n",
+        "Now that the project ID is set, you get your corresponding project number."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "2d6950574e1d"
+      },
+      "outputs": [],
+      "source": [
+        "shell_output = ! gcloud projects list --filter=\"PROJECT_ID:'{PROJECT_ID}'\" --format='value(PROJECT_NUMBER)'\n",
+        "PROJECT_NUMBER = shell_output[0]\n",
+        "print(\"Project Number:\", PROJECT_NUMBER)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "region"
+      },
+      "source": [
+        "#### Region\n",
+        "\n",
+        "You can also change the `REGION` variable, which is used for operations\n",
+        "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": "jIcZV7-C2RrX"
+      },
+      "outputs": [],
+      "source": [
+        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
+        "\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
       ]
     },
     {
@@ -353,7 +414,7 @@
       "source": [
         "### Authenticate your Google Cloud account\n",
         "\n",
-        "**If you are using Google Cloud Notebooks**, your environment is already\n",
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already\n",
         "authenticated. Skip this step."
       ]
     },
@@ -376,9 +437,13 @@
         "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",
+        "4. In the **Grant this service account access to project** section, click the **Role** drop-down list and add the following roles:\n",
+        "   - BigQuery Admin\n",
+        "   - Storage Admin\n",
+        "   - Storage Object Admin\n",
+        "   - Vertex AI Administrator\n",
+        "   - Vertex AI Feature Store Admin\n",
+        "\n",
         "\n",
         "5. Click *Create*. A JSON file that contains your key downloads to your\n",
         "local environment.\n",
@@ -395,19 +460,19 @@
       },
       "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",
-        "# The Google Cloud Notebook product has specific requirements\n",
-        "IS_GOOGLE_CLOUD_NOTEBOOK = os.path.exists(\"/opt/deeplearning/metadata/env_version\")\n",
+        "import os\n",
+        "import sys\n",
         "\n",
-        "# If on Google Cloud Notebooks, then don't execute this code\n",
-        "if not IS_GOOGLE_CLOUD_NOTEBOOK:\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",
@@ -447,8 +512,8 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_URI = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}\n",
-        "REGION = \"[your-region]\"  # @param {type:\"string\"}"
+        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
+        "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
       ]
     },
     {
@@ -459,11 +524,9 @@
       },
       "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\n",
-        "\n",
-        "if REGION == \"[your-region]\":\n",
-        "    REGION = \"us-central1\""
+        "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}\""
       ]
     },
     {
@@ -486,26 +549,6 @@
         "! gsutil mb -l $REGION -p $PROJECT_ID $BUCKET_URI"
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "994afa65eaa2"
-      },
-      "source": [
-        "Run the following cell to grant access to your Cloud Storage resources from Vertex AI Feature store"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "psP1rPU9TRnX"
-      },
-      "outputs": [],
-      "source": [
-        "! gsutil uniformbucketlevelaccess set on $BUCKET_URI"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -526,6 +569,78 @@
         "! gsutil ls -al $BUCKET_URI"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "set_service_account"
+      },
+      "source": [
+        "#### Service Account (Optional)\n",
+        "\n",
+        "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": "MQVV9haf2Rra"
+      },
+      "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",
+        "    else:  # 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)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "set_service_account:pipelines"
+      },
+      "source": [
+        "#### Set service account access\n",
+        "\n",
+        "Run the following commands to grant your service account access. You only need to run this step once per service account."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "U4UpQThc2Rrb"
+      },
+      "outputs": [],
+      "source": [
+        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectCreator $BUCKET_URI\n",
+        "\n",
+        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectViewer $BUCKET_URI"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -541,13 +656,22 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "G3G2BXqswb_J"
+        "id": "8615339fa4ca"
       },
       "outputs": [],
       "source": [
         "BQ_DATASET = \"Mobile_Gaming\"  # @param {type:\"string\"}\n",
-        "LOCATION = \"US\"\n",
-        "\n",
+        "LOCATION = \"US\""
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "G3G2BXqswb_J"
+      },
+      "outputs": [],
+      "source": [
         "!bq mk --location=$LOCATION --dataset $PROJECT_ID:$BQ_DATASET"
       ]
     },
@@ -600,12 +724,9 @@
       "outputs": [],
       "source": [
         "# Data Engineering and Feature Engineering\n",
-        "TODAY = \"2018-10-03\"\n",
-        "TOMORROW = \"2018-10-04\"\n",
+        "TODAY = \"2022-06-16\"\n",
         "LABEL_TABLE = f\"label_table_{TODAY}\".replace(\"-\", \"\")\n",
-        "FEATURES_TABLE = \"wide_features_table\"  # @param {type:\"string\"}\n",
-        "FEATURES_TABLE_TODAY = f\"wide_features_table_{TODAY}\".replace(\"-\", \"\")\n",
-        "FEATURES_TABLE_TOMORROW = f\"wide_features_table_{TOMORROW}\".replace(\"-\", \"\")\n",
+        "FEATURES_TABLE = f\"wide_features_table_{TODAY}\"  # @param {type:\"string\"}\n",
         "FEATURESTORE_ID = \"mobile_gaming\"  # @param {type:\"string\"}\n",
         "ENTITY_TYPE_ID = \"user\"\n",
         "\n",
@@ -947,13 +1068,37 @@
         "You will cover those steps in details below."
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "init_aip:mbsdk,all"
+      },
+      "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": "poLJ0fV52Rrc"
+      },
+      "outputs": [],
+      "source": [
+        "vertex_ai.init(project=PROJECT_ID, location=REGION, staging_bucket=BUCKET_URI)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
         "id": "4ffd54e97270"
       },
       "source": [
-        "## Initiate clients"
+        "### Initialize BigQuery SDK for Python\n",
+        "\n",
+        "Initialize the BigQuery AI SDK for Python for your project and corresponding bucket."
       ]
     },
     {
@@ -964,55 +1109,53 @@
       },
       "outputs": [],
       "source": [
-        "bq_client = bigquery.Client(project=PROJECT_ID, location=LOCATION)\n",
-        "vertex_ai.init(project=PROJECT_ID, location=REGION, staging_bucket=BUCKET_URI)"
+        "bq_client = bigquery.Client(project=PROJECT_ID, location=LOCATION)"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "zmMWIpCwsET9"
+        "id": "WnUQO2IHC9pZ"
       },
       "source": [
         "## Identify users and build your features\n",
-        "\n",
-        "This section we will static features we want to fetch from Vertex AI Feature Store. In particular, we will cover the following steps:\n",
-        "\n",
+        " \n",
+        "This section we will have static features we want to fetch from Vertex AI Feature Store. In particular, we will cover the following steps:\n",
+        " \n",
         "1. Identify users, process demographic features and process behavioral features within the last 24 hours using **BigQuery**\n",
-        "\n",
+        " \n",
         "2. Set up the feature store\n",
-        "\n",
+        " \n",
         "3. Register features using **Vertex AI Feature Store** and the SDK.\n",
-        "\n",
-        "Below you have a picture that shows the process. \n",
-        "\n",
+        " \n",
+        "Below you have a picture that shows the process.\n",
+        " \n",
         "<img src=\"./assets/feature_store_ingestion_2.png\">\n",
-        "\n",
-        "\n",
-        "\n",
-        "The original dataset contains raw event data we cannot ingest in the feature store as they are. We need to pre-process the raw data in order to get user features. \n",
-        "\n",
-        "**Notice we simulate those transformations in different point of time (today and tomorrow).**\n"
+        " \n",
+        " \n",
+        "The original dataset contains raw event data we cannot ingest in the feature store as they are. We need to pre-process the raw data in order to get user features.\n",
+        " \n",
+        "**Notice we simulate those transformations in different points of time (today and tomorrow).**\n"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "8avYy5QOv02s"
+        "id": "e9zIrwhpDF2q"
       },
       "source": [
         "### Label, Demographic and Behavioral Transformations\n",
-        "\n",
-        "This section is based on the [Churn prediction for game developers using Google Analytics 4 (GA4) and BigQuery ML](https://cloud.google.com/blog/topics/developers-practitioners/churn-prediction-game-developers-using-google-analytics-4-ga4-and-bigquery-ml?utm_source=linkedin&utm_medium=unpaidsoc&utm_campaign=FY21-Q2-Google-Cloud-Tech-Blog&utm_content=google-analytics-4&utm_term=-) blog article by Minhaz Kazi and Polong Lin. \n",
-        "\n",
-        "You will adapt it in order to turn a batch churn prediction (using features within the first 24h user of first engagment) in a real-time churn prediction (using features within the first 24h user of last engagment)."
+        " \n",
+        "This section is based on the [Churn prediction for game developers using Google Analytics 4 (GA4) and BigQuery ML](https://cloud.google.com/blog/topics/developers-practitioners/churn-prediction-game-developers-using-google-analytics-4-ga4-and-bigquery-ml?utm_source=linkedin&utm_medium=unpaidsoc&utm_campaign=FY21-Q2-Google-Cloud-Tech-Blog&utm_content=google-analytics-4&utm_term=-) blog article by Minhaz Kazi and Polong Lin.\n",
+        " \n",
+        "You will adapt it to turn a batch churn prediction (using features within the first 24h user of first engagement) into a real-time churn prediction (using features within the first 6h user of last engagement).\n"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "YO28RAITh6L-"
+        "id": "RQX5m8UiC_px"
       },
       "outputs": [],
       "source": [
@@ -1039,27 +1182,27 @@
         "  SELECT\n",
         "    event_timestamp,\n",
         "    user_pseudo_id,\n",
-        "    SUM(IF(event_name = 'user_engagement', 1, 0)) OVER (PARTITION BY user_pseudo_id ORDER BY event_timestamp ASC RANGE BETWEEN 86400000000 PRECEDING\n",
+        "    SUM(IF(event_name = 'user_engagement', 1, 0)) OVER (PARTITION BY user_pseudo_id ORDER BY event_timestamp ASC RANGE BETWEEN 21600000000 PRECEDING\n",
         "      AND CURRENT ROW ) AS cnt_user_engagement,\n",
-        "    SUM(IF(event_name = 'level_start_quickplay', 1, 0)) OVER (PARTITION BY user_pseudo_id ORDER BY event_timestamp ASC RANGE BETWEEN 86400000000 PRECEDING\n",
+        "    SUM(IF(event_name = 'level_start_quickplay', 1, 0)) OVER (PARTITION BY user_pseudo_id ORDER BY event_timestamp ASC RANGE BETWEEN 21600000000 PRECEDING\n",
         "      AND CURRENT ROW ) AS cnt_level_start_quickplay,\n",
-        "    SUM(IF(event_name = 'level_end_quickplay', 1, 0)) OVER (PARTITION BY user_pseudo_id ORDER BY event_timestamp ASC RANGE BETWEEN 86400000000 PRECEDING\n",
+        "    SUM(IF(event_name = 'level_end_quickplay', 1, 0)) OVER (PARTITION BY user_pseudo_id ORDER BY event_timestamp ASC RANGE BETWEEN 21600000000 PRECEDING\n",
         "      AND CURRENT ROW ) AS cnt_level_end_quickplay,\n",
-        "    SUM(IF(event_name = 'level_complete_quickplay', 1, 0)) OVER (PARTITION BY user_pseudo_id ORDER BY event_timestamp ASC RANGE BETWEEN 86400000000 PRECEDING\n",
+        "    SUM(IF(event_name = 'level_complete_quickplay', 1, 0)) OVER (PARTITION BY user_pseudo_id ORDER BY event_timestamp ASC RANGE BETWEEN 21600000000 PRECEDING\n",
         "      AND CURRENT ROW ) AS cnt_level_complete_quickplay,\n",
-        "    SUM(IF(event_name = 'level_reset_quickplay', 1, 0)) OVER (PARTITION BY user_pseudo_id ORDER BY event_timestamp ASC RANGE BETWEEN 86400000000 PRECEDING\n",
+        "    SUM(IF(event_name = 'level_reset_quickplay', 1, 0)) OVER (PARTITION BY user_pseudo_id ORDER BY event_timestamp ASC RANGE BETWEEN 21600000000 PRECEDING\n",
         "      AND CURRENT ROW ) AS cnt_level_reset_quickplay,\n",
-        "    SUM(IF(event_name = 'post_score', 1, 0)) OVER (PARTITION BY user_pseudo_id ORDER BY event_timestamp ASC RANGE BETWEEN 86400000000 PRECEDING\n",
+        "    SUM(IF(event_name = 'post_score', 1, 0)) OVER (PARTITION BY user_pseudo_id ORDER BY event_timestamp ASC RANGE BETWEEN 21600000000 PRECEDING\n",
         "      AND CURRENT ROW ) AS cnt_post_score,\n",
-        "    SUM(IF(event_name = 'spend_virtual_currency', 1, 0)) OVER (PARTITION BY user_pseudo_id ORDER BY event_timestamp ASC RANGE BETWEEN 86400000000 PRECEDING\n",
+        "    SUM(IF(event_name = 'spend_virtual_currency', 1, 0)) OVER (PARTITION BY user_pseudo_id ORDER BY event_timestamp ASC RANGE BETWEEN 21600000000 PRECEDING\n",
         "      AND CURRENT ROW ) AS cnt_spend_virtual_currency,\n",
-        "    SUM(IF(event_name = 'ad_reward', 1, 0)) OVER (PARTITION BY user_pseudo_id ORDER BY event_timestamp ASC RANGE BETWEEN 86400000000 PRECEDING\n",
+        "    SUM(IF(event_name = 'ad_reward', 1, 0)) OVER (PARTITION BY user_pseudo_id ORDER BY event_timestamp ASC RANGE BETWEEN 21600000000 PRECEDING\n",
         "      AND CURRENT ROW ) AS cnt_ad_reward,\n",
-        "    SUM(IF(event_name = 'challenge_a_friend', 1, 0)) OVER (PARTITION BY user_pseudo_id ORDER BY event_timestamp ASC RANGE BETWEEN 86400000000 PRECEDING\n",
+        "    SUM(IF(event_name = 'challenge_a_friend', 1, 0)) OVER (PARTITION BY user_pseudo_id ORDER BY event_timestamp ASC RANGE BETWEEN 21600000000 PRECEDING\n",
         "      AND CURRENT ROW ) AS cnt_challenge_a_friend,\n",
-        "    SUM(IF(event_name = 'completed_5_levels', 1, 0)) OVER (PARTITION BY user_pseudo_id ORDER BY event_timestamp ASC RANGE BETWEEN 86400000000 PRECEDING\n",
+        "    SUM(IF(event_name = 'completed_5_levels', 1, 0)) OVER (PARTITION BY user_pseudo_id ORDER BY event_timestamp ASC RANGE BETWEEN 21600000000 PRECEDING\n",
         "      AND CURRENT ROW ) AS cnt_completed_5_levels,\n",
-        "    SUM(IF(event_name = 'use_extra_steps', 1, 0)) OVER (PARTITION BY user_pseudo_id ORDER BY event_timestamp ASC RANGE BETWEEN 86400000000 PRECEDING\n",
+        "    SUM(IF(event_name = 'use_extra_steps', 1, 0)) OVER (PARTITION BY user_pseudo_id ORDER BY event_timestamp ASC RANGE BETWEEN 21600000000 PRECEDING\n",
         "      AND CURRENT ROW ) AS cnt_use_extra_steps,\n",
         "  FROM (\n",
         "    SELECT\n",
@@ -1071,7 +1214,7 @@
         "\n",
         "SELECT\n",
         "    -- PARSE_TIMESTAMP('%Y-%m-%d %H:%M:%S', CONCAT('{TODAY}', ' ', STRING(TIME_TRUNC(CURRENT_TIME(), SECOND))), 'UTC') as timestamp,\n",
-        "    PARSE_TIMESTAMP('%Y-%m-%d %H:%M:%S', FORMAT_TIMESTAMP('%Y-%m-%d %H:%M:%S', TIMESTAMP_MICROS(beh.event_timestamp))) AS timestamp,\n",
+        "    TIMESTAMP_ADD(PARSE_TIMESTAMP('%Y-%m-%d %H:%M:%S', FORMAT_TIMESTAMP('%Y-%m-%d %H:%M:%S', TIMESTAMP_MICROS(beh.event_timestamp))), INTERVAL 1351 DAY) AS timestamp,\n",
         "    dem.*,\n",
         "    CAST(IFNULL(beh.cnt_user_engagement, 0) AS FLOAT64)  AS cnt_user_engagement,\n",
         "    CAST(IFNULL(beh.cnt_level_start_quickplay, 0) AS FLOAT64) AS cnt_level_start_quickplay,\n",
@@ -1097,7 +1240,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "Z6CjIOmDsET-"
+        "id": "oGYxLCSnD068"
       },
       "outputs": [],
       "source": [
@@ -1107,31 +1250,31 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "Lx__2-assET-"
+        "id": "xQLIlsTCD_nk"
       },
       "source": [
         "## Create a Vertex AI Feature store and ingest your features\n",
-        "\n",
-        "Now you have the wide table of features. It is time to ingest them into the feature store. \n",
-        "\n",
+        " \n",
+        "Now you have a wide table of features. It is time to ingest them into the feature store.\n",
+        " \n",
         "Before to moving on, you may have a question: **Why do I need a feature store**\n",
         "in this scenario at that point?\n",
-        "\n",
-        "One of the reason would be to make those features accessable across team by calculating once and reuse them many times. And in order to make it possible you need also be able to monitor those features over time to guarantee freshness and in case have a new feature engineerign run to refresh them. \n",
-        "\n",
-        "If it is not your case, I will give even more reasons about why you should consider feature store in the following sections. Just keep following me for now.\n",
-        "\n",
-        "One of the most important thing is related to its data model. As you can see in the picture below, Vertex AI Feature Store organizes resources hierarchically in the following order: `Featurestore -> EntityType -> Feature`. You must create these resources before you can ingest data into Vertex AI Feature Store.\n",
-        "\n",
+        " \n",
+        "One of the reasons would be to make those features accessible across teams by calculating once and reuse them many times. And in order to make it possible you need also be able to monitor those features over time to guarantee freshness and in case have a new feature engineering run to refresh them.\n",
+        " \n",
+        "If it is not your case, I will give even more reasons about why you should consider a feature store in the following sections. Just keep following me for now.\n",
+        " \n",
+        "One of the most important things is related to its data model. As you can see in the picture below, Vertex AI Feature Store organizes resources hierarchically in the following order: `Featurestore -> EntityType -> Feature`. You must create these resources before you can ingest data into Vertex AI Feature Store.\n",
+        " \n",
         "<img src=\"./assets/feature_store_data_model_3.png\">\n",
-        "\n",
-        "In our case we are going to create **mobile_gaming** featurestore resource containing **user** entity type and all its associated **features** such as country or the number of times a user challenged a friend (cnt_challenge_a_friend)."
+        " \n",
+        "In our case we are going to create **mobile_gaming** featurestore resource containing **user** entity type and all its associated **features** such as country or the number of times a user challenged a friend (cnt_challenge_a_friend).\n"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "8dNlxda2sET_"
+        "id": "VR7BJEozED_Q"
       },
       "source": [
         "### Create featurestore, ```mobile_gaming```\n",
@@ -1143,7 +1286,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "t2en8I7TSe4b"
+        "id": "vUFqtYU-EDTR"
       },
       "outputs": [],
       "source": [
@@ -1164,7 +1307,7 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "rN-vlvPUsET_"
+        "id": "mUlCwfdpEHJG"
       },
       "source": [
         "### Create the ```User``` entity type and its features\n",
@@ -1176,7 +1319,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "CbZ2RQ5XbuRq"
+        "id": "PnCU1wBND3W7"
       },
       "outputs": [],
       "source": [
@@ -1194,7 +1337,7 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "B2PIAprPmnhB"
+        "id": "bT9LXzu1EOvW"
       },
       "source": [
         "### Set Feature Monitoring\n",
@@ -1208,7 +1351,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "N6im2c3ymiwC"
+        "id": "8WBlYUkOERaI"
       },
       "outputs": [],
       "source": [
@@ -1231,7 +1374,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "gp9xaLQXn0CS"
+        "id": "92X4-7PFETj5"
       },
       "outputs": [],
       "source": [
@@ -1254,18 +1397,18 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "ustwKOMle8Qp"
+        "id": "hxAuZjt3EWFo"
       },
       "source": [
         "### Create features\n",
         "\n",
-        "In order to ingest features, you need to provide feature configuration and create them as featurestore resources.\n"
+        "In order to ingest features, you need to provide feature configuration and create them as featurestore resources."
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "ijeZCTKIfCRL"
+        "id": "hRXO2I5VEYwt"
       },
       "source": [
         "#### Create Feature configuration\n",
@@ -1278,7 +1421,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "vX_uYmjUgd9x"
+        "id": "K26NEYZIEbvE"
       },
       "outputs": [],
       "source": [
@@ -1359,7 +1502,7 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "ErkruXPJkPuy"
+        "id": "FjzMd1XbEfdo"
       },
       "source": [
         "#### Create features using `batch_create_features` method\n",
@@ -1371,7 +1514,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "ZsCAO_IfsEUC"
+        "id": "nqlgCDI9pbCD"
       },
       "outputs": [],
       "source": [
@@ -1388,19 +1531,19 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "9WisJk18qqgs"
+        "id": "7zpFV7wAppkC"
       },
       "source": [
         "### Search features\n",
         "\n",
-        "Vertex AI Feature store supports serching capabilities. Below you have a simple example that show how to filter a feature based on its name. "
+        "Vertex AI Feature store supports searching capabilities. Below you have a simple example that shows how to filter a feature based on its name. "
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "JzqyarMZqvZS"
+        "id": "BJXYLLOfppCL"
       },
       "outputs": [],
       "source": [
@@ -1412,7 +1555,7 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "ugtBfW5gsEUD"
+        "id": "is9C_6-QpxG3"
       },
       "source": [
         "## Ingest features \n",
@@ -1447,7 +1590,7 @@
         "        entity_id_field=ENTITY_ID_FIELD,\n",
         "        disable_online_serving=False,\n",
         "        worker_count=10,\n",
-        "        sync=True,\n",
+        "        sync=False,\n",
         "    )\n",
         "except RuntimeError as error:\n",
         "    print(error)"
@@ -1456,7 +1599,7 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "3Yv8MenWXrRX"
+        "id": "8lCMpDPGp-oQ"
       },
       "source": [
         "# Train and deploy a real-time churn ML model using Vertex AI Training and Endpoints\n",
@@ -1467,34 +1610,34 @@
         "\n",
         "<img src=\"./assets/train_model_4.png\">\n",
         "\n",
-        "Let's dive into each step of this process.\n"
+        "Let's dive into each step of this process."
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "saZZ3zWKX1YK"
+        "id": "VMrvnuyjqGfY"
       },
       "source": [
-        "## Fetch training data with point-in-time query using BigQuery and Vertex AI Feature store  \n",
-        "\n",
-        "As we mentioned above, in real time churn prediction, it is so important defining the label you want to predict with your model. \n",
-        "\n",
-        "Let's assume that you decide to predict the churn probability over the last 24 hr. So now you have your label. Next step is to define your training sample. But let's think about that for a second. \n",
-        "\n",
-        "In that churn real time system, you have a high volume of transactions you could use to calculate those features which keep floating and are collected constantly over time. It implies that you always get fresh data to reconstruct features. And depending on when you decide to calculate one feature or another you can end up with a set of features that are not aligned in time. \n",
-        "\n",
+        "## Fetch training data with point-in-time query using BigQuery and Vertex AI Feature store \n",
+        " \n",
+        "As we mentioned above, in real time churn prediction, it is so important defining the label you want to predict with your model.\n",
+        " \n",
+        "Let's assume that you decide to predict the churn probability over the next hour. So now you have your label. Next step is to define your training sample. But let's think about that for a second.\n",
+        " \n",
+        "In that churn real time system, you have a high volume of transactions you could use to calculate those features which keep floating and are collected constantly over time. It implies that you always get fresh data to reconstruct features. And depending on when you decide to calculate one feature or another you can end up with a set of features that are not aligned in time.\n",
+        " \n",
         "When you have labels available, it would be incredibly difficult to say which set of features contains the most up to date historical information associated with the label you want to predict. And, when you are not able to guarantee that, the performance of your model would be badly affected because you serve no representative features of the data and the label from the field when it goes live. So you need a way to get the most updated features you calculated over time before the label becomes available in order to avoid this informational skew.\n",
-        "\n",
-        "**With the Vertex AI Feature store, you can fetch feature values corresponding to a particular timestamp thanks to point-in-time lookup capability.** In our case, it would be the timestamp associated to the label you want to predict with your model. In this way, you will avoid data leakage and you will get the most updated features to train your model. \n",
-        "\n",
-        "Let's see how to do that. \n"
+        " \n",
+        "**With the Vertex AI Feature store, you can fetch feature values corresponding to a particular timestamp thanks to point-in-time lookup capability.** In our case, it would be the timestamp associated with the label you want to predict with your model. In this way, you will avoid data leakage and you will get the most updated features to train your model.\n",
+        " \n",
+        "Let's see how to do that.\n"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "YHNbIHqFcQiM"
+        "id": "RE_Pvmu-qdDt"
       },
       "source": [
         "### Define query for reading instances at a specific point in time\n",
@@ -1506,7 +1649,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "DGUm0bYqhVV4"
+        "id": "bUDVw7l-qF2x"
       },
       "outputs": [],
       "source": [
@@ -1518,13 +1661,13 @@
         "  # get training threshold ----------------------------------------------------------------------------------\n",
         "  get_training_threshold AS (\n",
         "  SELECT\n",
-        "    (MAX(event_timestamp) - 86400000000) AS training_thrs\n",
+        "    (MAX(event_timestamp) - 10800000000) AS training_thrs\n",
         "  FROM\n",
         "    `firebase-public-project.analytics_153293282.events_*`\n",
         "  WHERE\n",
         "    event_name=\"user_engagement\"\n",
         "    AND\n",
-        "    PARSE_TIMESTAMP('%Y-%m-%d %H:%M:%S', FORMAT_TIMESTAMP('%Y-%m-%d %H:%M:%S', TIMESTAMP_MICROS(event_timestamp))) < '{TODAY}'),\n",
+        "    TIMESTAMP_ADD(PARSE_TIMESTAMP('%Y-%m-%d %H:%M:%S', FORMAT_TIMESTAMP('%Y-%m-%d %H:%M:%S', TIMESTAMP_MICROS(event_timestamp))), INTERVAL 1351 DAY) < '{TODAY}'),\n",
         "\n",
         "  # query to create label -----------------------------------------------------------------------------------\n",
         "  get_label AS (\n",
@@ -1549,7 +1692,7 @@
         "    WHERE\n",
         "      event_name=\"user_engagement\"\n",
         "    AND\n",
-        "    PARSE_TIMESTAMP('%Y-%m-%d %H:%M:%S', FORMAT_TIMESTAMP('%Y-%m-%d %H:%M:%S', TIMESTAMP_MICROS(event_timestamp))) < '{TODAY}'\n",
+        "    TIMESTAMP_ADD(PARSE_TIMESTAMP('%Y-%m-%d %H:%M:%S', FORMAT_TIMESTAMP('%Y-%m-%d %H:%M:%S', TIMESTAMP_MICROS(event_timestamp))), INTERVAL 1351 DAY) < '{TODAY}'\n",
         "    GROUP BY\n",
         "      user_pseudo_id )\n",
         "  GROUP BY\n",
@@ -1669,7 +1812,7 @@
       "source": [
         "!mkdir -m 777 -p trainer data/ingest data/raw model config\n",
         "!gsutil -m cp -r $GCS_DESTINATION_OUTPUT_URI/*.csv data/ingest\n",
-        "!head -n 1000 data/ingest/*.csv > data/raw/sample.csv"
+        "!head -n 2000 data/ingest/*.csv > data/raw/sample.csv"
       ]
     },
     {
@@ -2071,7 +2214,7 @@
       },
       "outputs": [],
       "source": [
-        "TRAIN_JOB_RESOURCE_NAME = \"\"  # @param {type:\"string\"}"
+        "TRAIN_JOB_RESOURCE_NAME = \"[your-train-job-resource-name]\"  # @param {type:\"string\"}"
       ]
     },
     {
@@ -2166,32 +2309,32 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "7c9330928aa1"
+        "id": "1TNzL_EGrVUm"
       },
       "source": [
         "# Serve ML features at scale with low latency\n",
-        "\n",
-        "At that time, you are ready **to deploy our simple model which would requires fetching preprocessed attributes as input features in real time**. \n",
-        "\n",
+        " \n",
+        "At that time, you are ready **to deploy our simple model which would requires fetching preprocessed attributes as input features in real time**.\n",
+        " \n",
         "Below you can see how it works\n",
-        "\n",
-        "<img src=\"./assets/online_serving_5.png\" width=\"600\">\n",
-        "\n",
-        "But think about those features for a second. \n",
-        "\n",
-        "Your behavioral features used to trained your model, they cannot be computed when you are going to serve the model online. \n",
-        "\n",
-        "How could you compute the number of time a user challenged a friend withing the last 24 hours on the fly?\n",
-        "\n",
-        "You simply can't do that. You need to be computed this feature on the server side and serve it with low latency. And becuase Bigquery is not optimized for those read operations, we need a different service that allows singleton lookup where the result is a single row with many columns.\n",
-        "\n",
-        "Also, even if it was not the case, when you deploy a model that requires preprocessing your data, you need to be sure to reproduce the same preprocessing steps you had when you trained it. If you are not able to do that a skew between training and serving data would happen and it will affect badly your model performance (and in the worst scenario break your serving system). \n",
-        "\n",
-        "You need a way to mitigate that in a way you don't need to implement those preprocessing steps online but just serve the same aggregated features you already have for training to generate online prediction. \n",
-        "\n",
-        "These are other valuable reasons to introduce Vertex AI Feature Store. With it, you have a service which helps you to serve feature at scale with low latency as they were available at training time mitigating in that way possible training-serving skew.\n",
-        "\n",
-        "Now that you know **why you need a feature store**, let's closing this journey by deploying your model and use feature store to retrieve features online, pass them to endpoint and generate predictions.\n"
+        " \n",
+        "<center><img src=\"./assets/online_serving_5.png\" width=\"800\"/></center>\n",
+        " \n",
+        "But think about those features for a second.\n",
+        " \n",
+        "Your behavioral features used to train your model, they cannot be computed when you are going to serve the model online.\n",
+        " \n",
+        "How could you compute the number of times a user challenged a friend within the last 24 hours on the fly?\n",
+        " \n",
+        "You need to be computed this feature on the server side and serve it with low latency. And because Bigquery is not optimized for those read operations, we need a different service that allows singleton lookup where the result is a single row with many columns.\n",
+        " \n",
+        "Also, even if it was not the case, when you deploy a model that requires preprocessing your data, you need to be sure to reproduce the same preprocessing steps you had when you trained it. If you are not able to do that a skew between training and serving data would happen and it will badly affect your model performance (and in the worst scenario break your serving system).\n",
+        " \n",
+        "You need a way to mitigate that in a way you don't need to implement those preprocessing steps online but just serve the same aggregated features you already have for training to generate online prediction.\n",
+        " \n",
+        "These are other valuable reasons to introduce Vertex AI Feature Store. With it, you have a service which helps you to serve features at scale with low latency as they were available at training time mitigating in that way possible training-serving skew.\n",
+        " \n",
+        "Now that you know **why you need a feature store**, let's conclude this journey by deploying your model using a feature store to retrieve features online, pass them to the endpoint and generate predictions.\n"
       ]
     },
     {
@@ -2221,13 +2364,13 @@
       },
       "outputs": [],
       "source": [
-        "simulate_prediction(endpoint=endpoint, n_requests=1000, latency=1)"
+        "simulate_prediction(endpoint=endpoint, n_requests=10, latency=1)"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "TpV-iwP9qw9c"
+        "id": "8d3S1d1urZOy"
       },
       "source": [
         "## Cleaning up\n",
@@ -2267,11 +2410,12 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "sx_vKniMq9ZX"
+        "id": "FMXT2akXrZOy"
       },
       "outputs": [],
       "source": [
         "# Delete bucket\n",
+        "delete_bucket = False\n",
         "if (delete_bucket or os.getenv(\"IS_TESTING\")) and \"BUCKET_URI\" in globals():\n",
         "    ! gsutil -m rm -r $BUCKET_URI"
       ]

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_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

@@ -34,17 +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",
-        "    <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",
+        "    <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",
@@ -174,12 +173,15 @@
       "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",
@@ -360,7 +362,7 @@
       "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",
@@ -387,20 +389,19 @@
       },
       "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",
-        "# The Google Cloud Notebook product has specific requirements\n",
-        "IS_GOOGLE_CLOUD_NOTEBOOK = os.path.exists(\"/opt/deeplearning/metadata/env_version\")\n",
+        "import os\n",
+        "import sys\n",
         "\n",
-        "# If on Google Cloud Notebooks, then don't execute this code\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
         "IS_COLAB = False\n",
-        "if not IS_GOOGLE_CLOUD_NOTEBOOK:\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",
@@ -1131,7 +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)"
       ]

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",
@@ -152,12 +158,15 @@
       "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 -U tensorflow==2.5 $USER_FLAG -q\n",
@@ -338,7 +347,7 @@
       "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",
@@ -365,20 +374,19 @@
       },
       "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",
-        "# The Google Cloud Notebook product has specific requirements\n",
-        "IS_GOOGLE_CLOUD_NOTEBOOK = os.path.exists(\"/opt/deeplearning/metadata/env_version\")\n",
+        "import os\n",
+        "import sys\n",
         "\n",
-        "# If on Google Cloud Notebooks, then don't execute this code\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
         "IS_COLAB = False\n",
-        "if not IS_GOOGLE_CLOUD_NOTEBOOK:\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",

notebooks/community/ml_ops/stage1/get_started_vertex_datasets.ipynb

@@ -44,7 +44,7 @@
         "    </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_vertex_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_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",
@@ -157,7 +157,7 @@
       "source": [
         "## Installations\n",
         "\n",
-        "Install *one time* the packages for executing the MLOps notebooks."
+        "Install the packages required for executing this notebook."
       ]
     },
     {
@@ -170,22 +170,25 @@
       "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 -U tensorflow $USER_FLAG\n",
-        "! pip3 install -U tensorflow-data-validation $USER_FLAG\n",
-        "! pip3 install -U tensorflow-transform $USER_FLAG\n",
-        "! pip3 install -U tensorflow-io $USER_FLAG\n",
-        "! pip3 install --upgrade google-cloud-aiplatform $USER_FLAG\n",
-        "! pip3 install --upgrade google-cloud-bigquery $USER_FLAG\n",
-        "! pip3 install -U tensorflow-io==0.18 $USER_FLAG\n",
-        "! pip3 install --upgrade future $USER_FLAG"
+        "! 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"
       ]
     },
     {
@@ -231,7 +234,7 @@
         "\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 need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
         "\n",
@@ -292,6 +295,17 @@
         "    PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
       ]
     },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "c021ca495967"
+      },
+      "outputs": [],
+      "source": [
+        "! gcloud config set project $PROJECT_ID"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -358,7 +372,7 @@
       "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",
@@ -393,11 +407,12 @@
         "import os\n",
         "import sys\n",
         "\n",
-        "# If on Google Cloud Notebook, then don't execute this code\n",
-        "IS_COLAB = False\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",
@@ -409,17 +424,6 @@
         "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
       ]
     },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "c021ca495967"
-      },
-      "outputs": [],
-      "source": [
-        "! gcloud config set project $PROJECT_ID"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -553,7 +557,7 @@
       },
       "outputs": [],
       "source": [
-        "aip.init(project=PROJECT_ID, location=REGION)"
+        "aip.init(project=PROJECT_ID, location=REGION, staging_bucket=BUCKET_URI)"
       ]
     },
     {
@@ -607,26 +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",
@@ -641,6 +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,
@@ -658,24 +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",
@@ -689,6 +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,
@@ -706,24 +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",
@@ -738,6 +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,
@@ -755,6 +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,
@@ -763,27 +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\""
       ]
     },
     {
@@ -801,15 +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)"
       ]
     },
     {
@@ -818,7 +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",
@@ -829,6 +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,
@@ -1274,7 +1378,7 @@
         "import os\n",
         "import sys\n",
         "\n",
-        "# If on Google Cloud Notebook, then don't execute this code\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",
@@ -1615,11 +1719,15 @@
       },
       "outputs": [],
       "source": [
+        "delete_bucket = False\n",
+        "\n",
         "# Delete the dataset using the Vertex dataset object\n",
-        "dataset.delete()\n",
+        "datasets = aip.TabularDataset.list(filter=f'display_name=\"example_{TIMESTAMP}\"')\n",
+        "for dataset in datasets:\n",
+        "    dataset.delete()\n",
         "\n",
         "# Delete the bucket\n",
-        "if os.getenv(\"IS_TESTING\"):\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

@@ -44,7 +44,7 @@
         "    </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_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",
@@ -145,17 +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 $USER_FLAG"
+        "! pip3 install --upgrade google-cloud-aiplatform $USER_FLAG -q\n",
+        "! pip3 install --upgrade google-cloud-storage $USER_FLAG -q"
       ]
     },
     {
@@ -207,7 +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 AI 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",
@@ -359,7 +362,7 @@
       "source": [
         "### Authenticate your Google Cloud account\n",
         "\n",
-        "**If you are using Google Cloud Notebooks**, your environment is already\n",
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already\n",
         "authenticated. Skip this step."
       ]
     },
@@ -401,20 +404,19 @@
       },
       "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",
-        "# The Google Cloud Notebook product has specific requirements\n",
-        "IS_GOOGLE_CLOUD_NOTEBOOK = os.path.exists(\"/opt/deeplearning/metadata/env_version\")\n",
+        "import os\n",
+        "import sys\n",
         "\n",
-        "# If on Google Cloud Notebooks, then don't execute this code\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
         "IS_COLAB = False\n",
-        "if not IS_GOOGLE_CLOUD_NOTEBOOK:\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",

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",
@@ -133,6 +139,19 @@
       },
       "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 = True\n",
         "if ONCE_ONLY:\n",
         "    ! pip3 install -U tensorflow==2.5 $USER_FLAG\n",
@@ -318,7 +337,7 @@
       "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",
@@ -345,20 +364,19 @@
       },
       "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",
-        "# The Google Cloud Notebook product has specific requirements\n",
-        "IS_GOOGLE_CLOUD_NOTEBOOK = os.path.exists(\"/opt/deeplearning/metadata/env_version\")\n",
+        "import os\n",
+        "import sys\n",
         "\n",
-        "# If on Google Cloud Notebooks, then don't execute this code\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
         "IS_COLAB = False\n",
-        "if not IS_GOOGLE_CLOUD_NOTEBOOK:\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",

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)
 
 ```
@@ -205,19 +235,6 @@ The steps performed include:
 ```
 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 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.

notebooks/community/ml_ops/stage2/get_started_automl_training.ipynb

@@ -40,11 +40,11 @@
         "  </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_automl_training.ipynb\">\n",
-        "        <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\\\" alt=\"Colab logo\"> Run in Colab\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_automl_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/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",
@@ -187,7 +187,7 @@
         "import os\n",
         "\n",
         "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\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",

notebooks/community/ml_ops/stage2/get_started_bqml_training.ipynb

@@ -44,7 +44,7 @@
         "        </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",
@@ -134,7 +134,7 @@
         "import os\n",
         "\n",
         "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\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",
         "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
@@ -442,6 +442,54 @@
         "! 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)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -730,32 +778,6 @@
         "print(\"{} created in {}\".format(tblname, job.ended - job.started))"
       ]
     },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "3b3aa4481cd7"
-      },
-      "outputs": [],
-      "source": [
-        "MODEL_QUERY = f\"\"\"\n",
-        "DROP MODEL `{BQ_DATASET_NAME}.{MODEL_NAME}`\n",
-        "\"\"\"\n",
-        "\n",
-        "job = bqclient.query(MODEL_QUERY)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "ef9e14b91475"
-      },
-      "outputs": [],
-      "source": [
-        "job"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -1185,24 +1207,21 @@
         "\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."
+        "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": "0472e888105e"
+        "id": "29229f72d13d"
       },
       "outputs": [],
       "source": [
         "! gcloud projects add-iam-policy-binding $PROJECT_ID \\\n",
-        "      --member='serviceAccount:cloud-dataengine@system.gserviceaccount.com' \\\n",
-        "      --role='roles/aiplatform.admin'\n",
-        "\n",
-        "! gcloud projects add-iam-policy-binding $PROJECT_ID \\\n",
-        "      --member='user:cloud-dataengine@prod.google.com' \\\n",
-        "      --role='roles/aiplatform.admin'"
+        "    --member=serviceAccount:$SERVICE_ACCOUNT --role=roles/aiplatform.admin --condition=None"
       ]
     },
     {
@@ -1283,6 +1302,20 @@
         "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": {

notebooks/community/ml_ops/stage2/get_started_vertex_distributed_training.ipynb

@@ -33,7 +33,7 @@
         "\n",
         "<table align=\"left\">\n",
         "      <td>\n",
-        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/master/notebooks/community/ml_ops/stage2/get_started_vertex_distributed_training.ipynb\">\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",
@@ -44,7 +44,7 @@
         "    </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_distributed_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/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",
@@ -160,7 +160,7 @@
         "import os\n",
         "\n",
         "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\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",

notebooks/community/ml_ops/stage2/get_started_vertex_experiments.ipynb

@@ -40,11 +40,11 @@
         "  </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",
+        "        <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",
@@ -143,7 +143,7 @@
         "import os\n",
         "\n",
         "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\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",

notebooks/community/ml_ops/stage2/get_started_vertex_feature_store.ipynb

@@ -41,12 +41,12 @@
         "    \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_feature_store.ipynb\">\n",
-        "        <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\\\" alt=\"Colab logo\"> Run in Colab\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://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_vertex_feature_store.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_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",
@@ -145,7 +145,7 @@
         "import os\n",
         "\n",
         "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\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",
@@ -188,6 +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": {
@@ -338,12 +362,11 @@
         "import sys\n",
         "\n",
         "# If on Vertex AI Workbench, then don't execute this code\n",
-        "IS_COLAB = False\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",
@@ -466,7 +489,7 @@
       "outputs": [],
       "source": [
         "# Represents featurestore resource path.\n",
-        "FEATURESTORE_NAME = \"movies\"\n",
+        "FEATURESTORE_NAME = \"movies_\" + TIMESTAMP\n",
         "\n",
         "featurestore = aiplatform.Featurestore.create(\n",
         "    featurestore_id=FEATURESTORE_NAME,\n",

notebooks/community/ml_ops/stage2/get_started_vertex_tensorboard.ipynb

@@ -44,7 +44,7 @@
         "    </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",
@@ -194,7 +194,7 @@
         "import os\n",
         "\n",
         "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\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",
@@ -253,7 +253,7 @@
         "\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",

notebooks/community/ml_ops/stage2/get_started_vertex_training.ipynb

@@ -39,17 +39,16 @@
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samplestree/master/notebooks/community/ml_ops/stage2/get_started_vertex_training.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",
+        "        <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://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/master/notebooks/community/ml_ops/stage2/get_started_vertex_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/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",
+        "  </td>\n",
         "</table>\n",
         "<br/><br/><br/>"
       ]
@@ -148,7 +147,7 @@
         "import os\n",
         "\n",
         "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\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",
@@ -208,7 +207,7 @@
         "\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",

notebooks/community/ml_ops/stage2/get_started_vertex_training_pytorch.ipynb

@@ -44,7 +44,7 @@
         "    </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",
@@ -191,7 +191,7 @@
         "import os\n",
         "\n",
         "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\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",
@@ -1373,8 +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

@@ -33,7 +33,7 @@
         "\n",
         "<table align=\"left\">\n",
         "  <td>\n",
-        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/master/notebooks/community/ml_ops/stage2/get_started_vertex_training_sklearn.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_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",
@@ -44,15 +44,12 @@
         "    </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/>"
       ]
     },
@@ -186,7 +183,7 @@
         "import os\n",
         "\n",
         "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\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",
@@ -244,7 +241,7 @@
         "\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",
@@ -1179,7 +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

@@ -45,7 +45,7 @@
         "    </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_xgboost.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_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",
@@ -136,7 +136,7 @@
         "import os\n",
         "\n",
         "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\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",
@@ -149,6 +149,32 @@
         "! 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."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -1032,7 +1058,9 @@
       },
       "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_vizier.ipynb

@@ -40,11 +40,11 @@
         "  </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_vizier.ipynb\">\n",
-        "        <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\\\" alt=\"Colab logo\"> Run in Colab\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_vizier.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_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",
@@ -156,7 +156,7 @@
         "import os\n",
         "\n",
         "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\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",
@@ -198,6 +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": {
@@ -1657,6 +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

@@ -38,7 +38,12 @@
         "    </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/notebook_template.ipynb\">\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",
@@ -134,7 +139,7 @@
         "import os\n",
         "\n",
         "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\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",
@@ -200,7 +205,7 @@
         "\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",

notebooks/community/ml_ops/stage2/get_started_with_tabnet.ipynb

@@ -34,18 +34,18 @@
         "<table align=\"left\">\n",
         "\n",
         "  <td>\n",
-        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/master/notebooks/community/ml_ops/stage2/get_started_with_tabnet.ipynb\">\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_with_tabnet.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-samplestree/master/notebooks/community/ml_ops/stage2/get_started_with_tabnet.ipynb\">\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samplestree/main/notebooks/community/ml_ops/stage2/get_started_with_tabnet.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/master/notebooks/community/ml_ops/stage2/get_started_with_tabnet.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_with_tabnet.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",
@@ -133,7 +133,7 @@
         "import os\n",
         "\n",
         "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\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",
@@ -198,7 +198,7 @@
         "\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",
@@ -488,8 +488,6 @@
       "outputs": [],
       "source": [
         "import os\n",
-        "import re\n",
-        "import time\n",
         "from datetime import datetime\n",
         "\n",
         "import google.cloud.aiplatform as aip\n",

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",
@@ -144,7 +145,7 @@
         "import os\n",
         "\n",
         "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\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",
@@ -228,7 +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",
@@ -1396,7 +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/get_started_with_visionapi_and_automl.ipynb

@@ -56,7 +56,7 @@
         "    </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/tree/master/notebooks/community/ml_ops/stage2/get_started_with_visionapi_and_automl.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_with_visionapi_and_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",
@@ -84,11 +84,11 @@
       "source": [
         "### Dataset\n",
         "\n",
-        "The dataset used for this tutorial is the [Patent PDF Samples with Extracted Structured Data](https://pantheon.corp.google.com/marketplace/details/global-patents/labeled-patents?project=kudos-333820) from Google Public Data Sets. \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 Google 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 on `BigQuery`."
+        "The data is published as a [public dataset](https://cloud.google.com/bigquery/public-data) on `BigQuery`."
       ]
     },
     {
@@ -103,11 +103,11 @@
         "\n",
         "Using existing training data that have been previously annotated can be very useful in training a model, as it allows you to use a larger data set with minimal resources.\n",
         "\n",
-        "This tutorial uses the following Google Cloud ML services:\n",
+        "This tutorial uses the following Google Cloud services:\n",
         "\n",
-        "- `Vertex AI AutoML`\n",
         "- `BigQuery`\n",
         "- `Vision AI`\n",
+        "- `Vertex AI AutoML`\n",
         "\n",
         "The steps performed include:\n",
         "\n",
@@ -132,12 +132,12 @@
         "This tutorial uses billable components of Google Cloud:\n",
         "\n",
         "* BigQuery\n",
-        "* Vision AI\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 AI pricing](https://cloud.google.com/vision/pricing), [BigQuery pricing](https://cloud.google.com/bigquery/pricing), [Cloud Storage\n",
+        "pricing](https://cloud.google.com/vertex-ai/pricing), [Vision API pricing](https://cloud.google.com/vision/pricing), [BigQuery pricing](https://cloud.google.com/bigquery/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."
@@ -156,7 +156,7 @@
         "Otherwise, make sure your environment meets this notebook's requirements. You need the following:\n",
         "\n",
         "- The BigQuery SDK\n",
-        "- The Vision AI SDK\n",
+        "- The Vision API SDK\n",
         "- The Vertex AI SDK\n",
         "- The Cloud Storage SDK\n",
         "- Git\n",
@@ -201,7 +201,7 @@
         "import os\n",
         "\n",
         "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\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",
@@ -263,7 +263,7 @@
         "\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: BigQuery APIs, Vision API, Vertex AI APIs, Compute Engine APIs, and Cloud Storage.](https://console.cloud.google.com/flows/enableapi?apiid=bigquery.googleapis.com,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",
@@ -454,7 +454,7 @@
         "\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 AI SDK PDF-to-text conversion process.\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."
       ]
@@ -556,7 +556,7 @@
         "id": "init_aip:mbsdk"
       },
       "source": [
-        "### Create BigQuery client\n",
+        "### Initalize BigQuery SDK for Python\n",
         "\n",
         "Create the BigQuery client."
       ]
@@ -578,7 +578,7 @@
         "id": "hodnaGMZzhBz"
       },
       "source": [
-        "### Initialize Vision AI SDK for Python"
+        "### Initialize Vision API SDK for Python"
       ]
     },
     {
@@ -775,7 +775,7 @@
         "gcs_destination_path = \"ocr-output\"\n",
         "gcs_destination_uri = f\"{BUCKET_URI}/{gcs_destination_path}\"\n",
         "\n",
-        "# Specify the feature for the Vision AI processor\n",
+        "# Specify the feature for the Vision API processor\n",
         "feature = vision.Feature(type_=vision.Feature.Type.DOCUMENT_TEXT_DETECTION)\n",
         "\n",
         "# Create a collection of requests. The SDK requires a separate request per each\n",
@@ -1251,6 +1251,8 @@
       },
       "outputs": [],
       "source": [
+        "delete_bucket = False\n",
+        "\n",
         "# Delete the dataset using the Vertex dataset object\n",
         "dataset.delete()\n",
         "\n",
@@ -1263,7 +1265,7 @@
         "# Delete the AutoML or Pipeline training job\n",
         "job.delete()\n",
         "\n",
-        "if os.getenv(\"IS_TESTING\"):\n",
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
         "    ! gsutil -m rm -r $BUCKET_URI\n",
         "\n",
         "print(\"Clean up completed!\")"

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",
@@ -176,7 +182,7 @@
         "import os\n",
         "\n",
         "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\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",
@@ -233,6 +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": {

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
 
@@ -166,6 +166,17 @@ The steps performed in this tutorial include:
 - 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

@@ -40,11 +40,11 @@
         "  </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",
+        "        <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/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",
@@ -133,7 +133,7 @@
         "import os\n",
         "\n",
         "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\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",
@@ -180,6 +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": {

notebooks/community/ml_ops/stage3/get_started_with_bq_tfdv_pipeline_components.ipynb

@@ -44,7 +44,7 @@
         "    </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/stage3/get_started_with_bq_tfdv_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_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",
@@ -129,7 +129,7 @@
       "source": [
         "## Installations\n",
         "\n",
-        "Install the packages for executing the MLOps notebooks."
+        "Install the packages for executing this notebook."
       ]
     },
     {
@@ -143,7 +143,7 @@
         "import os\n",
         "\n",
         "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\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",
@@ -153,9 +153,9 @@
         "if IS_WORKBENCH_NOTEBOOK:\n",
         "    USER_FLAG = \"--user\"\n",
         "\n",
-        "! pip3 install -U tensorflow $USER_FLAG\n",
-        "! pip3 install --upgrade google-cloud-aiplatform[tensorboard] $USER_FLAG\n",
-        "! pip3 install --upgrade kfp $USER_FLAG"
+        "! 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"
       ]
     },
     {
@@ -187,6 +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": {
@@ -294,26 +318,6 @@
         "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "b468c1ba2051"
-      },
-      "source": [
-        "#### Declare IS_COLAB variable"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "f5ad5d370123"
-      },
-      "outputs": [],
-      "source": [
-        "IS_COLAB = False"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {

notebooks/community/ml_ops/stage3/get_started_with_bqml_pipeline_components.ipynb

@@ -44,7 +44,7 @@
         "    </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/stage3/get_started_with_bqml_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_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",
@@ -149,7 +149,7 @@
         "import os\n",
         "\n",
         "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\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",
@@ -195,6 +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": {
@@ -302,26 +326,6 @@
         "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "b468c1ba2051"
-      },
-      "source": [
-        "#### Declare IS_COLAB variable"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "f5ad5d370123"
-      },
-      "outputs": [],
-      "source": [
-        "IS_COLAB = False"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {

notebooks/community/ml_ops/stage3/get_started_with_custom_training_pipeline_components.ipynb

@@ -44,7 +44,7 @@
         "    </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/stage3/get_started_with_custom_training_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_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",
@@ -153,7 +153,7 @@
         "import os\n",
         "\n",
         "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\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",
@@ -198,6 +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": {

notebooks/community/ml_ops/stage3/get_started_with_dataflow_pipeline_components.ipynb

@@ -45,7 +45,7 @@
         "    </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/stage3/get_started_with_dataflow_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_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",
@@ -173,7 +173,7 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "cb082379ed5b"
+        "id": "BF1j6f9HApxa"
       },
       "source": [
         "### Set up your Google Cloud project\n",
@@ -184,9 +184,9 @@
         "\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 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 need to install the [Cloud SDK](https://cloud.google.com/sdk).\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",
@@ -499,9 +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)"
       ]
     },

notebooks/community/ml_ops/stage3/get_started_with_dataproc_serverless_pipeline_components.ipynb

@@ -44,7 +44,7 @@
         "        </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/stage3/get_started_with_dataproc_serverless_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_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",
@@ -179,6 +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": {

notebooks/community/ml_ops/stage3/get_started_with_hpt_pipeline_components.ipynb

@@ -44,7 +44,7 @@
         "    </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/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",
@@ -186,6 +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": {
@@ -463,15 +489,20 @@
       "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)"
       ]
     },
     {
@@ -1489,7 +1520,9 @@
       },
       "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/stage3/get_started_with_kubeflow_pipelines.ipynb

@@ -45,7 +45,7 @@
         "  </td>\n",
         "    \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/stage3/get_started_with_kubeflow_pipelines.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_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",
@@ -163,6 +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": {

notebooks/community/ml_ops/stage3/get_started_with_rapid_prototyping_bqml_automl.ipynb

@@ -43,7 +43,7 @@
         "    </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/stage3/get_started_with_rapid_prototyping_bqml_automl.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_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",
@@ -300,26 +300,6 @@
         "    app.kernel.do_shutdown(True)"
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "9a4444d892e2"
-      },
-      "source": [
-        "#### Declare IS_COLAB variable"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "84fa1aac5f41"
-      },
-      "outputs": [],
-      "source": [
-        "IS_COLAB = False"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -366,7 +346,7 @@
         "import sys\n",
         "\n",
         "# If on Vertex AI Workbench, then don't execute this code\n",
-        "IS_COLAB = False\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",
@@ -403,7 +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",

notebooks/community/ml_ops/stage3/get_started_with_tfx_pipeline.ipynb

@@ -44,18 +44,18 @@
         "<table align=\"left\">\n",
         "\n",
         "  <td>\n",
-        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/master/notebooks/community/ml_ops/stage3/get_started_with_tfx_pipeline.ipynb\">\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage3/get_started_with_tfx_pipeline.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-samplestree/master/notebooks/community/ml_ops/stage3/get_started_with_tfx_pipeline.ipynb\">\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samplestree/main/notebooks/community/ml_ops/stage3/get_started_with_tfx_pipeline.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/master/notebooks/community/ml_ops/stage3/get_started_with_tfx_pipeline.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_tfx_pipeline.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",

notebooks/community/ml_ops/stage3/mlops_formalization.ipynb

@@ -33,18 +33,18 @@
         "\n",
         "<table align=\"left\">\n",
         "   <td>\n",
-        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/master/notebooks/community/ml_ops/stage3/mlops_formalization.ipynb\">\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-samplestree/master/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/vertex-ai/workbench/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/master/notebooks/community/ml_ops/stage3/mlops_formalization.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/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",
@@ -250,6 +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": {
@@ -397,7 +423,7 @@
         "import sys\n",
         "\n",
         "# If on Vertex AI Workbench, then don't execute this code\n",
-        "IS_COLAB = False\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",

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

@@ -33,7 +33,7 @@
         "\n",
         "<table align=\"left\">\n",
         "  <td>\n",
-        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/master/notebooks/community/ml_ops/stage4/get_started_with_google_artifact_registry.ipynb\">\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",
@@ -44,7 +44,7 @@
         "    </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/master/notebooks/community/ml_ops/stage4/get_started_with_google_artifact_registry.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/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",
@@ -172,7 +172,7 @@
         "\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",

notebooks/community/ml_ops/stage4/get_started_with_model_evaluation.ipynb

@@ -35,18 +35,18 @@
         "<table align=\"left\">\n",
         "\n",
         "  <td>\n",
-        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/master/notebooks/community/ml_ops/stage4/get_started_with_model_evaluation.ipynb\">\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage4/get_started_with_model_evaluation.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-samplestree/master/notebooks/community/ml_ops/stage4/get_started_with_model_evaluation.ipynb\">\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samplestree/main/notebooks/community/ml_ops/stage4/get_started_with_model_evaluation.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/master/notebooks/community/ml_ops/stage4/get_started_with_model_evaluation.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/stage4/get_started_with_model_evaluation.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",
@@ -234,7 +234,7 @@
         "\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",

notebooks/community/ml_ops/stage4/get_started_with_vertex_xai.ipynb

@@ -44,7 +44,7 @@
         "    </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/master/notebooks/community/ml_ops/stage4/get_started_with_vertex_xai.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/stage4/get_started_with_vertex_xai.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",
@@ -226,7 +226,7 @@
         "\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",

notebooks/community/ml_ops/stage5/README.md

@@ -2,11 +2,23 @@
 
 ## Purpose
 
+Configure compute and networking requirements for containerized serving binaries for a production load.
+
 
 ## Recommendations  
 
+The fifth stage in MLOps is deployment to production of the blessed model, which will replace the previous blessed model in production. This stage may be done entirely by MLOps. We recommend:
 
-<img src='stage5.png'>
+- Deploy the blessed model from the Vertex Model Registry.
+- Use the Google Container Registry for the deployment container.
+- Attach, if any, serving function from the Vertex Model Registry to the deployed model.
+- Use Vertex Pipelines for the deployment.
+- For cloud models, deploy within the Google Cloud infrastructure.
+- Use Vertex Prediction traffic split for production rollout.
+- Use Vertex Prediction to set your criteria for scaling and load balancing.
+
+
+<img src='stage5v3.png'>
 
 ## Notebooks
 
@@ -45,3 +57,35 @@ The steps performed include:
 - Deploying a `Model` resource to a `Private Endpoint` resource.
 - Send a prediction request to a `Private Endpoint`
 ```
+
+[Get started with Vertex AI Endpoints and co-hosting models on shared VM](get_started_with_vertex_endpoint_and_shared_vm.ipynb)
+
+```
+The steps performed include:
+
+- Upload a pre-trained image classification model as a `Model` resource (model A).
+- Upload a pre-trained text sentence encoder model as a `Model` resource (model B).
+- Create a shared VM deployment resource pool.
+- List shared VM deployment resource pools.
+- Create two `Endpoint` resources.
+- Deploy first model (model A) to first `Endpoint` resource using shared VM deployment resource pool.
+- Deploy second model (model B) to second `Endpoint` resource using shared VM deployment resource pool.
+- Make a prediction request with first deployed model (model A).
+- Make a prediction request with second deployed model (model B).
+```
+
+[Get started with Auto-Scaling for Vertex AI Endpoints](get_started_with_autoscaling.ipynb)
+
+```
+The steps performed include:
+
+- Download a pretrained image classification model from TensorFlow Hub.
+- Upload the pretrained model as a `Model` resource.
+- Create an `Endpoint` resource.
+- Deploy `Model` resource for no-scaling (single node).
+- Deploy `Model` resource for manual scaling.
+- Deploy `Model` resource for auto-scaling.
+- Fine-tune scaling thresholds for CPU utilization.
+- Fine-tune scaling thresholds for GPU utilization.
+- Deploy mix of CPU and GPU model instances with auto-scaling to an `Endpoint` resource.
+```

notebooks/community/ml_ops/stage5/get_started_with_vertex_endpoints.ipynb

@@ -32,7 +32,7 @@
         "# E2E ML on GCP: MLOps stage 5 : Get started with Vertex AI Endpoints\n",
         "<table align=\"left\">\n",
         "  <td>\n",
-        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/master/notebooks/community/ml_ops/stage5/get_started_with_vertex_endpoints.ipynb\">\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage5/get_started_with_vertex_endpoints.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",
@@ -43,7 +43,7 @@
         "    </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/master/notebooks/community/ml_ops/stage5/get_started_with_vertex_endpoints.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/stage5/get_started_with_vertex_endpoints.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",
@@ -161,9 +161,9 @@
         "if IS_WORKBENCH_NOTEBOOK:\n",
         "    USER_FLAG = \"--user\"\n",
         "\n",
-        "! pip3 install --upgrade google-cloud-aiplatform $USER_FLAG\n",
-        "! pip3 install --upgrade google-cloud-pipeline-components $USER_FLAG\n",
-        "! pip3 install tensorflow-hub $USER_FLAG"
+        "! pip3 install --upgrade google-cloud-aiplatform $USER_FLAG -q\n",
+        "! pip3 install --upgrade google-cloud-pipeline-components $USER_FLAG -q\n",
+        "! pip3 install tensorflow-hub $USER_FLAG -q"
       ]
     },
     {
@@ -216,7 +216,7 @@
         "\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",
@@ -1710,7 +1710,7 @@
       },
       "outputs": [],
       "source": [
-        "delete_bucket = True\n",
+        "delete_bucket = False\n",
         "delete_model = True\n",
         "\n",
         "if delete_model:\n",

notebooks/community/ml_ops/stage5/get_started_with_vertex_private_endpoints.ipynb

@@ -32,18 +32,18 @@
         "# E2E ML on GCP: MLOps stage 5 : Get started with Vertex AI Private Endpoints\n",
         "<table align=\"left\">\n",
         "  <td>\n",
-        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/master/notebooks/community/ml_ops/stage5/get_started_with_vertex_private_endpoints.ipynb\">\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage5/get_started_with_vertex_private_endpoints.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-samplestree/master/notebooks/community/ml_ops/stage5/get_started_with_vertex_private_endpoints.ipynb\">\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samplestree/main/notebooks/community/ml_ops/stage5/get_started_with_vertex_private_endpoints.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/master/notebooks/community/ml_ops/stage5/get_started_with_vertex_private_endpoints.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/stage5/get_started_with_vertex_private_endpoints.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",
@@ -235,7 +235,7 @@
         "\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. [Enable the Service Networking API](https://console.cloud.google.com/flows/enableapi?apiid=servicenetworking.googleapis.com).\n",
         "\n",

notebooks/community/ml_ops/stage6/README.md

@@ -23,9 +23,7 @@ This stage may be done entirely by MLOps. We recommend:
 - Features that dynamically change per example (e.g., bank balance) are stored in Vertex Feature Store.
 
 
-<img src='stage6a.png'>
-<img src='stage6b.png'>
-<img src='stage6c.png'>
+<img src='stage6v2.png'>
 
 ## Notebooks
 
@@ -157,3 +155,50 @@ The steps performed include:
 - Deploy brute force Index.
 - Perform calibration between ANN and brute force index.
 ```
+
+[Get started with Vertex AI Matching Engine using Two Towers builtin algorithm](get_started_with_matchine_engine_twotowers.ipynb)
+
+```
+The steps performed include:
+
+1. Train the `Two-Tower` algorithm to generate embeddings (encoder) for the dataset.
+2. Hyperparameter tune the trained `Two-Tower` encoder.
+3. Make example predictions (embeddings) from then trained encoder.
+4. Generate embeddings using the trained `Two-Tower` builtin algorithm.
+5. Store embeddings to format supported by `Matching Engine`.
+6. Create a `Matching Engine Index` for the embeddings.
+7. Deploy the `Matching Engine Index` to a `Index Endpoint`.
+8. Make a matching engine prediction request.
+```
+
+[Get started with Vertex AI Matching Engine using Swivel builtin algorithm](get_started_with_matchine_swivel.ipynb)
+
+```
+The steps performed include:
+
+1. Train the `Swivel` algorithm to generate embeddings (encoder) for the dataset.
+2. Hyperparameter tune the trained `Swivel` encoder.
+3. Make example predictions (embeddings) from then trained encoder.
+4. Generate embeddings using the trained `Swivel` builtin algorithm.
+5. Store embeddings to format supported by `Matching Engine`.
+6. Create a `Matching Engine Index` for the embeddings.
+7. Deploy the `Matching Engine Index` to a `Index Endpoint`.
+8. Make a matching engine prediction request.
+```
+
+[Get started with Explainable AI and custom model server](get_started_with_xai_and_custom_server.ipynb)
+
+```
+The steps performed include:
+
+- Locally train a Pytorch tabular classifier.
+- Locally test the trained model.
+- Build a HTTP server using FastAPI.
+- Create a custom serving container with the trained model and FastAPI server.
+- Locally test the custom serving container.
+- Push the custom serving container to the Artifact Registry.
+- Upload the custom serving container as a `Model` resource.
+- Deploy the `Model` resource to an `Endpoint` resource.
+- Make a prediction request to the deployed custom serving container.
+- Make an explanation request to the deployed custom serving container.
+```

notebooks/community/ml_ops/stage6/get_started_with_cpr.ipynb

@@ -32,7 +32,7 @@
         "# E2E ML on GCP: MLOps stage 6 : Get started with Custom Prediction Routine (CPR)\n",
         "<table align=\"left\">\n",
         "  <td>\n",
-        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/master/notebooks/community/ml_ops/stage6/get_started_with_custom_predictions.ipynb\">\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage6/get_started_with_custom_predictions.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",
@@ -43,7 +43,7 @@
         "    </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/master/notebooks/community/ml_ops/stage6/get_started_with_custom_predictions.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/stage6/get_started_with_custom_predictions.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",
@@ -241,7 +241,7 @@
         "\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",

notebooks/community/ml_ops/stage6/get_started_with_fastapi.ipynb

@@ -33,7 +33,7 @@
         "\n",
         "<table align=\"left\">\n",
         "  <td>\n",
-        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/master/notebooks/community/ml_ops/stage6/get_started_with_fastapi.ipynb\">\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage6/get_started_with_fastapi.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",
@@ -44,7 +44,7 @@
         "    </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/master/notebooks/community/ml_ops/stage6/get_started_with_fastapi.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/stage6/get_started_with_fastapi.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",
@@ -210,7 +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 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",