Merge branch 'main' into batch_predict_index

* fix: filename rename

* fix: lint issues

community-content/CODEOWNERS

@@ -1,5 +1,6 @@
 *  @vertex-ai-samples-contributors  @GoogleCloudPlatform/cloudml-samples-owners
 /tf_agents_bandits_movie_recommendation_with_kfp_and_vertex_sdk	@yinghsienwu
+/pytorch_pre_built_images_deployment @googleapis/vertex-prediction-team
 /pytorch_text_classification_using_vertex_sdk_and_gcloud  @RajeshThallam
 /pytorch_text_classification_using_vertex_sdk_and_gcloud		@RajeshThallam @ultrons
 /sklearn_text_classification_from_script_using_vertex_sdk       @maxhardt

community-content/cpr-examples/timm_serving/.gitignore

@@ -2,4 +2,5 @@ cpr_model_server.py
 entrypoint.py
 state_dict.pth
 config.json
-**/__pycache__
+**/__pycache__
+!testdata/**

community-content/cpr-examples/timm_serving/README.md

@@ -2,7 +2,7 @@
 
 ## About CPR
 
-CPR ([custom prediction routines](https://github.com/googleapis/python-aiplatform/blob/custom-prediction-routine/google/cloud/aiplatform/prediction/README.md)) is a framework designed by Google Cloud developers to make it easier to combine machine learning models with custom preprocessing and postprocessing logic in a real-time serving application. 
+CPR ([custom prediction routines](https://github.com/googleapis/python-aiplatform/blob/main/google/cloud/aiplatform/prediction/README.md)) is a framework designed by Google Cloud developers to make it easier to combine machine learning models with custom preprocessing and postprocessing logic in a real-time serving application. 
 
 ## Using this example
 
@@ -34,6 +34,23 @@ Finally, install the Python modules required to build and run the model server:
 pip install -r requirements.txt
 ```
 
+### Auth
+
+This example uses Google Cloud Storage for hosting model artifacts and Artifact Registry to store the container image. 
+You'll need to authorize yourself before you can interact with these.
+
+First, log in to GCP with application default credentials:
+```sh
+gcloud auth application-default login
+```
+
+Next, if you haven't done so already, set up the [gcloud credential helper](https://cloud.google.com/artifact-registry/docs/docker/authentication)
+for the Artifact Registry region where you intend to host the image.  
+```
+gcloud auth configure-docker <region>-docker.pkg.dev
+```
+
+
 ### Predictor
 
 The `TimmPredictor` class in `timm_serving/predictor.py` implements most of the important logic for the server.

community-content/cpr-examples/timm_serving/config.py

@@ -60,9 +60,9 @@ class CPRConfig(object):
     image: str = "timm_predictor:latest"
     artifact_local_dir: str = ""
     region: str = "us-central1"
-    project_id: str = "samthrasher-experimental"
+    project_id: str = "<your project ID here>"
     repository: str = "cpr-images"
-    artifact_gcs_dir: str = "gs://samthrasher-cpr-example/timm-vit224/"
+    artifact_gcs_dir: str = "gs://<your bucket ID here>/timm-vit224/"
     model_name: str = ""
     endpoint_name: str = ""
     machine_type: str = "n1-standard-2"

community-content/cpr-examples/timm_serving/requirements.txt

@@ -5,4 +5,4 @@ timm==0.5.4
 smart_open==6.0.0
 
 google-cloud-storage>=1.26.0,<2.0.0dev
-google-cloud-aiplatform[prediction] @ git+https://github.com/googleapis/python-aiplatform.git@custom-prediction-routine
+google-cloud-aiplatform[prediction]>=1.16.0

community-content/cpr-examples/timm_serving/test.py

@@ -70,7 +70,10 @@ class PredictorUnitTests(absltest.TestCase):
     def setUp(self):
         super().setUp()
         self.config = CPRConfig()
-        self.config.load()
+        try:
+            self.config.load()
+        except FileNotFoundError:
+            logging.info("No saved config file found, using default values.")
         self.predictor = predictor.TimmPredictor()
 
     def test_load_from_saved_state_dict_ok(self):
@@ -170,7 +173,10 @@ class ServerEndToEndTests(absltest.TestCase):
     def setUp(self):
         super().setUp()
         self.config = CPRConfig()
-        self.config.load()
+        try:
+            self.config.load()
+        except FileNotFoundError:
+            logging.info("No saved config file found, using default values.")
         self.local_model = cpr.LocalModel(
             serving_container_spec=aiplatform.gapic.ModelContainerSpec(
                 image_uri=self.config.image

community-content/cpr-examples/timm_serving/testdata/bad_model_1/state_dict.pth

@@ -0,0 +1 @@
+blah

community-content/pytorch_pre_built_images_deployment/README.md

@@ -0,0 +1,30 @@
+# PyTorch Deployment on Google Cloud: Text Classification
+
+**This is an Experimental release**, covered by the Pre-GA Offerings Terms of your Google Cloud Platform [Terms of Service](https://cloud.google.com/terms).
+
+Experiments are focused on validating a prototype and are not guaranteed to be released. They are not intended for production use or covered by any SLA, support obligation, or deprecation policy and might be subject to backward-incompatible changes.
+
+**Kindly drop us a note before you run any scale tests.**
+
+**Do not hesitate to contact vertexai-prediction-preview-feedback@google.com if you have any questions or run into any issues.**
+
+The projects need to be added to the allowlist in order to deploy PyTorch models using Vertex AI Prediction pre-built PyTorch images. If you are interested in the feature, please send an email to vertexai-prediction-preview-feedback@google.com to provide your project numbers OR project ids.
+
+## Overview
+
+In the PyTorch on Google Cloud series of blog posts, we aim to share how to deploy PyTorch models at scale on [Vertex AI](https://cloud.google.com/vertex-ai).
+
+This tutorial on text classification shows how to deploy a PyTorch based text classification model on [Vertex AI](https://cloud.google.com/vertex-ai/docs/start/client-libraries#python) using Vertex SDK and [`gcloud ai`](https://cloud.google.com/sdk/gcloud/reference/beta/ai).
+
+## Notebooks
+
+| <h4>Notebook</h4> | <h4>Description</h4>                       |
+| :-------- | :------- |
+| [pytorch-text-classification-vertex-ai-deploy.ipynb](./pytorch-text-classification-vertex-ai-deploy.ipynb) | Notebook to show deploying a PyTorch model on Vertex AI |
+
+## Folders
+
+
+| <h4>Folder Name</h4> | <h4>Description</h4>                       |
+| :-------- | :------- |
+| [`predictor`](./predictor) | Folder with custom prediction handler to deploy a PyTorch model to Vertex Prediction. In the [notebook](./pytorch-text-classification-vertex-ai-deploy.ipynb), this folder is used for deploying a PyTorch model on Vertex AI using Vertex Prediction pre-built PyTorch images |

community-content/pytorch_pre_built_images_deployment/predictor/custom_handler.py

@@ -0,0 +1,91 @@
+
+import os
+import json
+import logging
+
+import torch
+from transformers import AutoModelForSequenceClassification, AutoTokenizer
+from ts.torch_handler.base_handler import BaseHandler
+
+logger = logging.getLogger(__name__)
+
+
+class TransformersClassifierHandler(BaseHandler):
+    """
+    The handler takes an input string and returns the classification text 
+    based on the serialized transformers checkpoint.
+    """
+    def __init__(self):
+        super(TransformersClassifierHandler, self).__init__()
+        self.initialized = False
+
+    def initialize(self, ctx):
+        """ Loads the model.pt file and initialized the model object.
+        Instantiates Tokenizer for preprocessor to use
+        Loads labels to name mapping file for post-processing inference response
+        """
+        self.manifest = ctx.manifest
+
+        properties = ctx.system_properties
+        model_dir = properties.get("model_dir")
+        self.device = torch.device("cuda:" + str(properties.get("gpu_id")) if torch.cuda.is_available() else "cpu")
+
+        # Read model serialize/pt file
+        serialized_file = self.manifest["model"]["serializedFile"]
+        model_pt_path = os.path.join(model_dir, serialized_file)
+        if not os.path.isfile(model_pt_path):
+            raise RuntimeError("Missing the model.pt or pytorch_model.bin file")
+        
+        # Load model
+        self.model = AutoModelForSequenceClassification.from_pretrained(model_dir)
+        self.model.to(self.device)
+        self.model.eval()
+        logger.debug('Transformer model from path {0} loaded successfully'.format(model_dir))
+        
+        # Ensure to use the same tokenizer used during training
+        self.tokenizer = AutoTokenizer.from_pretrained('bert-base-cased')
+
+        # Read the mapping file, index to object name
+        mapping_file_path = os.path.join(model_dir, "index_to_name.json")
+
+        if os.path.isfile(mapping_file_path):
+            with open(mapping_file_path) as f:
+                self.mapping = json.load(f)
+        else:
+            logger.warning('Missing the index_to_name.json file. Inference output will default.')
+            self.mapping = {"0": "Negative",  "1": "Positive"}
+
+        self.initialized = True
+
+    def preprocess(self, data):
+        """ Preprocessing input request by tokenizing
+            Extend with your own preprocessing steps as needed
+        """
+        text = data[0].get("data")
+        if text is None:
+            text = data[0].get("body")
+        sentences = text.decode('utf-8')
+        logger.info("Received text: '%s'", sentences)
+
+        # Tokenize the texts
+        tokenizer_args = ((sentences,))
+        inputs = self.tokenizer(*tokenizer_args,
+                                padding='max_length',
+                                max_length=128,
+                                truncation=True,
+                                return_tensors = "pt")
+        return inputs
+
+    def inference(self, inputs):
+        """ Predict the class of a text using a trained transformer model.
+        """
+        prediction = self.model(inputs['input_ids'].to(self.device))[0].argmax().item()
+
+        if self.mapping:
+            prediction = self.mapping[str(prediction)]
+
+        logger.info("Model predicted: '%s'", prediction)
+        return [prediction]
+
+    def postprocess(self, inference_output):
+        return inference_output

community-content/pytorch_pre_built_images_deployment/predictor/index_to_name.json

@@ -0,0 +1,5 @@
+
+{
+    "0": "Negative", 
+    "1": "Positive"
+}

community-content/pytorch_text_classification_using_vertex_sdk_and_gcloud/pytorch-text-classification-vertex-ai-train-tune-deploy.ipynb

@@ -658,8 +658,8 @@
       },
       "outputs": [],
       "source": [
-        "datasets = load_dataset(\"imdb\")\n",
-        "datasets"
+        "dataset = load_dataset(\"imdb\")\n",
+        "dataset"
       ]
     },
     {
@@ -668,7 +668,7 @@
         "id": "RzfPtOMoIrIu"
       },
       "source": [
-        "The `datasets` object itself is [`DatasetDict`](https://huggingface.co/docs/datasets/package_reference/main_classes.html#datasetdict), which contains one key for the training, validation and test set."
+        "The `dataset` object itself is [`DatasetDict`](https://huggingface.co/docs/datasets/package_reference/main_classes.html#datasetdict), which contains one key for the training, validation and test set."
       ]
     },
     {
@@ -681,12 +681,12 @@
       "source": [
         "print(\n",
         "    \"Total # of rows in training dataset {} and size {:5.2f} MB\".format(\n",
-        "        datasets[\"train\"].shape[0], datasets[\"train\"].size_in_bytes / (1024 * 1024)\n",
+        "        dataset[\"train\"].shape[0], dataset[\"train\"].size_in_bytes / (1024 * 1024)\n",
         "    )\n",
         ")\n",
         "print(\n",
         "    \"Total # of rows in test dataset {} and size {:5.2f} MB\".format(\n",
-        "        datasets[\"test\"].shape[0], datasets[\"test\"].size_in_bytes / (1024 * 1024)\n",
+        "        dataset[\"test\"].shape[0], dataset[\"test\"].size_in_bytes / (1024 * 1024)\n",
         "    )\n",
         ")"
       ]
@@ -708,7 +708,7 @@
       },
       "outputs": [],
       "source": [
-        "datasets[\"train\"][0]"
+        "dataset[\"train\"][0]"
       ]
     },
     {
@@ -728,7 +728,7 @@
       },
       "outputs": [],
       "source": [
-        "label_list = datasets[\"train\"].unique(\"label\")\n",
+        "label_list = dataset[\"train\"].unique(\"label\")\n",
         "label_list"
       ]
     },
@@ -779,7 +779,7 @@
       },
       "outputs": [],
       "source": [
-        "show_random_elements(datasets[\"train\"])"
+        "show_random_elements(dataset[\"train\"])"
       ]
     },
     {
@@ -883,7 +883,7 @@
       },
       "outputs": [],
       "source": [
-        "example = datasets[\"train\"][4]\n",
+        "example = dataset[\"train\"][4]\n",
         "print(example)"
       ]
     },
@@ -920,7 +920,7 @@
       "source": [
         "# Dataset loading repeated here to make this cell idempotent\n",
         "# Since we are over-writing datasets variable\n",
-        "datasets = load_dataset(\"imdb\")\n",
+        "dataset = load_dataset(\"imdb\")\n",
         "\n",
         "# Mapping labels to ids\n",
         "# NOTE: We can extract this automatically but the `Unique` method of the datasets\n",
@@ -948,7 +948,7 @@
         "\n",
         "\n",
         "# apply preprocessing function to input examples\n",
-        "datasets = datasets.map(preprocess_function, batched=True, load_from_cache_file=True)"
+        "dataset = dataset.map(preprocess_function, batched=True, load_from_cache_file=True)"
       ]
     },
     {
@@ -1091,8 +1091,8 @@
         "trainer = Trainer(\n",
         "    model,\n",
         "    args,\n",
-        "    train_dataset=datasets[\"train\"],\n",
-        "    eval_dataset=datasets[\"test\"],\n",
+        "    train_dataset=dataset[\"train\"],\n",
+        "    eval_dataset=dataset[\"test\"],\n",
         "    data_collator=default_data_collator,\n",
         "    tokenizer=tokenizer,\n",
         "    compute_metrics=compute_metrics,\n",

notebooks/community/CODEOWNERS

@@ -17,6 +17,7 @@
 /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
+/matching_engine/stream_update_for_matching_engine.ipynb @peterping666
 /sdk/pytorch_lightning_custom_container_training.ipynb @brianchunkang
 /tensorboard @yfang1
 /feature_store @nayaknishant @morgandu

notebooks/community/feature_store/gapic-feature-store.ipynb

@@ -292,6 +292,37 @@
         "    PROJECT_ID = \"python-docs-samples-tests\"  # @param {type:\"string\"}"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "d9f118b92c74"
+      },
+      "source": [
+        "#### UUID\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 uuid for each instance session, and append it onto the name of resources you create in this tutorial."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "3ee72715c0fd"
+      },
+      "outputs": [],
+      "source": [
+        "import random\n",
+        "import string\n",
+        "\n",
+        "\n",
+        "# Generate a uuid of a specifed length(default=8)\n",
+        "def generate_uuid(length: int = 8) -> str:\n",
+        "    return \"\".join(random.choices(string.ascii_lowercase + string.digits, k=length))\n",
+        "\n",
+        "\n",
+        "UUID = generate_uuid()"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -478,7 +509,6 @@
         "from google.cloud.aiplatform_v1.types import \\\n",
         "    featurestore_service as featurestore_service_pb2\n",
         "from google.cloud.aiplatform_v1.types import io as io_pb2\n",
-        "from google.protobuf.duration_pb2 import Duration\n",
         "\n",
         "# Create admin_client for CRUD and data_client for reading feature values.\n",
         "admin_client = FeaturestoreServiceClient(client_options={\"api_endpoint\": API_ENDPOINT})\n",
@@ -542,7 +572,7 @@
       },
       "outputs": [],
       "source": [
-        "FEATURESTORE_ID = \"movie_prediction\"\n",
+        "FEATURESTORE_ID = f\"movie_prediction_{UUID}\"\n",
         "try:\n",
         "    create_lro = admin_client.create_featurestore(\n",
         "        featurestore_service_pb2.CreateFeaturestoreRequest(\n",
@@ -567,7 +597,7 @@
         "id": "ag8pCQ7rNjVf"
       },
       "source": [
-        "You can use [GetFeaturestore](https://cloud.google.com/vertex-ai/docs/reference/rpc/google.cloud.aiplatform.v1beta1#google.cloud.aiplatform.v1beta1.FeaturestoreService.GetFeaturestore) or [ListFeaturestores](https://cloud.google.com/vertex-ai/docs/reference/rpc/google.cloud.aiplatform.v1beta1#google.cloud.aiplatform.v1beta1.FeaturestoreService.ListFeaturestores) to check if the Featurestore was successfully created. The following example gets the details of the Featurestore.\n"
+        "You can use [GetFeaturestore](https://cloud.google.com/vertex-ai/docs/reference/rpc/google.cloud.aiplatform.v1#google.cloud.aiplatform.v1.FeaturestoreService.GetFeaturestore) or [ListFeaturestores](https://cloud.google.com/vertex-ai/docs/reference/rpc/google.cloud.aiplatform.v1#google.cloud.aiplatform.v1.FeaturestoreService.ListFeaturestores) to check if the Featurestore was successfully created. The following example gets the details of the Featurestore.\n"
       ]
     },
     {
@@ -589,7 +619,7 @@
         "id": "018ab19d934f"
       },
       "source": [
-        "Auto scaling is available in v1beta1 since v1.11. Below is the example for the `CreateFeaturestoreRequest` with auto-scaling, use it with `aiplatform_v1beta1.FeaturestoreServiceClient` to create Featurestore:"
+        "Auto scaling is available in v1 since v1.11. Below is the example for the `CreateFeaturestoreRequest` with auto-scaling, use it with `aiplatform_v1.FeaturestoreServiceClient` to create Featurestore:"
       ]
     },
     {
@@ -600,17 +630,17 @@
       },
       "outputs": [],
       "source": [
-        "from google.cloud.aiplatform_v1beta1.types import \\\n",
-        "    featurestore as v1beta1_featurestore_pb2\n",
-        "from google.cloud.aiplatform_v1beta1.types import \\\n",
-        "    featurestore_service as v1beta1_featurestore_service_pb2\n",
+        "from google.cloud.aiplatform_v1.types import \\\n",
+        "    featurestore as v1_featurestore_pb2\n",
+        "from google.cloud.aiplatform_v1.types import \\\n",
+        "    featurestore_service as v1_featurestore_service_pb2\n",
         "\n",
-        "create_featurestore_request = v1beta1_featurestore_service_pb2.CreateFeaturestoreRequest(\n",
+        "create_featurestore_request = v1_featurestore_service_pb2.CreateFeaturestoreRequest(\n",
         "    parent=BASE_RESOURCE_PATH,\n",
         "    featurestore_id=FEATURESTORE_ID,\n",
-        "    featurestore=v1beta1_featurestore_pb2.Featurestore(\n",
-        "        online_serving_config=v1beta1_featurestore_pb2.Featurestore.OnlineServingConfig(\n",
-        "            scaling=v1beta1_featurestore_pb2.Featurestore.OnlineServingConfig.Scaling(\n",
+        "    featurestore=v1_featurestore_pb2.Featurestore(\n",
+        "        online_serving_config=v1_featurestore_pb2.Featurestore.OnlineServingConfig(\n",
+        "            scaling=v1_featurestore_pb2.Featurestore.OnlineServingConfig.Scaling(\n",
         "                min_node_count=1, max_node_count=5\n",
         "            )\n",
         "        ),\n",
@@ -681,7 +711,7 @@
         "id": "dPkT7KDuEvWv"
       },
       "source": [
-        "Feature [monitoring](https://cloud.google.com/vertex-ai/docs/featurestore/monitoring) is in preview, so you need to use v1beta1 Python. Import feature analysis is only available through SDK for now."
+        "Feature [monitoring](https://cloud.google.com/vertex-ai/docs/featurestore/monitoring) is in preview, so you need to use v1 Python. Import feature analysis is only available through SDK for now."
       ]
     },
     {
@@ -692,36 +722,35 @@
       },
       "outputs": [],
       "source": [
-        "from google.cloud.aiplatform_v1beta1 import \\\n",
-        "    FeaturestoreServiceClient as v1beta1_FeaturestoreServiceClient\n",
-        "from google.cloud.aiplatform_v1beta1.types import \\\n",
-        "    entity_type as v1beta1_entity_type_pb2\n",
-        "from google.cloud.aiplatform_v1beta1.types import \\\n",
-        "    featurestore_monitoring as v1beta1_featurestore_monitoring_pb2\n",
-        "from google.cloud.aiplatform_v1beta1.types import \\\n",
-        "    featurestore_service as v1beta1_featurestore_service_pb2\n",
+        "from google.cloud.aiplatform_v1 import \\\n",
+        "    FeaturestoreServiceClient as v1_FeaturestoreServiceClient\n",
+        "from google.cloud.aiplatform_v1.types import entity_type as v1_entity_type_pb2\n",
+        "from google.cloud.aiplatform_v1.types import \\\n",
+        "    featurestore_monitoring as v1_featurestore_monitoring_pb2\n",
+        "from google.cloud.aiplatform_v1.types import \\\n",
+        "    featurestore_service as v1_featurestore_service_pb2\n",
         "\n",
-        "v1beta1_admin_client = v1beta1_FeaturestoreServiceClient(\n",
+        "v1_admin_client = v1_FeaturestoreServiceClient(\n",
         "    client_options={\"api_endpoint\": API_ENDPOINT}\n",
         ")\n",
         "\n",
         "# Enable import feature analysis for users entity type.\n",
         "# All Features belonging to this EntityType will by default inherit the monitoring config.\n",
-        "v1beta1_admin_client.update_entity_type(\n",
-        "    v1beta1_featurestore_service_pb2.UpdateEntityTypeRequest(\n",
-        "        entity_type=v1beta1_entity_type_pb2.EntityType(\n",
+        "v1_admin_client.update_entity_type(\n",
+        "    v1_featurestore_service_pb2.UpdateEntityTypeRequest(\n",
+        "        entity_type=v1_entity_type_pb2.EntityType(\n",
         "            name=admin_client.entity_type_path(\n",
         "                PROJECT_ID, REGION, FEATURESTORE_ID, \"users\"\n",
         "            ),\n",
-        "            monitoring_config=v1beta1_featurestore_monitoring_pb2.FeaturestoreMonitoringConfig(\n",
-        "                import_features_analysis=v1beta1_featurestore_monitoring_pb2.FeaturestoreMonitoringConfig.ImportFeaturesAnalysis(\n",
-        "                    anomaly_detection_baseline=v1beta1_featurestore_monitoring_pb2.FeaturestoreMonitoringConfig.ImportFeaturesAnalysis.Baseline.LATEST_STATS,\n",
-        "                    state=v1beta1_featurestore_monitoring_pb2.FeaturestoreMonitoringConfig.ImportFeaturesAnalysis.State.ENABLED,\n",
+        "            monitoring_config=v1_featurestore_monitoring_pb2.FeaturestoreMonitoringConfig(\n",
+        "                import_features_analysis=v1_featurestore_monitoring_pb2.FeaturestoreMonitoringConfig.ImportFeaturesAnalysis(\n",
+        "                    anomaly_detection_baseline=v1_featurestore_monitoring_pb2.FeaturestoreMonitoringConfig.ImportFeaturesAnalysis.Baseline.LATEST_STATS,\n",
+        "                    state=v1_featurestore_monitoring_pb2.FeaturestoreMonitoringConfig.ImportFeaturesAnalysis.State.ENABLED,\n",
         "                ),\n",
-        "                numerical_threshold_config=v1beta1_featurestore_monitoring_pb2.FeaturestoreMonitoringConfig.ThresholdConfig(\n",
+        "                numerical_threshold_config=v1_featurestore_monitoring_pb2.FeaturestoreMonitoringConfig.ThresholdConfig(\n",
         "                    value=0.001,\n",
         "                ),\n",
-        "                categorical_threshold_config=v1beta1_featurestore_monitoring_pb2.FeaturestoreMonitoringConfig.ThresholdConfig(\n",
+        "                categorical_threshold_config=v1_featurestore_monitoring_pb2.FeaturestoreMonitoringConfig.ThresholdConfig(\n",
         "                    value=0.001,\n",
         "                ),\n",
         "            ),\n",
@@ -736,7 +765,7 @@
         "id": "85b1f59fbf6d"
       },
       "source": [
-        "The easiest way to set up snapshot analysis for now is using [console UI](https://console.cloud.google.com/vertex-ai/features). For completeness, below is example to do this using v1beta1 SDK.\n",
+        "The easiest way to set up snapshot analysis for now is using [console UI](https://console.cloud.google.com/vertex-ai/features). For completeness, below is example to do this using v1 SDK.\n",
         "\n",
         "You can view monitoring statistics on [console UI](https://console.cloud.google.com/vertex-ai/features)."
       ]
@@ -749,36 +778,35 @@
       },
       "outputs": [],
       "source": [
-        "from google.cloud.aiplatform_v1beta1 import \\\n",
-        "    FeaturestoreServiceClient as v1beta1_FeaturestoreServiceClient\n",
-        "from google.cloud.aiplatform_v1beta1.types import \\\n",
-        "    entity_type as v1beta1_entity_type_pb2\n",
-        "from google.cloud.aiplatform_v1beta1.types import \\\n",
-        "    featurestore_monitoring as v1beta1_featurestore_monitoring_pb2\n",
-        "from google.cloud.aiplatform_v1beta1.types import \\\n",
-        "    featurestore_service as v1beta1_featurestore_service_pb2\n",
+        "from google.cloud.aiplatform_v1 import \\\n",
+        "    FeaturestoreServiceClient as v1_FeaturestoreServiceClient\n",
+        "from google.cloud.aiplatform_v1.types import entity_type as v1_entity_type_pb2\n",
+        "from google.cloud.aiplatform_v1.types import \\\n",
+        "    featurestore_monitoring as v1_featurestore_monitoring_pb2\n",
+        "from google.cloud.aiplatform_v1.types import \\\n",
+        "    featurestore_service as v1_featurestore_service_pb2\n",
         "\n",
-        "v1beta1_admin_client = v1beta1_FeaturestoreServiceClient(\n",
+        "v1_admin_client = v1_FeaturestoreServiceClient(\n",
         "    client_options={\"api_endpoint\": API_ENDPOINT}\n",
         ")\n",
         "\n",
         "# Enable snapshot analysis for users entity type.\n",
         "# All Features belonging to this EntityType will by default inherit the monitoring config.\n",
-        "v1beta1_admin_client.update_entity_type(\n",
-        "    v1beta1_featurestore_service_pb2.UpdateEntityTypeRequest(\n",
-        "        entity_type=v1beta1_entity_type_pb2.EntityType(\n",
+        "v1_admin_client.update_entity_type(\n",
+        "    v1_featurestore_service_pb2.UpdateEntityTypeRequest(\n",
+        "        entity_type=v1_entity_type_pb2.EntityType(\n",
         "            name=admin_client.entity_type_path(\n",
         "                PROJECT_ID, REGION, FEATURESTORE_ID, \"users\"\n",
         "            ),\n",
-        "            monitoring_config=v1beta1_featurestore_monitoring_pb2.FeaturestoreMonitoringConfig(\n",
-        "                snapshot_analysis=v1beta1_featurestore_monitoring_pb2.FeaturestoreMonitoringConfig.SnapshotAnalysis(\n",
-        "                    monitoring_interval=Duration(seconds=86400),  # 1 day\n",
+        "            monitoring_config=v1_featurestore_monitoring_pb2.FeaturestoreMonitoringConfig(\n",
+        "                snapshot_analysis=v1_featurestore_monitoring_pb2.FeaturestoreMonitoringConfig.SnapshotAnalysis(\n",
+        "                    monitoring_interval_days=1,  # 1 day\n",
         "                    staleness_days=30,\n",
         "                ),\n",
-        "                numerical_threshold_config=v1beta1_featurestore_monitoring_pb2.FeaturestoreMonitoringConfig.ThresholdConfig(\n",
+        "                numerical_threshold_config=v1_featurestore_monitoring_pb2.FeaturestoreMonitoringConfig.ThresholdConfig(\n",
         "                    value=0.001,\n",
         "                ),\n",
-        "                categorical_threshold_config=v1beta1_featurestore_monitoring_pb2.FeaturestoreMonitoringConfig.ThresholdConfig(\n",
+        "                categorical_threshold_config=v1_featurestore_monitoring_pb2.FeaturestoreMonitoringConfig.ThresholdConfig(\n",
         "                    value=0.001,\n",
         "                ),\n",
         "            ),\n",
@@ -891,8 +919,8 @@
       "source": [
         "## Search created features\n",
         "\n",
-        "While the [ListFeatures](https://cloud.google.com/vertex-ai/docs/reference/rpc/google.cloud.aiplatform.v1beta1#google.cloud.aiplatform.v1beta1.FeaturestoreService.ListFeatures) method allows you to easily view all features of a single\n",
-        "entity type, the [SearchFeatures](https://cloud.google.com/vertex-ai/docs/reference/rpc/google.cloud.aiplatform.v1beta1#google.cloud.aiplatform.v1beta1.FeaturestoreService.SearchFeatures) method searches across all featurestores\n",
+        "While the [ListFeatures](https://cloud.google.com/vertex-ai/docs/reference/rpc/google.cloud.aiplatform.v1#google.cloud.aiplatform.v1.FeaturestoreService.ListFeatures) method allows you to easily view all features of a single\n",
+        "entity type, the [SearchFeatures](https://cloud.google.com/vertex-ai/docs/reference/rpc/google.cloud.aiplatform.v1#google.cloud.aiplatform.v1.FeaturestoreService.SearchFeatures) method searches across all featurestores\n",
         "and entity types in a given location (such as `us-central1`). This can help you discover features that were created by someone else.\n",
         "\n",
         "You can query based on feature properties including feature ID, entity type ID,\n",
@@ -1206,7 +1234,7 @@
       },
       "source": [
         "The\n",
-        "[Online Serving APIs](https://cloud.google.com/vertex-ai/docs/reference/rpc/google.cloud.aiplatform.v1beta1#featurestoreonlineservingservice)\n",
+        "[Online Serving APIs](https://cloud.google.com/vertex-ai/docs/reference/rpc/google.cloud.aiplatform.v1#featurestoreonlineservingservice)\n",
         "lets you serve feature values for small batches of entities. It's designed for latency-sensitive service, such as online model prediction. For example, for a movie service, you might want to quickly shows movies that the current user would most likely watch by using online predictions."
       ]
     },

notebooks/community/ml_ops/stage1/get_started_with_data_labeling.ipynb

@@ -212,7 +212,7 @@
         "\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",
+        "4. [Google Cloud SDK](https://cloud.google.com/sdk) is already installed in Vertex AI Workbench Notebooks.\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",
@@ -374,15 +374,8 @@
         "### Authenticate your Google Cloud account\n",
         "\n",
         "**If you are using Vertex AI Workbench Notebooks**, your environment is already\n",
-        "authenticated. Skip this step."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "32e1cd21a5d5"
-      },
-      "source": [
+        "authenticated. \n",
+        "\n",
         "**If you are using Colab**, run the cell below and follow the instructions\n",
         "when prompted to authenticate your account via oAuth.\n",
         "\n",

notebooks/community/ml_ops/stage5/get_started_with_vertex_endpoints.ipynb

@@ -340,7 +340,7 @@
       "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",
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already authenticated. \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",
@@ -376,12 +376,11 @@
         "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",
@@ -428,8 +427,9 @@
       },
       "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"
+        "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}\""
       ]
     },
     {
@@ -785,7 +785,7 @@
       },
       "outputs": [],
       "source": [
-        "endpoint.gca_resource"
+        "print(endpoint.gca_resource)"
       ]
     },
     {
@@ -908,7 +908,7 @@
       },
       "outputs": [],
       "source": [
-        "endpoint.gca_resource.deployed_models[0]"
+        "print(endpoint.gca_resource.deployed_models[0])"
       ]
     },
     {
@@ -1203,12 +1203,10 @@
         "\n",
         "In this pipeline, you create an `Endpoint` resource, and then you deploy a `Model` resource to the `Endpoint` resource. The `Model` resource  to deploy is your existing TFHub model which you previously imported as a `Model` resource. The steps are:\n",
         "\n",
-        "- For pipeline parameters, pass the resource name and resource URI for the existing `Model` resource.\n",
-        "- Use the `importer_node()` component to create a `VertexModel` pipeline artifact for the model.\n",
+        "- For pipeline parameters, pass the resource name for the existing `Model` resource.\n",
+        "- Use the `GetVertexModelOp()` component to create a `VertexModel` pipeline artifact for the model.\n",
         "- Create an `Endpoint` resource.\n",
-        "- Using the `VertexModel` pipeline artifact, deploy the `Model` resource to the `Endpoint` resource.\n",
-        "\n",
-        "*Note:* This example currently blocked by internal issue: b/219835305"
+        "- Using the `VertexModel` pipeline artifact, deploy the `Model` resource to the `Endpoint` resource."
       ]
     },
     {
@@ -1225,20 +1223,6 @@
         "\n",
         "PIPELINE_ROOT = \"{}/pipeline_root/endpoint_example\".format(BUCKET_URI)\n",
         "\n",
-        "# (WORKAROUND  b/219835305)\n",
-        "@component(\n",
-        "    base_image=\"python:3.9\",\n",
-        "    packages_to_install=[\"google-cloud-aiplatform\"],\n",
-        ")\n",
-        "def return_unmanaged_model(\n",
-        "    serving_image: str, artifact_uri: str, resource_name: str, model: Output[Artifact]\n",
-        "):\n",
-        "    model.metadata[\"containerSpec\"] = {\"imageUri\": serving_image}\n",
-        "\n",
-        "    model.metadata[\"resourceName\"] = resource_name\n",
-        "\n",
-        "    model.uri = artifact_uri\n",
-        "\n",
         "\n",
         "@dsl.pipeline(\n",
         "    name=\"create-endpoint-deploy-model\",\n",
@@ -1246,34 +1230,16 @@
         ")\n",
         "def pipeline(\n",
         "    display_name: str,\n",
-        "    resource_uri: str,\n",
         "    resource_name: str,\n",
-        "    # Model properties (WORKAROUND  b/219835305)\n",
-        "    serving_image: str,\n",
-        "    artifact_uri: str,\n",
         "    project: str = PROJECT_ID,\n",
         "    region: str = REGION,\n",
         "):\n",
-        "    from google_cloud_pipeline_components.types import artifact_types\n",
+        "    from google_cloud_pipeline_components.experimental.evaluation import \\\n",
+        "        GetVertexModelOp\n",
         "    from google_cloud_pipeline_components.v1.endpoint import (EndpointCreateOp,\n",
         "                                                              ModelDeployOp)\n",
-        "    from kfp.v2.components import importer_node\n",
         "\n",
-        "    # Desired sequence: blocked by b/219835305\n",
-        "    \"\"\"\n",
-        "    model = importer_node.importer(\n",
-        "        artifact_uri=resource_uri,\n",
-        "        artifact_class=artifact_types.VertexModel,\n",
-        "        metadata={\"resourceName\": resource_name},\n",
-        "    )\n",
-        "    \"\"\"\n",
-        "\n",
-        "    # (WORKAROUND  b/219835305)\n",
-        "    model = return_unmanaged_model(\n",
-        "        serving_image=serving_image,\n",
-        "        artifact_uri=artifact_uri,\n",
-        "        resource_name=resource_name,\n",
-        "    )\n",
+        "    model = GetVertexModelOp(model_resource_name=resource_name)\n",
         "\n",
         "    endpoint_op = EndpointCreateOp(\n",
         "        project=project,\n",
@@ -1281,7 +1247,7 @@
         "        display_name=display_name,\n",
         "    )\n",
         "\n",
-        "    deploy_op = ModelDeployOp(\n",
+        "    _ = ModelDeployOp(\n",
         "        model=model.outputs[\"model\"],\n",
         "        endpoint=endpoint_op.outputs[\"endpoint\"],\n",
         "        dedicated_resources_min_replica_count=1,\n",
@@ -1310,7 +1276,6 @@
         "\n",
         "- `display_name`: The display name for the generated Vertex AI resources.\n",
         "- `resource_name`: The resource name of the existing `Model` resource.\n",
-        "- `resource_uri`: The resource uri of the existing `Model` resource.\n",
         "- `project`: The project ID.\n",
         "- `region`: The region."
       ]
@@ -1323,10 +1288,6 @@
       },
       "outputs": [],
       "source": [
-        "# Model properties (WORKAROUND  b/219835305)\n",
-        "SERVING_CONTAINER_URI = model.gca_resource.container_spec.image_uri\n",
-        "ARTIFACT_URI = model.gca_resource.artifact_uri\n",
-        "\n",
         "try:\n",
         "    pipeline = aip.PipelineJob(\n",
         "        display_name=\"create-endpoint-deploy-pipeline\",\n",
@@ -1335,11 +1296,6 @@
         "        parameter_values={\n",
         "            \"display_name\": \"create_endpoint_and_deploy_model_\" + TIMESTAMP,\n",
         "            \"resource_name\": model.resource_name,\n",
-        "            \"resource_uri\": \"https://us-central1-aiplatform.googleapis.com/v1/\"\n",
-        "            + model.resource_name,\n",
-        "            # Model properties (WORKAROUND  b/219835305)\n",
-        "            \"serving_image\": SERVING_CONTAINER_URI,\n",
-        "            \"artifact_uri\": ARTIFACT_URI,\n",
         "            \"project\": PROJECT_ID,\n",
         "            \"region\": REGION,\n",
         "        },\n",
@@ -1488,7 +1444,7 @@
         "\n",
         "- For pipeline parameters, pass the resource names and resource URIs for the existing `Model` and `Endpoint` resource.\n",
         "- Use the `importer_node()` component to create a `VertexModel` pipeline artifact for the model.\n",
-        "- Use the `importer_node()` component to create a `VertexEndpoint` pipeline artifact for the endpoint.\n",
+        "- Use the `GetVertexModelOp()` component to create a `VertexModel` pipeline artifact for the model.\n",
         "- Using the `VertexModel` and `VertexEndpoint` pipeline artifacts, deploy the `Model` resource to the `Endpoint` resource.\n",
         "\n",
         "*Note:* This example currently blocked by internal issue: b/219835305"
@@ -1504,6 +1460,7 @@
       "source": [
         "PIPELINE_ROOT = \"{}/pipeline_root/endpoint_example_2\".format(BUCKET_URI)\n",
         "\n",
+        "\n",
         "# (WORKAROUND  b/219835305)\n",
         "@component(\n",
         "    base_image=\"python:3.9\",\n",
@@ -1520,35 +1477,23 @@
         ")\n",
         "def pipeline(\n",
         "    display_name: str,\n",
-        "    model_resource_uri: str,\n",
         "    model_resource_name: str,\n",
         "    endpoint_resource_uri: str,\n",
         "    endpoint_resource_name: str,\n",
-        "    # Model properties (WORKAROUND  b/219835305)\n",
-        "    serving_image: str,\n",
-        "    artifact_uri: str,\n",
         "    project: str = PROJECT_ID,\n",
         "    region: str = REGION,\n",
         "):\n",
-        "    from google_cloud_pipeline_components.types import artifact_types\n",
+        "    from google_cloud_pipeline_components.experimental.evaluation import \\\n",
+        "        GetVertexModelOp\n",
         "    from google_cloud_pipeline_components.v1.endpoint import ModelDeployOp\n",
-        "    from kfp.v2.components import importer_node\n",
         "\n",
         "    # Desired sequence: blocked by b/219835305\n",
         "    \"\"\"\n",
-        "    model = importer_node.importer(\n",
-        "        artifact_uri=resource_uri,\n",
-        "        artifact_class=artifact_types.VertexModel,\n",
-        "        metadata={\"resourceName\": resource_name},\n",
-        "    )\n",
+        "    from kfp.v2.components import importer_node\n",
+        "    from google_cloud_pipeline_components.types import artifact_types\n",
         "    \"\"\"\n",
         "\n",
-        "    # (WORKAROUND  b/219835305)\n",
-        "    model = return_unmanaged_model(\n",
-        "        serving_image=serving_image,\n",
-        "        artifact_uri=artifact_uri,\n",
-        "        resource_name=model_resource_name,\n",
-        "    )\n",
+        "    model = GetVertexModelOp(model_resource_name=model_resource_name)\n",
         "\n",
         "    # Desired sequence: blocked by b/219835305\n",
         "    \"\"\"\n",
@@ -1562,7 +1507,7 @@
         "    # (WORKAROUND  b/219835305)\n",
         "    endpoint = return_unmanaged_endpoint(resource_name=endpoint_resource_name)\n",
         "\n",
-        "    deploy_op = ModelDeployOp(\n",
+        "    _ = ModelDeployOp(\n",
         "        model=model.outputs[\"model\"],\n",
         "        endpoint=endpoint.outputs[\"endpoint\"],\n",
         "        dedicated_resources_min_replica_count=1,\n",
@@ -1591,7 +1536,6 @@
         "\n",
         "- `display_name`: The display name for the generated Vertex AI resources.\n",
         "- `model_resource_name`: The resource name of the existing `Model` resource.\n",
-        "- `model_resource_uri`: The resource uri of the existing `Model` resource.\n",
         "- `endpoint_resource_name`: The resource name of the existing `Endpoint` resource.\n",
         "- `endpoint_resource_uri`: The resource uri of the existing `Endpoint` resource.\n",
         "- `project`: The project ID.\n",
@@ -1614,14 +1558,9 @@
         "        parameter_values={\n",
         "            \"display_name\": \"deploy_model_existing_endpoint_\" + TIMESTAMP,\n",
         "            \"model_resource_name\": model.resource_name,\n",
-        "            \"model_resource_uri\": \"https://us-central1-aiplatform.googleapis.com/v1/\"\n",
-        "            + model.resource_name,\n",
         "            \"endpoint_resource_name\": endpoint.resource_name,\n",
         "            \"endpoint_resource_uri\": \"https://us-central1-aiplatform.googleapis.com/v1/\"\n",
         "            + endpoint.resource_name,\n",
-        "            # Model properties (WORKAROUND  b/219835305)\n",
-        "            \"serving_image\": SERVING_CONTAINER_URI,\n",
-        "            \"artifact_uri\": ARTIFACT_URI,\n",
         "            \"project\": PROJECT_ID,\n",
         "            \"region\": REGION,\n",
         "        },\n",

notebooks/community/ml_ops/stage5/get_started_with_vertex_private_endpoints.ipynb

@@ -385,12 +385,11 @@
         "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",
@@ -1068,7 +1067,6 @@
         "- `model`: The `Model` resource.\n",
         "- `deployed_model_displayed_name`: The human readable name for the deployed model instance.\n",
         "- `machine_type`: The machine type for each VM instance.\n",
-        "- `traffic_split`: Set to `{}` to indicate no traffic split.\n",
         "\n",
         "Do to the requirements to provision the resource, this may take upto a few minutes."
       ]
@@ -1085,7 +1083,6 @@
         "    model=model,\n",
         "    deployed_model_display_name=\"example_\" + TIMESTAMP,\n",
         "    machine_type=DEPLOY_COMPUTE,\n",
-        "    traffic_split={},  # no traffic split\n",
         ")\n",
         "\n",
         "print(endpoint)"
@@ -1187,62 +1184,6 @@
         "    f.write(json.dumps({\"instances\": [{serving_input: {\"b64\": b64str}}]}))"
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "23e995c35fd6"
-      },
-      "source": [
-        "#### Construct the `Private Endpoint` URI\n",
-        "\n",
-        "Next, you construct the URI for the `Private Endpoint`."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "97b248b2efb5"
-      },
-      "outputs": [],
-      "source": [
-        "endpoint_id = endpoint.resource_name\n",
-        "\n",
-        "ENDPOINT_URL = ! gcloud beta ai endpoints describe {endpoint_id} \\\n",
-        "  --region={REGION} \\\n",
-        "  --format=\"value(deployedModels.privateEndpoints.predictHttpUri)\"\n",
-        "\n",
-        "private_url = ENDPOINT_URL[1]\n",
-        "print(private_url)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "27605b5f0c3a"
-      },
-      "source": [
-        "### Make the prediction request using curl\n",
-        "\n",
-        "Use `curl` to make the prediction request to the private URI."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "6cb568e6bb49"
-      },
-      "outputs": [],
-      "source": [
-        "output = ! curl -X POST -d@instances.json $private_url\n",
-        "\n",
-        "predictions = output[5]\n",
-        "print(predictions)\n",
-        "\n",
-        "! rm test.jpg instances.json"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -1251,7 +1192,7 @@
       "source": [
         "### Make the prediction request using SDK\n",
         "\n",
-        "Finally, use the `Vertex AI SDK` to make a prediction request."
+        "Next, use the `Vertex AI SDK` to make a prediction request."
       ]
     },
     {

notebooks/community/ml_ops/stage6/get_started_with_tf_serving.ipynb

@@ -702,7 +702,7 @@
         "        + f\"/{PRIVATE_REPO}\"\n",
         "        + \"/tf_serving:gpu\"\n",
         "    )\n",
-        "    TF_IMAGE = \"tensorflow/serving:latest-gpu\"\n",
+        "    TF_IMAGE = \"tensorflow/serving:2.5.4-gpu\"\n",
         "else:\n",
         "    DEPLOY_IMAGE = (\n",
         "        f\"{REGION}-docker.pkg.dev/\"\n",
@@ -710,15 +710,15 @@
         "        + f\"/{PRIVATE_REPO}\"\n",
         "        + \"/tf_serving:cpu\"\n",
         "    )\n",
-        "    TF_IMAGE = \"tensorflow/serving:latest\"\n",
+        "    TF_IMAGE = \"tensorflow/serving:2.5.4\"\n",
         "\n",
         "if not IS_COLAB:\n",
         "    if DEPLOY_GPU:\n",
-        "        ! sudo docker pull tensorflow/serving:latest-gpu\n",
+        "        ! sudo docker pull tensorflow/serving:2.5.4-gpu\n",
         "    else:\n",
-        "        ! sudo docker pull tensorflow/serving:latest\n",
+        "        ! sudo docker pull tensorflow/serving:2.5.4\n",
         "\n",
-        "    ! docker tag tensorflow/serving $DEPLOY_IMAGE\n",
+        "    ! docker tag $TF_IMAGE $DEPLOY_IMAGE\n",
         "    ! docker push $DEPLOY_IMAGE\n",
         "else:\n",
         "    # install docker daemon\n",
@@ -1434,7 +1434,7 @@
       },
       "outputs": [],
       "source": [
-        "delete_bucket = False\n",
+        "delete_bucket = True\n",
         "delete_model = True\n",
         "delete_endpoint = True\n",
         "delete_batch_job = True\n",

notebooks/community/ml_ops/stage7/get_started_with_model_monitoring_setup.ipynb

@@ -140,8 +140,6 @@
         "id": "8yVpQt-JHKPF"
       },
       "source": [
-        "## Before you begin\n",
-        "\n",
         "### Set up your local development environment\n",
         "\n",
         "**If you are using Colab or Vertex AI Workbench notebooks**, your environment already meets\n",
@@ -254,6 +252,8 @@
         "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",
@@ -502,6 +502,86 @@
         "- For the CSV data source, grant both service accounts the \"Storage Object Viewer\" role."
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "bucket:custom"
+      },
+      "source": [
+        "### Create a Cloud Storage bucket\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "Set the name of your Cloud Storage bucket below, which you use in this tutorial to upload the `input schema` for the monitoring service.\n",
+        "\n",
+        "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": "bucket"
+      },
+      "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": "autoset_bucket"
+      },
+      "outputs": [],
+      "source": [
+        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"[your-bucket-name]\":\n",
+        "    BUCKET_NAME = PROJECT_ID + \"aip-\" + UUID\n",
+        "    BUCKET_URI = \"gs://\" + BUCKET_NAME"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "create_bucket"
+      },
+      "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": "create_bucket"
+      },
+      "outputs": [],
+      "source": [
+        "! gsutil mb -l $REGION $BUCKET_URI"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "validate_bucket"
+      },
+      "source": [
+        "Finally, validate access to your Cloud Storage bucket by examining its contents:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "validate_bucket"
+      },
+      "outputs": [],
+      "source": [
+        "! gsutil ls -al $BUCKET_URI"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -686,7 +766,7 @@
       "source": [
         "## Introduction to Vertex AI Model Monitoring\n",
         "\n",
-        "Vertex AI Model Monitoring is supported for AutoML tabular models and custom tabular model. You can monitor for skew and drift detection of the features in the inbound prediction requests or skew and drift detection of the feature attributions (Explainable AI) in the outbound prediction response -- that is, the distribution of the attributions on how they contributed to the output (predictions).\n",
+        "Vertex AI Model Monitoring is supported for AutoML tabular models and custom tabular models. You can monitor for skew and drift detection of the features in the inbound prediction requests or skew and drift detection of the feature attributions (Explainable AI) in the outbound prediction response -- that is, the distribution of the attributions on how they contributed to the output (predictions).\n",
         "\n",
         "The following are the basic steps to enable model monitoring:\n",
         "\n",
@@ -694,16 +774,16 @@
         "2. Configure a model monitoring specification.\n",
         "3. Upload the model monitoring specification to the `Vertex AI Endpoint`.\n",
         "4. Upload or automatic generation of the `input schema` for parsing.\n",
-        "5. For feature skew detection, upload the training data to automatic generation of the feature distribution.\n",
+        "5. For feature skew detection, upload the training data for automatic generation of the feature distribution.\n",
         "6. For feature attributions, upload corresponding `Vertex AI Explainability` specification.\n",
         "\n",
         "Once configured, you can enable/disable monitoring, change alerts and update the model monitoring configuration. \n",
         "\n",
-        "When model monitoring is enabled, incoming prediction requests are logged in a BigQuery table. The input feature values contained in the logged requests are then analyzed for skew or drift. You can set a sampling rate to monitor a subset of the production inputs to a model.\n",
+        "When model monitoring is enabled, the sampled incoming prediction requests are logged into a BigQuery table. The input feature values contained in the logged requests are then analyzed for skew or drift on an specified interval basis. You set a sampling rate to monitor a subset of the production inputs to a model, and the monitoring interval.\n",
         "\n",
-        "The model monitoring service needs to know how to parse the feature values, which is referred to as the input schema. For AutoML tabular models, the input schema is automatically provided. For custom tabular models, the service will attempt to automatically derive the input schema from the first 1000 prediction requests. Alternatively, one can upload the input schema.\n",
+        "The model monitoring service needs to know how to parse the feature values, which is referred to as the input schema. For AutoML tabular models, the input schema is automatically generated. For custom tabular models, the service will attempt to automatically derive the input schema from the first 1000 prediction requests. Alternatively, one can upload the input schema.\n",
         "\n",
-        "For skew detection, requires a baseline for the statistical distribution of values in the training data. For AutoML tabular models this is automatically derived. For custom tabular models, you upload the training data to the service, and have the service automatically derived the distribution.\n",
+        "For skew detection, the monitoring service requires a baseline for the statistical distribution of values in the training data. For AutoML tabular models this is automatically derived. For custom tabular models, you upload the training data to the service, and have the service automatically derive the distribution.\n",
         "\n",
         "For feature attribution skew and drift detection, requires enabling your deployed model for `Vertex AI Explainability`\n",
         "\n",
@@ -1144,7 +1224,11 @@
       "source": [
         "#### Monitoring Job State\n",
         "\n",
-        "After you start the `Vertex AI Model Monitoring` job, it will be in a `PENDING` state until the `input schema` and `skew distribution baselines` are calculated. The process happens sequentially. In this example where we use automatic generation of the `input schema` will stay in a `PENDING` state until the 1000 prediction request (discussed subsequently) is sent. Once the `input schema` has been generated, then a batch job will be initiated to generate the distribution baseline from the training data. Once the baseline distribution is generated, then the monitoring job will enter `RUNNING` state."
+        "After you start the `Vertex AI Model Monitoring` job, it will be in a `PENDING` state until the `input schema` and `skew distribution baselines` are calculated. The process happens sequentially. In this example where you use automatic generation of the `input schema`, the service stays in a `PENDING` state until the 1000 prediction request (discussed subsequently) is sent. \n",
+        "\n",
+        "Once the `input schema` has been generated, then a batch job will be initiated to generate the distribution baseline from the training data. Again, the service stays in a `PENDING` state until the baseline distribution is calculated.\n",
+        "\n",
+        "Once the baseline distribution is generated, then the monitoring job will enter `OFFLINE` state. On the per interval basis -- e.g., once an hour, the monitoring job will enter `RUNNING` state while analyzing the sampled data. Once completed, it will return to an `OFFLINE` state while awaiting the next scheduled analysis."
       ]
     },
     {
@@ -1243,7 +1327,7 @@
         "\n",
         "### Automatic generation of the baseline distribution\n",
         "\n",
-        "After the `input schema` is generated, the monitoring service creates a batch job to analyze for first 1000 predictions to generate the baseline distribution. Once completed, the monitoring service will be in `RUNNING` state."
+        "After the `input schema` is generated, the monitoring service creates a batch job to analyze the training data to determine the baseline distribution. "
       ]
     },
     {
@@ -1254,16 +1338,9 @@
       },
       "outputs": [],
       "source": [
-        "import time\n",
-        "\n",
-        "while True:\n",
-        "    time.sleep(60)\n",
-        "    jobs = monitoring_job.list(filter=f\"display_name=churn_{UUID}\")\n",
-        "    job = jobs[0]\n",
-        "    print(job.state)\n",
-        "    if job.state == aiplatform.gapic.JobState.JOB_STATE_PENDING:\n",
-        "        continue\n",
-        "    break"
+        "# Pause a bit for the baseline distribution to be calculated\n",
+        "if os.getenv(\"IS_TESTING\"):\n",
+        "    time.sleep(120)"
       ]
     },
     {
@@ -1415,7 +1492,7 @@
       "source": [
         "# Delete the monitoring logged data BigQuery dataset\n",
         "\n",
-        "! bq rm -r -f {PROJECT_ID}:model_deployment_monitoring_{ENDPOINT_ID}"
+        "! bq rm -r -f {PROJECT_ID}.model_deployment_monitoring_{ENDPOINT_ID}"
       ]
     },
     {
@@ -1430,7 +1507,7 @@
         "\n",
         "#### Create the predefined input schema\n",
         "\n",
-        "The predefined `input schema` is specified as a YAML file. In this example, you retrieve the BigQuery schema for the training data, which includes the feature names and data types, to generate the YAML specification.\n",
+        "The predefined `input schema` is specified as a YAML file. In this example, you retrieve the BigQuery schema for the training data, which includes the feature names and data types, to generate the YAML specification. The predefined `input schema` must be loaded to a Cloud Storage location.\n",
         "\n",
         "Learn more about [Custom instance schemas for parsing input](https://cloud.google.com/vertex-ai/docs/model-monitoring/overview#custom-input-schemas)."
       ]
@@ -1475,7 +1552,9 @@
         "print(yaml)\n",
         "\n",
         "with open(\"schema.yaml\", \"w\") as f:\n",
-        "    f.write(yaml)"
+        "    f.write(yaml)\n",
+        "\n",
+        "! gsutil cp schema.yaml {BUCKET_URI}/schema.yaml"
       ]
     },
     {
@@ -1508,7 +1587,7 @@
         "    schedule_config=schedule_config,\n",
         "    alert_config=alerting_config,\n",
         "    objective_configs=objective_config,\n",
-        "    analysis_instance_schema_uri=\"schema.yaml\",\n",
+        "    analysis_instance_schema_uri=f\"{BUCKET_URI}/schema.yaml\",\n",
         ")\n",
         "\n",
         "print(monitoring_job)"
@@ -1588,7 +1667,12 @@
         "id": "18889460bd33"
       },
       "source": [
-        "### Cleanup"
+        "## Cleaning up\n",
+        "\n",
+        "To clean up all Google Cloud resources used in this project, you can [delete the Google Cloud\n",
+        "project](https://cloud.google.com/resource-manager/docs/creating-managing-projects#shutting_down_projects) you used for the tutorial.\n",
+        "\n",
+        "Otherwise, you can delete the individual resources you created in this tutorial."
       ]
     },
     {
@@ -1599,14 +1683,21 @@
       },
       "outputs": [],
       "source": [
-        "! rm -f schema.yaml"
+        "delete_bucket = False\n",
+        "\n",
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil rm -rf {BUCKET_URI}\n",
+        "\n",
+        "! rm -f schema.yaml\n",
+        "\n",
+        "! bq rm -r -f {PROJECT_ID}.model_deployment_monitoring_{ENDPOINT_ID}"
       ]
     }
   ],
   "metadata": {
     "colab": {
       "collapsed_sections": [],
-      "name": "model_monitoring_setup.ipynb",
+      "name": "get_started_with_model_monitoring_setup.ipynb",
       "toc_visible": true
     },
     "kernelspec": {

notebooks/notebook_template_review.py

@@ -56,7 +56,7 @@ def parse_notebook(path):
         # cell 1 is copyright
         nth = 0
         cell, nth = get_cell(path, cells, nth)
-        if not cell['source'][0].startswith('# Copyright'):
+        if not 'Copyright' in cell['source'][0]:
             report_error(path, 0, "missing copyright cell")
             
         # check for notices

notebooks/official/CODEOWNERS

@@ -16,6 +16,7 @@
 /model_monitoring @andrewferlitsch
 /tensorboard @zbl94
 
+/bigquery_ml/bqml-online-prediction.ipynb @polong-lin
 /model_monitoring/model_monitoring.ipynb @mco-gh
 /ml_metadata/sdk-metric-parameter-tracking-for-custom-jobs.ipynb @jialuzh
 /ml_metadata/sdk-metric-parameter-tracking-for-locally-trained-models.ipynb @jialuzh
@@ -28,5 +29,9 @@
 /automl/automl_forecasting_bqml_arima_plus_comparison.ipynb @TheMichaelHu
 /automl/automl_tabular_on_vertex_pipelines.ipynb @helinwang
 /custom/custom_training_tensorboard_profiler.ipynb @itseric
-/workbench/spark/spark_sample_notebook.ipynb @bmiro
+/workbench/spark/spark_sample_notebook.ipynb @bradmiro
+/workbench/spark/spark_ml.ipynb @bradmiro
 /model-registry/bqml-vertexai-model-registry.ipynb @soheilazangeneh
+/workbench/exploratory_data_analysis/explore_data_in_bigquery_with_workbench.ipynb @alokpattani
+/model_evaluation/automl_tabular_classification_model_evaluation.ipynb @soheilazangeneh
+/model_evaluation/automl_tabular_regression_model_evaluation.ipynb @soheilazangeneh

notebooks/official/automl/automl_forecasting_bqml_arima_plus_comparison.ipynb

@@ -176,7 +176,10 @@
         "else:\n",
         "    USER_FLAG = \"\"\n",
         "\n",
-        "! pip3 install --upgrade google-cloud-bigquery[pandas] google-cloud-aiplatform google-cloud-pipeline-components $USER_FLAG"
+        "! (pip3 install --upgrade $USER_FLAG \\\n",
+        "    google-cloud-bigquery[pandas]==2.34.4 \\\n",
+        "    google-cloud-aiplatform==1.16.1 \\\n",
+        "    google-cloud-pipeline-components==1.0.18)"
       ]
     },
     {

notebooks/official/automl/sdk_automl_image_object_detection_batch.ipynb

@@ -8,7 +8,7 @@
       },
       "outputs": [],
       "source": [
-        "# Copyright 2022 Google LLC\n",
+        "# Copyright 2021 Google LLC\n",
         "#\n",
         "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
         "# you may not use this file except in compliance with the License.\n",
@@ -66,17 +66,6 @@
         "This tutorial demonstrates how to use the Vertex AI SDK to create image object detection models and do batch prediction using a Google Cloud [AutoML](https://cloud.google.com/vertex-ai/docs/start/automl-users) model."
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "dataset:salads,iod"
-      },
-      "source": [
-        "### Dataset\n",
-        "\n",
-        "The dataset used for this tutorial is the Salads category of the [OpenImages dataset](https://www.tensorflow.org/datasets/catalog/open_images_v4) from [TensorFlow Datasets](https://www.tensorflow.org/datasets/catalog/overview). This dataset does not require any feature engineering. The version of the dataset you will use in this tutorial is stored in a public Cloud Storage bucket. The trained model predicts the bounding box locations and the corresponding type of salad items in an image from a class of five items: salad, seafood, tomato, baked goods, or cheese."
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -101,6 +90,17 @@
         "* Batch Prediction Service: Does a queued (batch) prediction for the entire set of instances in the background and stores the results in a Cloud Storage bucket when ready."
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "dataset:salads,iod"
+      },
+      "source": [
+        "### Dataset\n",
+        "\n",
+        "The dataset used for this tutorial is the Salads category of the [OpenImages dataset](https://www.tensorflow.org/datasets/catalog/open_images_v4) from [TensorFlow Datasets](https://www.tensorflow.org/datasets/catalog/overview). This dataset does not require any feature engineering. The version of the dataset you will use in this tutorial is stored in a public Cloud Storage bucket. The trained model predicts the bounding box locations and the corresponding type of salad items in an image from a class of five items: salad, seafood, tomato, baked goods, or cheese."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -201,7 +201,7 @@
       },
       "outputs": [],
       "source": [
-        "! pip3 install -U google-cloud-storage $USER_FLAG"
+        "! pip3 install -U --upgrade tensorflow google-cloud-storage $USER_FLAG"
       ]
     },
     {
@@ -213,17 +213,6 @@
         "Install the latest version of *tensorflow* library."
       ]
     },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "install_tensorflow"
-      },
-      "outputs": [],
-      "source": [
-        "! pip3 install --upgrade tensorflow $USER_FLAG"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -383,9 +372,9 @@
         "id": "timestamp"
       },
       "source": [
-        "#### Timestamp\n",
+        "#### UUID\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 the timestamp onto the name of resources you create in this tutorial."
+        "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 uuid for each instance session, and append it onto the name of resources you create in this tutorial."
       ]
     },
     {
@@ -396,9 +385,16 @@
       },
       "outputs": [],
       "source": [
-        "from datetime import datetime\n",
+        "import random\n",
+        "import string\n",
         "\n",
-        "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
+        "\n",
+        "# Generate a uuid of a specifed length(default=8)\n",
+        "def generate_uuid(length: int = 8) -> str:\n",
+        "    return \"\".join(random.choices(string.ascii_lowercase + string.digits, k=length))\n",
+        "\n",
+        "\n",
+        "UUID = generate_uuid()"
       ]
     },
     {
@@ -409,7 +405,7 @@
       "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 Google Cloud Notebooks**, your environment is already authenticated.\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",
@@ -494,7 +490,7 @@
       "outputs": [],
       "source": [
         "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"[your-bucket-name]\":\n",
-        "    BUCKET_URI = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
+        "    BUCKET_URI = \"gs://\" + PROJECT_ID + \"aip-\" + UUID"
       ]
     },
     {
@@ -669,7 +665,7 @@
       "outputs": [],
       "source": [
         "dataset = aiplatform.ImageDataset.create(\n",
-        "    display_name=\"Salads\" + \"_\" + TIMESTAMP,\n",
+        "    display_name=\"Salads\" + \"_\" + UUID,\n",
         "    gcs_source=[IMPORT_FILE],\n",
         "    import_schema_uri=aiplatform.schema.dataset.ioformat.image.bounding_box,\n",
         ")\n",
@@ -717,7 +713,7 @@
       "outputs": [],
       "source": [
         "job = aiplatform.AutoMLImageTrainingJob(\n",
-        "    display_name=\"salads_\" + TIMESTAMP,\n",
+        "    display_name=\"salads_\" + UUID,\n",
         "    prediction_type=\"object_detection\",\n",
         "    multi_label=False,\n",
         "    model_type=\"CLOUD\",\n",
@@ -760,7 +756,7 @@
       "source": [
         "model = job.run(\n",
         "    dataset=dataset,\n",
-        "    model_display_name=\"salads_\" + TIMESTAMP,\n",
+        "    model_display_name=\"salads_\" + UUID,\n",
         "    training_fraction_split=0.8,\n",
         "    validation_fraction_split=0.1,\n",
         "    test_fraction_split=0.1,\n",
@@ -790,7 +786,7 @@
       "outputs": [],
       "source": [
         "# Get model resource ID\n",
-        "models = aiplatform.Model.list(filter=\"display_name=salads_\" + TIMESTAMP)\n",
+        "models = aiplatform.Model.list(filter=\"display_name=salads_\" + UUID)\n",
         "\n",
         "# Get a reference to the Model Service client\n",
         "client_options = {\"api_endpoint\": f\"{REGION}-aiplatform.googleapis.com\"}\n",
@@ -961,7 +957,7 @@
       "outputs": [],
       "source": [
         "batch_predict_job = model.batch_predict(\n",
-        "    job_display_name=\"salads_\" + TIMESTAMP,\n",
+        "    job_display_name=\"salads_\" + UUID,\n",
         "    gcs_source=gcs_input_uri,\n",
         "    gcs_destination_prefix=BUCKET_URI,\n",
         "    machine_type=\"n1-standard-4\",\n",

notebooks/official/bigquery_ml/bqml-online-prediction.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/master/notebooks/community/bigquery_ml/bqml-online-prediction.ipynb\">\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/master/notebooks/official/bigquery_ml/bqml-online-prediction.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/GoogleCloudPlatform/vertex-ai-samples/blob/master/notebooks/community/bigquery_ml/bqml-online-prediction.ipynb\">\n",
+        "    <a href=\"https://github/GoogleCloudPlatform/vertex-ai-samples/blob/master/notebooks/official/bigquery_ml/bqml-online-prediction.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/master/notebooks/community/bigquery_ml/bqml-online-prediction.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/master/notebooks/official/bigquery_ml/bqml-online-prediction.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",
@@ -63,7 +63,7 @@
         "\n",
         "### Dataset\n",
         "\n",
-        "The dataset, [available publicly on BigQuery](https://console.cloud.google.com/bigquery?project=bigquery-public-data&d=ga4_obfuscated_sample_ecommerce&p=bigquery-public-data&page=dataset), comes from obfuscated [Google Analytics 4 data](https://support.google.com/analytics/answer/10937659) from the [Google Merchandise Store](https://shop.googlemerchandisestore.com/).\n",
+        "The dataset, <a href=\"https://console.cloud.google.com/bigquery?project=bigquery-public-data&d=ga4_obfuscated_sample_ecommerce&p=bigquery-public-data&page=dataset\" target=\"_blank\">available publicly on BigQuery</a>, comes from obfuscated <a href=\"https://support.google.com/analytics/answer/10937659\" target=\"_blank\">Google Analytics 4 data</a> from the <a href=\"https://shop.googlemerchandisestore.com/\" target=\"_blank\">Google Merchandise Store</a>).\n",
         "\n",
         "### Objective\n",
         "\n",
@@ -95,9 +95,9 @@
         "* Vertex AI\n",
         "\n",
         "\n",
-        "Learn about [BigQuery Pricing](https://cloud.google.com/bigquery/pricing), [BigQuery ML pricing](https://cloud.google.com/bigquery-ml/pricing), [Vertex AI\n",
-        "pricing](https://cloud.google.com/vertex-ai/pricing), and use the [Pricing\n",
-        "Calculator](https://cloud.google.com/products/calculator/)\n",
+        "Learn about <a href=\"https://cloud.google.com/bigquery/pricing\" target=\"_blank\">BigQuery Pricing</a>, <a href=\"https://cloud.google.com/bigquery-ml/pricing\" target=\"_blank\">BigQuery ML pricing</a>, <a href=\"https://cloud.google.com/vertex-ai/pricing\" target=\"_blank\">Vertex AI\n",
+        "pricing</a>, and use the <a href=\"https://cloud.google.com/products/calculator/\" target=\"_blank\">Pricing\n",
+        "Calculator</a>\n",
         "to generate a cost estimate based on your projected usage."
       ]
     },
@@ -128,18 +128,18 @@
         "* virtualenv\n",
         "* Jupyter notebook running in a virtual environment with Python 3\n",
         "\n",
-        "The Google Cloud guide to [Setting up a Python development\n",
-        "environment](https://cloud.google.com/python/setup) and the [Jupyter\n",
-        "installation guide](https://jupyter.org/install) provide detailed instructions\n",
+        "The Google Cloud guide to <a href=\"https://cloud.google.com/python/setup\" target=\"_blank\">Setting up a Python development\n",
+        "environment</a> and the <a href=\"https://jupyter.org/install\" target=\"_blank\">Jupyter\n",
+        "installation guide</a> provide detailed instructions\n",
         "for meeting these requirements. The following steps provide a condensed set of\n",
         "instructions:\n",
         "\n",
-        "1. [Install and initialize the Cloud SDK.](https://cloud.google.com/sdk/docs/)\n",
+        "1. <a href=\"https://cloud.google.com/sdk/docs/\" target=\"_blank\">Install and initialize the Cloud SDK.</a>\n",
         "\n",
-        "1. [Install Python 3.](https://cloud.google.com/python/setup#installing_python)\n",
+        "1. <a href=\"https://cloud.google.com/python/setup#installing_python\" target=\"_blank\">Install Python 3.</a>\n",
         "\n",
-        "1. [Install\n",
-        "   virtualenv](https://cloud.google.com/python/setup#installing_and_using_virtualenv)\n",
+        "1. <a href=\"https://cloud.google.com/python/setup#installing_and_using_virtualenv\" target=\"_blank\">Install\n",
+        "   virtualenv</a>\n",
         "   and create a virtual environment that uses Python 3. Activate the virtual environment.\n",
         "\n",
         "1. To install Jupyter, run `pip3 install jupyter` on the\n",
@@ -234,13 +234,13 @@
         "\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",
+        "1. <a href=\"https://console.cloud.google.com/cloud-resource-manager\" target=\"_blank\">Select or create a Google Cloud project</a>. 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",
+        "1. <a href=\"https://cloud.google.com/billing/docs/how-to/modify-project\" target=\"_blank\">Make sure that billing is enabled for your project</a>.\n",
         "\n",
-        "1. [Enable the Vertex AI API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com).\n",
+        "1. <a href=\"https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com\" target=\"_blank\">Enable the Vertex AI API</a>.\n",
         "\n",
-        "1. If you are running this notebook locally, you will 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 <a href=\"https://cloud.google.com/sdk\" target=\"_blank\">Cloud SDK</a>.\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",
@@ -267,7 +267,7 @@
       },
       "outputs": [],
       "source": [
-        "PROJECT_ID = \"YOUR-PROJECT-ID\"\n",
+        "PROJECT_ID = \"[YOUR-PROJECT-ID]\"\n",
         "\n",
         "# Get your Google Cloud project ID from gcloud\n",
         "import os\n",
@@ -314,9 +314,9 @@
         "- 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",
+        "You might not be able to 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)."
+        "Learn more about <a href=\"https://cloud.google.com/vertex-ai/docs/general/locations\" target=\"_blank\">Vertex AI regions</a>."
       ]
     },
     {
@@ -339,9 +339,9 @@
         "id": "06571eb4063b"
       },
       "source": [
-        "#### Timestamp\n",
+        "#### UUID\n",
         "\n",
-        "If you are in a live tutorial session, you might be using a shared test account or project. To avoid name collisions between users on resources created, you create a timestamp for each instance session, and append it onto the name of resources you create in this tutorial."
+        "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 uuid for each instance session, and append it onto the name of resources you create in this tutorial."
       ]
     },
     {
@@ -352,9 +352,16 @@
       },
       "outputs": [],
       "source": [
-        "from datetime import datetime\n",
+        "import random\n",
+        "import string\n",
         "\n",
-        "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
+        "\n",
+        "# Generate a uuid of a specifed length(default=8)\n",
+        "def generate_uuid(length: int = 8) -> str:\n",
+        "    return \"\".join(random.choices(string.ascii_lowercase + string.digits, k=length))\n",
+        "\n",
+        "\n",
+        "UUID = generate_uuid()"
       ]
     },
     {
@@ -380,8 +387,7 @@
         "\n",
         "**Otherwise**, follow these steps:\n",
         "\n",
-        "1. In the Cloud Console, go to the [**Create service account key**\n",
-        "   page](https://console.cloud.google.com/apis/credentials/serviceaccountkey).\n",
+        "1. In the Cloud Console, go to the <a href=\"https://console.cloud.google.com/apis/credentials/serviceaccountkey\" target=\"_blank\">**Create service account key** page</a>.\n",
         "\n",
         "2. Click **Create service account**.\n",
         "\n",
@@ -486,7 +492,10 @@
       },
       "outputs": [],
       "source": [
+        "from typing import Union\n",
+        "\n",
         "import google.cloud.aiplatform as vertex_ai\n",
+        "import pandas as pd\n",
         "from google.cloud import bigquery"
       ]
     },
@@ -550,24 +559,17 @@
       "outputs": [],
       "source": [
         "# Wrapper to use BigQuery client to run query/job, return job ID or result as DF\n",
-        "def bq_query(sql):\n",
+        "def run_bq_query(sql: str) -> Union[str, pd.DataFrame]:\n",
         "    \"\"\"\n",
         "    Input: SQL query, as a string, to execute in BigQuery\n",
         "    Returns the query results as a pandas DataFrame, or error, if any\n",
         "    \"\"\"\n",
-        "    # Import Exceptions library to help with dataset error catching\n",
-        "    from google.cloud.exceptions import BadRequest\n",
         "\n",
         "    # Try dry run before executing query to catch any errors\n",
-        "    try:\n",
-        "        job_config = bigquery.QueryJobConfig(dry_run=True, use_query_cache=False)\n",
-        "\n",
-        "        bq_client.query(sql, job_config=job_config)\n",
-        "\n",
-        "    except BadRequest as err:\n",
-        "        print(err)\n",
-        "        return\n",
+        "    job_config = bigquery.QueryJobConfig(dry_run=True, use_query_cache=False)\n",
+        "    bq_client.query(sql, job_config=job_config)\n",
         "\n",
+        "    # If dry run succeeds without errors, proceed to run query\n",
         "    job_config = bigquery.QueryJobConfig()\n",
         "    client_result = bq_client.query(sql, job_config=job_config)\n",
         "\n",
@@ -589,7 +591,7 @@
         "\n",
         "BigQuery ML (BQML) provides the capability to train ML tabular models, such as classification, regression, forecasting, and matrix factorization, in BigQuery using SQL syntax directly. BigQuery ML uses the scalable infrastructure of BigQuery ML so you don't need to set up additional infrastructure for training or batch serving.\n",
         "\n",
-        "Learn more about [BigQuery ML documentation](https://cloud.google.com/bigquery-ml/docs)."
+        "Learn more about <a href=\"https://cloud.google.com/bigquery-ml/docs\" target=\"_blank\">BigQuery ML documentation</a>."
       ]
     },
     {
@@ -600,9 +602,13 @@
       },
       "outputs": [],
       "source": [
-        "BQ_DATASET_NAME = \"ga4_churnprediction\"\n",
+        "BQ_DATASET_NAME = f\"ga4_churnprediction_{UUID}\"\n",
         "\n",
-        "bq_query(f\"\"\"CREATE SCHEMA IF NOT EXISTS {BQ_DATASET_NAME}\"\"\")"
+        "sql_create_dataset = f\"\"\"CREATE SCHEMA IF NOT EXISTS {BQ_DATASET_NAME}\"\"\"\n",
+        "\n",
+        "print(sql_create_dataset)\n",
+        "\n",
+        "run_bq_query(sql_create_dataset)"
       ]
     },
     {
@@ -620,7 +626,7 @@
         "id": "49dd00d5fbe5"
       },
       "source": [
-        "Inpect data that has been pre-processed from [Google Analytics 4 data from the Google Merchandise Store](https://support.google.com/analytics/answer/10937659) so that it can be used for classification. For more information on how this data was prepared, read [this blog post](https://cloud.google.com/blog/topics/developers-practitioners/churn-prediction-game-developers-using-google-analytics-4-ga4-and-bigquery-ml).\n",
+        "Inpect data that has been pre-processed from <a href=\"https://support.google.com/analytics/answer/10937659\" target=\"_blank\">Google Analytics 4 data from the Google Merchandise Store</a> so that it can be used for classification. For more information on how this data was prepared, read <a href=\"https://cloud.google.com/blog/topics/developers-practitioners/churn-prediction-game-developers-using-google-analytics-4-ga4-and-bigquery-ml\" target=\"_blank\">this blog post</a>.\n",
         "\n",
         "As seen below, each row represents a single user, and the columns represent their demographic features, their aggregated behavioral features in the first 24 hours of visiting the Google Merchandise Store, and the label (whether the user churned or returned any time after the first 24 hours)."
       ]
@@ -641,7 +647,7 @@
         "LIMIT\n",
         "    100\n",
         "\"\"\"\n",
-        "bq_query(sql_inspect)"
+        "run_bq_query(sql_inspect)"
       ]
     },
     {
@@ -662,9 +668,9 @@
         "The query below trains a logistic regression model using BigQuery ML. BigQuery resources are used to train the model.\n",
         "\n",
         "In the `OPTIONS` parameter:\n",
-        "* with `model_registry=\"vertex_ai\"`, the BigQuery ML model will automatically be [registered to Vertex AI Model Registry](https://cloud.google.com/vertex-ai/docs/model-registry/model-registry-bqml), which enables you to view all of your registered models and its versions on Google Cloud in one place.\n",
+        "* with `model_registry=\"vertex_ai\"`, the BigQuery ML model will automatically be <a href=\"https://cloud.google.com/vertex-ai/docs/model-registry/model-registry-bqml\" target=\"_blank\">registered to Vertex AI Model Registry</a>, which enables you to view all of your registered models and its versions on Google Cloud in one place.\n",
         "\n",
-        "* `vertex_ai_model_version_aliases allows you to set aliases to help you keep track of your model version ([documentation](https://cloud.google.com/vertex-ai/docs/model-registry/model-alias))."
+        "* `vertex_ai_model_version_aliases allows you to set aliases to help you keep track of your model version (<a href=\"https://cloud.google.com/vertex-ai/docs/model-registry/model-alias\" target=\"_blank\">documentation</a>)."
       ]
     },
     {
@@ -677,7 +683,7 @@
       "source": [
         "# this cell may take ~1 min to run\n",
         "\n",
-        "BQML_MODEL_NAME = \"bqmlmodelchurn\"\n",
+        "BQML_MODEL_NAME = f\"bqml_model_churn_{UUID}\"\n",
         "\n",
         "sql_train_model_bqml = f\"\"\"\n",
         "CREATE OR REPLACE MODEL {BQ_DATASET_NAME}.{BQML_MODEL_NAME}    \n",
@@ -696,7 +702,7 @@
         "\n",
         "print(sql_train_model_bqml)\n",
         "\n",
-        "bq_query(sql_train_model_bqml)"
+        "run_bq_query(sql_train_model_bqml)"
       ]
     },
     {
@@ -714,7 +720,7 @@
         "id": "2aaaae772f67"
       },
       "source": [
-        "With the model created, you can now evaluate the logistic regression model. Behind the scenes, BigQuery ML automatically [split the data](https://cloud.google.com/bigquery-ml/docs/reference/standard-sql/bigqueryml-syntax-create#data_split_method), which makes it easier to quickly train and evaluate models."
+        "With the model created, you can now evaluate the logistic regression model. Behind the scenes, BigQuery ML automatically <a href=\"https://cloud.google.com/bigquery-ml/docs/reference/standard-sql/bigqueryml-syntax-create#data_split_method\" target=\"_blank\">split the data</a>, which makes it easier to quickly train and evaluate models."
       ]
     },
     {
@@ -734,7 +740,7 @@
         "\n",
         "print(sql_evaluate_model)\n",
         "\n",
-        "bq_query(sql_evaluate_model)"
+        "run_bq_query(sql_evaluate_model)"
       ]
     },
     {
@@ -745,7 +751,7 @@
       "source": [
         "These metrics help you understand the performance of the model. \n",
         "\n",
-        "There are various metrics for logistic regression and other model types (full list of metrics can be found in the [documentation](https://cloud.google.com/bigquery-ml/docs/reference/standard-sql/bigqueryml-syntax-evaluate#mlevaluate_output))."
+        "There are various metrics for logistic regression and other model types (full list of metrics can be found in the <a href=\"https://cloud.google.com/bigquery-ml/docs/reference/standard-sql/bigqueryml-syntax-evaluate#mlevaluate_output\" target=\"_blank\">documentation</a>)."
       ]
     },
     {
@@ -765,7 +771,7 @@
       "source": [
         "Make a batch prediction in BigQuery ML on the original training data to check the probability of churn for each of the users, as seen in the `probability` column, with the predicted label under the `predicted_churn` column.\n",
         "\n",
-        "[ML.EXPLAIN_PREDICT](https://cloud.google.com/bigquery-ml/docs/reference/standard-sql/bigqueryml-syntax-explain-predict) has built-in [Explainable AI](https://cloud.google.com/bigquery-ml/docs/reference/standard-sql/bigqueryml-syntax-xai-overview). This allows you to see the top contributing features to each prediction and interpret how it was computed."
+        "<a href=\"https://cloud.google.com/bigquery-ml/docs/reference/standard-sql/bigqueryml-syntax-explain-predict\" target=\"_blank\">ML.EXPLAIN_PREDICT</a> has built-in <a href=\"https://cloud.google.com/bigquery-ml/docs/reference/standard-sql/bigqueryml-syntax-xai-overview\" target=\"_blank\">Explainable AI</a>. This allows you to see the top contributing features to each prediction and interpret how it was computed."
       ]
     },
     {
@@ -787,7 +793,7 @@
         "\n",
         "print(sql_explain_predict)\n",
         "\n",
-        "bq_query(sql_explain_predict)"
+        "run_bq_query(sql_explain_predict)"
       ]
     },
     {
@@ -796,7 +802,7 @@
         "id": "fa1f96c0f452"
       },
       "source": [
-        "Since the `top_feature_attributions` is a nested column, you can unnest the array ([documentation](https://cloud.google.com/bigquery/docs/reference/standard-sql/arrays)) into separate rows for each of the features. In other words, since ML.EXPLAIN_PREDICT provides the top 5 most important features, using `UNNEST` results in 5 rows per prediction:"
+        "Since the `top_feature_attributions` is a nested column, you can unnest the array (<a href=\"https://cloud.google.com/bigquery/docs/reference/standard-sql/arrays\" target=\"_blank\">documentation</a>) into separate rows for each of the features. In other words, since ML.EXPLAIN_PREDICT provides the top 5 most important features, using `UNNEST` results in 5 rows per prediction:"
       ]
     },
     {
@@ -827,7 +833,7 @@
         "\n",
         "print(sql_explain_predict)\n",
         "\n",
-        "bq_query(sql_explain_predict)"
+        "run_bq_query(sql_explain_predict)"
       ]
     },
     {
@@ -847,7 +853,7 @@
       "source": [
         "When the model was trained in BigQuery ML, the line `model_registry=\"vertex_ai\"` registered the model to Vertex AI Model Registry automatically upon completion.\n",
         "\n",
-        "You can view the model on the [Vertex AI Model Registry page](https://console.cloud.google.com/vertex-ai/models), or use the code below to check that it was successfully registered:"
+        "You can view the model on the <a href=\"https://console.cloud.google.com/vertex-ai/models\" target=\"_blank\">Vertex AI Model Registry page</a>, or use the code below to check that it was successfully registered:"
       ]
     },
     {
@@ -858,12 +864,7 @@
       },
       "outputs": [],
       "source": [
-        "print(f\"BQML_MODEL_NAME = {BQML_MODEL_NAME}\")\n",
-        "\n",
-        "models = vertex_ai.Model.list(\n",
-        "    filter=f\"display_name={BQML_MODEL_NAME}\", order_by=\"update_time\"\n",
-        ")\n",
-        "model = models[0]\n",
+        "model = vertex_ai.Model(model_name=BQML_MODEL_NAME)\n",
         "\n",
         "print(model.gca_resource)"
       ]
@@ -883,7 +884,7 @@
         "id": "b6120dcc1ff6"
       },
       "source": [
-        "While BigQuery ML supports batch prediction with [ML.PREDICT](https://cloud.google.com/bigquery-ml/docs/reference/standard-sql/bigqueryml-syntax-predict) and [ML.EXPLAIN_PREDICT](https://cloud.google.com/bigquery-ml/docs/reference/standard-sql/bigqueryml-syntax-explain-predict), BigQuery ML is not suitable for real-time predictions where you need low latency predictions with potentially high frequency of requests.\n",
+        "While BigQuery ML supports batch prediction with <a href=\"https://cloud.google.com/bigquery-ml/docs/reference/standard-sql/bigqueryml-syntax-predict\" target=\"_blank\">ML.PREDICT</a> and <a href=\"https://cloud.google.com/bigquery-ml/docs/reference/standard-sql/bigqueryml-syntax-explain-predict\" target=\"_blank\">ML.EXPLAIN_PREDICT</a>, BigQuery ML is not suitable for real-time predictions where you need low latency predictions with potentially high frequency of requests.\n",
         "\n",
         "In other words, deploying the BigQuery ML model to an endpoint enables you to do online predictions."
       ]
@@ -906,30 +907,6 @@
         "To deploy your model to an endpoint, you will first need to create an endpoint before you deploy the model to it."
       ]
     },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "3ce73125dff6"
-      },
-      "outputs": [],
-      "source": [
-        "def create_endpoint(\n",
-        "    project: str,\n",
-        "    display_name: str,\n",
-        "    location: str,\n",
-        "):\n",
-        "    endpoint = vertex_ai.Endpoint.create(\n",
-        "        display_name=display_name,\n",
-        "        project=project,\n",
-        "        location=location,\n",
-        "    )\n",
-        "\n",
-        "    print(endpoint.display_name)\n",
-        "    print(endpoint.resource_name)\n",
-        "    return endpoint"
-      ]
-    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -938,17 +915,16 @@
       },
       "outputs": [],
       "source": [
-        "endpoint_name = f\"{BQML_MODEL_NAME}-{TIMESTAMP}\"\n",
+        "ENDPOINT_NAME = f\"{BQML_MODEL_NAME}-endpoint\"\n",
         "\n",
-        "print(\n",
-        "    f\"\"\"\n",
-        "PROJECT_ID: {PROJECT_ID},\n",
-        "endpoint_name: {endpoint_name}\n",
-        "REGION: {REGION}\n",
-        "\"\"\"\n",
+        "endpoint = vertex_ai.Endpoint.create(\n",
+        "    display_name=ENDPOINT_NAME,\n",
+        "    project=PROJECT_ID,\n",
+        "    location=REGION,\n",
         ")\n",
         "\n",
-        "create_endpoint(PROJECT_ID, endpoint_name, REGION)"
+        "print(endpoint.display_name)\n",
+        "print(endpoint.resource_name)"
       ]
     },
     {
@@ -966,31 +942,7 @@
         "id": "951ed1693f6b"
       },
       "source": [
-        "List the endpoints to make sure it has successfully been created. You can also view your endpoints on the [Vertex AI Endpoints page](https://console.cloud.google.com/vertex-ai/endpoints?project=polong-contentdev)."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "0a9bad8d9ad4"
-      },
-      "outputs": [],
-      "source": [
-        "endpoint = vertex_ai.Endpoint.list(\n",
-        "    # filter=f'display_name={endpoint_name}', # optional: filter by specific endpoint name\n",
-        "    order_by=\"update_time\"\n",
-        ")\n",
-        "endpoint[-1]"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "2431a4d28d97"
-      },
-      "source": [
-        "Retrieve the endpoint id so you can use it in the next step."
+        "List the endpoints to make sure it has successfully been created. (You can also view your endpoints on the <a href=\"https://console.cloud.google.com/vertex-ai/endpoints\" target=\"_blank\">Vertex AI Endpoints page</a>)."
       ]
     },
     {
@@ -1001,7 +953,7 @@
       },
       "outputs": [],
       "source": [
-        "endpoint[-1].to_dict()"
+        "endpoint.list()"
       ]
     },
     {
@@ -1019,74 +971,19 @@
         "id": "6a90be5b77a2"
       },
       "source": [
-        "With the model, you can now deploy it to an endpoint. "
+        "With the new endpoint, you can now deploy your model."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "af323ea42c5b"
-      },
-      "outputs": [],
-      "source": [
-        "from typing import Dict, Optional, Sequence, Tuple\n",
-        "\n",
-        "\n",
-        "def deploy_model_with_automatic_resources_sample(\n",
-        "    project,\n",
-        "    location,\n",
-        "    model_name: str,\n",
-        "    endpoint: Optional[vertex_ai.Endpoint] = None,\n",
-        "    deployed_model_display_name: Optional[str] = None,\n",
-        "    traffic_percentage: Optional[int] = 0,\n",
-        "    traffic_split: Optional[Dict[str, int]] = None,\n",
-        "    min_replica_count: int = 1,\n",
-        "    max_replica_count: int = 1,\n",
-        "    metadata: Optional[Sequence[Tuple[str, str]]] = (),\n",
-        "    sync: bool = True,\n",
-        "):\n",
-        "    \"\"\"\n",
-        "    model_name: A fully-qualified model resource name or model ID.\n",
-        "          Example: \"projects/123/locations/us-central1/models/456\" or\n",
-        "          \"456\" when project and location are initialized or passed.\n",
-        "    \"\"\"\n",
-        "\n",
-        "    model = vertex_ai.Model(model_name=model_name)\n",
-        "\n",
-        "    model.deploy(\n",
-        "        endpoint=endpoint,\n",
-        "        deployed_model_display_name=deployed_model_display_name,\n",
-        "        traffic_percentage=traffic_percentage,\n",
-        "        traffic_split=traffic_split,\n",
-        "        min_replica_count=min_replica_count,\n",
-        "        max_replica_count=max_replica_count,\n",
-        "        metadata=metadata,\n",
-        "        sync=sync,\n",
-        "    )\n",
-        "\n",
-        "    model.wait()\n",
-        "\n",
-        "    print(model.display_name)\n",
-        "    print(model.resource_name)\n",
-        "    return"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "9e6763369af4"
+        "id": "c70ecc568ee5"
       },
       "outputs": [],
       "source": [
         "# deploying the model to the endpoint may take 10-15 minutes\n",
-        "deploy_model_with_automatic_resources_sample(\n",
-        "    project=PROJECT_ID,\n",
-        "    location=REGION,\n",
-        "    model_name=BQML_MODEL_NAME,\n",
-        "    endpoint=endpoint[-1],\n",
-        ")"
+        "model.deploy(endpoint=endpoint)"
       ]
     },
     {
@@ -1095,7 +992,7 @@
         "id": "c303d779477b"
       },
       "source": [
-        "You can also check on the status of your model by visiting the [Vertex AI Endpoints page](https://console.cloud.google.com/vertex-ai/endpoints)."
+        "You can also check on the status of your model by visiting the <a href=\"https://console.cloud.google.com/vertex-ai/endpoints\" target=\"_blank\">Vertex AI Endpoints page</a>."
       ]
     },
     {
@@ -1168,35 +1065,12 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "2c6093ce9f8a"
+        "id": "b4839f31d2f8"
       },
       "outputs": [],
       "source": [
-        "def endpoint_predict_sample(\n",
-        "    project: str, location: str, instances: list, endpoint: str\n",
-        "):\n",
-        "    endpoint = vertex_ai.Endpoint(endpoint)\n",
-        "\n",
-        "    prediction = endpoint.predict(instances=instances)\n",
-        "    return prediction"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "0c41fd6eeb6f"
-      },
-      "outputs": [],
-      "source": [
-        "prediction_response = endpoint_predict_sample(\n",
-        "    project=PROJECT_ID,\n",
-        "    location=REGION,\n",
-        "    instances=df_sample_requests_list,\n",
-        "    endpoint=endpoint[-1].name,\n",
-        ")\n",
-        "\n",
-        "prediction_response"
+        "prediction = endpoint.predict(df_sample_requests_list)\n",
+        "print(prediction)"
       ]
     },
     {
@@ -1216,7 +1090,7 @@
       },
       "outputs": [],
       "source": [
-        "prediction_response.predictions"
+        "prediction.predictions"
       ]
     },
     {
@@ -1227,8 +1101,8 @@
       "source": [
         "## Cleaning up\n",
         "\n",
-        "To clean up all Google Cloud resources used in this project, you can [delete the Google Cloud\n",
-        "project](https://cloud.google.com/resource-manager/docs/creating-managing-projects#shutting_down_projects) you used for the tutorial.\n",
+        "To clean up all Google Cloud resources used in this project, you can <a href=\"https://cloud.google.com/resource-manager/docs/creating-managing-projects#shutting_down_projects\" target=\"_blank\">delete the Google Cloud\n",
+        "project</a> you used for the tutorial.\n",
         "\n",
         "Otherwise, you can delete the individual resources you created in this tutorial:"
       ]
@@ -1241,18 +1115,12 @@
       },
       "outputs": [],
       "source": [
-        "# MODEL_ID = model.name\n",
+        "# Undeploy model from endpoint and delete endpoint\n",
+        "endpoint.undeploy_all()\n",
+        "endpoint.delete()\n",
         "\n",
-        "ENDPOINT_ID = int(endpoint[-1].name)\n",
-        "\n",
-        "# Undeploy model from endpoint\n",
-        "endpoint[-1].undeploy_all()\n",
-        "\n",
-        "# Delete endpoint resource\n",
-        "! gcloud ai endpoints delete $ENDPOINT_ID --quiet --region $REGION\n",
-        "\n",
-        "# Delete BigQuery ML model\n",
-        "! bq rm -f --model $PROJECT_ID\\:$BQ_DATASET_NAME\\.$BQML_MODEL_NAME"
+        "# Delete BigQuery dataset, including the BigQuery ML model\n",
+        "! bq rm -r -f $PROJECT_ID:$BQ_DATASET_NAME"
       ]
     }
   ],

notebooks/official/custom/custom-tabular-bq-managed-dataset.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/official/custom/custom-tabular-bq-managed-dataset.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/official/custom/custom-tabular-bq-managed-dataset.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",
@@ -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 Vertex AI API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com).\n",
+        "3. [Enable the following APIs: Vertex AI API, Cloud Resource Manager API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,cloudresourcemanager.googleapis.com).\n",
         "\n",
         "4. If you are running this notebook locally, you need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
         "\n",

notebooks/official/experiments/build_model_experimentation_lineage_with_prebuild_code.ipynb

@@ -8,7 +8,7 @@
       },
       "outputs": [],
       "source": [
-        "# Copyright 2022 Google LLC\n",
+        "# Copyright 2021 Google LLC\n",
         "#\n",
         "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
         "# you may not use this file except in compliance with the License.\n",
@@ -54,13 +54,31 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "tvgnzT1CKxrO"
+        "id": "d975c5729f18"
       },
       "source": [
         "## Overview\n",
         "\n",
-        "As a Data Scientist, you want to be able to reuse code path (data preprocessing, feature engineering etc...) that others within your team have written to simplify and standardize all the complex data wrangling. \n",
+        "As a Data Scientist, you want to be able to reuse code path (data preprocessing, feature engineering etc...) that others within your team have written to simplify and standardize all the complex data wrangling. "
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "3a0f8061b9c1"
+      },
+      "source": [
+        "### Objective\n",
         "\n",
+        "In this notebook, you learn how to integrate preprocessing code in a Vertex AI experiments. Also you build the experiment lineage lets you record, analyze, debug, and audit metadata and artifacts produced along your ML journey."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "tvgnzT1CKxrO"
+      },
+      "source": [
         "### Dataset\n",
         "\n",
         "This dataset is the UCI News Aggregator Data Set which contains 422,937 news collected between March 10th, 2014 and August 10th, 2014. Below are example records from the dataset:\n",
@@ -72,13 +90,15 @@
         "|2  |Fed's Charles Plosser sees high bar for change in pace of tapering   |http://www.livemint.com/Politics/H2EvwJSK2VE6OF7iK1g3PP/Feds-Charles-Plosser-sees-high-bar-for-change-in-pace-of-ta.html   |Livemint         |b       |ddUyU0VZz0BRneMioxUPQVP6sIxvM|www.livemint.com   |1394470371207|\n",
         "|3  |US open: Stocks fall after Fed official hints at accelerated tapering|http://www.ifamagazine.com/news/us-open-stocks-fall-after-fed-official-hints-at-accelerated-tapering-294436                |IFA Magazine     |b       |ddUyU0VZz0BRneMioxUPQVP6sIxvM|www.ifamagazine.com|1394470371550|\n",
         "|4  |Fed risks falling 'behind the curve', Charles Plosser says           |http://www.ifamagazine.com/news/fed-risks-falling-behind-the-curve-charles-plosser-says-294430                             |IFA Magazine     |b       |ddUyU0VZz0BRneMioxUPQVP6sIxvM|www.ifamagazine.com|1394470371793|\n",
-        "|5  |Fed's Plosser: Nasty Weather Has Curbed Job Growth                   |http://www.moneynews.com/Economy/federal-reserve-charles-plosser-weather-job-growth/2014/03/10/id/557011                   |Moneynews        |b       |ddUyU0VZz0BRneMioxUPQVP6sIxvM|www.moneynews.com  |1394470372027|\n",
-        "\n",
-        "\n",
-        "### Objective\n",
-        "\n",
-        "In this notebook, you learn how to integrate preprocessing code in a Vertex AI experiments. Also you will build the experiment lineage lets you record, analyze, debug, and audit metadata and artifacts produced along your ML journey.\n",
-        "\n",
+        "|5  |Fed's Plosser: Nasty Weather Has Curbed Job Growth                   |http://www.moneynews.com/Economy/federal-reserve-charles-plosser-weather-job-growth/2014/03/10/id/557011                   |Moneynews        |b       |ddUyU0VZz0BRneMioxUPQVP6sIxvM|www.moneynews.com  |1394470372027|"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "5e2eba58ad71"
+      },
+      "source": [
         "### Costs \n",
         "\n",
         "This tutorial uses billable components of Google Cloud:\n",
@@ -150,7 +170,7 @@
       "source": [
         "### Install additional packages\n",
         "\n",
-        "Install additional package dependencies not installed in your notebook environment, such as TensorFlow or Vertex AI SDK. Use the latest major GA version of each package."
+        "Install additional package dependencies not installed in your notebook environment,TensorFlow or Vertex AI SDK. Use the latest major GA version of each package."
       ]
     },
     {
@@ -175,7 +195,7 @@
         "    USER_FLAG = \"--user\"\n",
         "\n",
         "! pip3 install {USER_FLAG} --upgrade joblib fsspec gcsfs scikit-learn -q\n",
-        "! pip3 install {USER_FLAG} --force-reinstall 'google-cloud-aiplatform>=1.15' -q"
+        "! pip install {USER_FLAG} --upgrade google-cloud-aiplatform -q"
       ]
     },
     {
@@ -208,21 +228,14 @@
         "    app.kernel.do_shutdown(True)"
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "lWEdiXsJg0XY"
-      },
-      "source": [
-        "## Before you begin"
-      ]
-    },
     {
       "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",
@@ -233,7 +246,7 @@
         "\n",
         "1. [Enable APIs](https://console.cloud.google.com/flows/enableapi?apiid=cloudresourcemanager.googleapis.com,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",
+        "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",
@@ -343,9 +356,9 @@
         "id": "06571eb4063b"
       },
       "source": [
-        "#### Timestamp\n",
+        "#### UUID\n",
         "\n",
-        "If you are in a live tutorial session, you might be using a shared test account or project. To avoid name collisions between users on resources created, you create a timestamp for each instance session, and append it onto the name of resources you create in this tutorial."
+        "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 uuid for each instance session, and append it onto the name of resources you create in this tutorial."
       ]
     },
     {
@@ -356,9 +369,16 @@
       },
       "outputs": [],
       "source": [
-        "from datetime import datetime\n",
+        "import random\n",
+        "import string\n",
         "\n",
-        "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
+        "\n",
+        "# Generate a uuid of a specifed length(default=8)\n",
+        "def generate_uuid(length: int = 8) -> str:\n",
+        "    return \"\".join(random.choices(string.ascii_lowercase + string.digits, k=length))\n",
+        "\n",
+        "\n",
+        "UUID = generate_uuid()"
       ]
     },
     {
@@ -370,7 +390,7 @@
         "### Authenticate your Google Cloud account\n",
         "\n",
         "**If you are using Vertex AI Workbench Notebooks**, your environment is already\n",
-        "authenticated. Skip this step."
+        "authenticated."
       ]
     },
     {
@@ -484,7 +504,7 @@
       "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_NAME = PROJECT_ID + \"aip-\" + UUID\n",
         "    BUCKET_URI = f\"gs://{BUCKET_NAME}\""
       ]
     },
@@ -537,17 +557,6 @@
         "### Set project folder"
       ]
     },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "AARD6Fsr-DSi"
-      },
-      "outputs": [],
-      "source": [
-        "DATA_PATH = \"data\""
-      ]
-    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -556,6 +565,7 @@
       },
       "outputs": [],
       "source": [
+        "DATA_PATH = \"data\"\n",
         "!mkdir -m 777 -p {DATA_PATH}"
       ]
     },
@@ -568,17 +578,6 @@
         "### Get the data"
       ]
     },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "3V6W2nIo9FtL"
-      },
-      "outputs": [],
-      "source": [
-        "DATASET_URL = \"https://archive.ics.uci.edu/ml/machine-learning-databases/00359/NewsAggregatorDataset.zip\""
-      ]
-    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -587,6 +586,7 @@
       },
       "outputs": [],
       "source": [
+        "DATASET_URL = \"https://archive.ics.uci.edu/ml/machine-learning-databases/00359/NewsAggregatorDataset.zip\"\n",
         "!wget --no-parent {DATASET_URL} --directory-prefix={DATA_PATH}\n",
         "!mkdir -m 777 -p {DATA_PATH}/temp {DATA_PATH}/raw\n",
         "!unzip {DATA_PATH}/*.zip -d {DATA_PATH}/temp\n",
@@ -662,7 +662,7 @@
         "# Experiments\n",
         "TASK = \"classification\"\n",
         "MODEL_TYPE = \"naivebayes\"\n",
-        "EXPERIMENT_NAME = f\"{TASK}-{MODEL_TYPE}-{TIMESTAMP}\"\n",
+        "EXPERIMENT_NAME = f\"{TASK}-{MODEL_TYPE}-{UUID}\"\n",
         "EXPERIMENT_RUN_NAME = \"run-1\"\n",
         "\n",
         "# Preprocessing\n",
@@ -690,7 +690,7 @@
         "FEATURES = \"title\"\n",
         "TEST_SIZE = 0.2\n",
         "SEED = 8\n",
-        "TRAINED_MODEL_URI = f\"{BUCKET_URI}/deliverables/{TIMESTAMP}\"\n",
+        "TRAINED_MODEL_URI = f\"{BUCKET_URI}/deliverables/{UUID}\"\n",
         "MODEL_NAME = f\"{EXPERIMENT_NAME}-model\""
       ]
     },
@@ -800,7 +800,7 @@
       "source": [
         "#### Create a Dataset Metadata Artifact\n",
         "\n",
-        "First you create the Dataset artifact to track the dataset resource in the Vertex AI ML Metadata and create the experiment lineage."
+        "First you create the Dataset artifact to track the dataset resource in the Vertex ML Metadata and create the experiment lineage."
       ]
     },
     {
@@ -839,7 +839,6 @@
         "Preprocess module\n",
         "\"\"\"\n",
         "\n",
-        "import string\n",
         "\n",
         "import pandas as pd\n",
         "\n",
@@ -869,7 +868,10 @@
       "source": [
         "#### Add the `preprocessing` Execution\n",
         "\n",
-        "You add the preprocessing step to track its execution in the lineage associated to Vertex AI Experiment. "
+        "Vertex AI Experiments supports tracking both executions and artifacts. Executions are steps in an ML workflow that can include but are not limited to data preprocessing, training, and model evaluation. Executions can consume artifacts such as datasets and produce artifacts such as models.\n",
+        "\n",
+        "You add the preprocessing step to track its execution in the lineage associated to Vertex AI Experiment. \n",
+        "For Vertex AI, the parameters are passed inside the message field which we see in the logs. These structures of the logs are predefined."
       ]
     },
     {
@@ -943,7 +945,16 @@
       "source": [
         "#### Create model training module\n",
         "\n",
-        "Below the training module."
+        "Below the training module.\n",
+        "\n",
+        "**get_training_split :** It takes parameters like  x(The data to be split), y(The labels to be split), test_size(The proportion of the data to be reserved for testing) and random_state(The seed used by the random number generator).\n",
+        "This function return training data, testing data , The training labels and The testing labels.\n",
+        "\n",
+        "**get_pipeline :** It return's the model.\n",
+        "\n",
+        "**train_pipeline :** It train the model by using model, training data, training lables and return's the trained model.\n",
+        "\n",
+        "**evaluate_model :** It evaluate the model and return the accuracy of the model.\n"
       ]
     },
     {
@@ -1151,6 +1162,15 @@
         "    exc.assign_output_artifacts([model])"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "e595c893de8d"
+      },
+      "source": [
+        "### Stop Experiment run"
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -1170,7 +1190,7 @@
       "source": [
         "### Visualize Experiment Lineage\n",
         "\n",
-        "Below you will get the link to Vertex AI Metadata UI in the console that will show the experiment lineage."
+        "Below you get the link to Vertex AI Metadata UI in the console that show the experiment lineage."
       ]
     },
     {
@@ -1208,17 +1228,8 @@
       "source": [
         "# Delete experiment\n",
         "exp = vertex_ai.Experiment(EXPERIMENT_NAME)\n",
-        "exp.delete()"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "gW8Ddbr8xaKp"
-      },
-      "outputs": [],
-      "source": [
+        "exp.delete()\n",
+        "\n",
         "# Delete model\n",
         "model_list = vertex_ai.Model.list(filter=f'display_name=\"{MODEL_NAME}\"')\n",
         "for model in model_list:\n",
@@ -1230,22 +1241,15 @@
         "        filter=f'display_name=\"{dataset_name}\"'\n",
         "    )\n",
         "    for dataset in dataset_list:\n",
-        "        dataset.delete()"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "sx_vKniMq9ZX"
-      },
-      "outputs": [],
-      "source": [
+        "        dataset.delete()\n",
+        "\n",
         "# Delete Cloud Storage objects that were created\n",
         "delete_bucket = True\n",
         "\n",
         "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
-        "    ! gsutil -m rm -r $BUCKET_URI"
+        "    ! gsutil -m rm -r $BUCKET_URI\n",
+        "\n",
+        "!rm -Rf {DATA_PATH}"
       ]
     },
     {

notebooks/official/explainable_ai/sdk_automl_tabular_binary_classification_batch_explain.ipynb

@@ -105,7 +105,7 @@
       "source": [
         "### Dataset\n",
         "\n",
-        "The dataset used for this tutorial is the [Bank Marketing](https://pantheon.corp.google.com/storage/browser/_details/cloud-ml-tables-data/bank-marketing.csv) . This dataset does not require any feature engineering. The version of the dataset you use in this tutorial is stored in a public Cloud Storage bucket."
+        "The dataset used for this tutorial is the Bank Marketing. This dataset does not require any feature engineering. The version of the dataset you use in this tutorial is stored in a public Cloud Storage bucket."
       ]
     },
     {

notebooks/official/feature_store/sdk-feature-store.ipynb

@@ -29,6 +29,8 @@
         "id": "JAPoU8Sm5E6e"
       },
       "source": [
+        "# Online and Batch predictions using Vertex AI Feature Store\n",
+        "\n",
         "<table align=\"left\">\n",
         "  <td>\n",
         "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/feature_store/sdk-feature-store.ipynb\">\n",
@@ -51,19 +53,22 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "tvgnzT1CKxrO"
+        "id": "c4aaea3bab5e"
       },
       "source": [
         "## Overview\n",
         "\n",
         "This notebook introduces Vertex AI Feature Store, a managed cloud service for machine learning engineers and data scientists to store, serve, manage and share machine learning features at a large scale.\n",
         "\n",
-        "This notebook assumes that you understand basic Google Cloud concepts such as [Project](https://cloud.google.com/storage/docs/projects), [Storage](https://cloud.google.com/storage) and [Vertex AI](https://cloud.google.com/vertex-ai/docs). Some machine learning knowledge is also helpful but not required.\n",
-        "\n",
-        "### Dataset\n",
-        "\n",
-        "This notebook uses a movie recommendation dataset as an example throughout all the sessions. The task is to train a model to predict if a user is going to watch a movie and serve this model online. \n",
-        "\n",
+        "This notebook assumes that you understand basic Google Cloud concepts such as [Project](https://cloud.google.com/storage/docs/projects), [Storage](https://cloud.google.com/storage) and [Vertex AI](https://cloud.google.com/vertex-ai/docs). Some machine learning knowledge is also helpful but not required.\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "71779c8088bf"
+      },
+      "source": [
         "### Objective\n",
         "\n",
         "In this notebook, you will learn how to use `Vertex AI Feature Store` to import feature data, and to access the feature data for both online serving and offline tasks, such as training.\n",
@@ -79,8 +84,26 @@
         "- Create featurestore, entity type, and feature resources.\n",
         "- Import feature data into `Vertex AI Feature Store` resource.\n",
         "- Serve online prediction requests using the imported features.\n",
-        "- Access imported features in offline jobs, such as training jobs.\n",
+        "- Access imported features in offline jobs, such as training jobs."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "55e01a856f57"
+      },
+      "source": [
+        "### Dataset\n",
         "\n",
+        "This notebook uses a movie recommendation dataset as an example throughout all the sessions. The task is to train a model to predict if a user is going to watch a movie and serve this model online."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "tvgnzT1CKxrO"
+      },
+      "source": [
         "### Costs \n",
         "\n",
         "This tutorial uses billable components of Google Cloud:\n",
@@ -262,7 +285,15 @@
       },
       "outputs": [],
       "source": [
-        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
+        "import os\n",
+        "\n",
+        "PROJECT_ID = \"\"\n",
+        "\n",
+        "# Get your Google Cloud project ID from gcloud\n",
+        "if not os.getenv(\"IS_TESTING\"):\n",
+        "    shell_output = !gcloud config list --format 'value(core.project)' 2>/dev/null\n",
+        "    PROJECT_ID = shell_output[0]\n",
+        "    print(\"Project ID: \", PROJECT_ID)"
       ]
     },
     {
@@ -275,10 +306,7 @@
       "source": [
         "if PROJECT_ID == \"\" or PROJECT_ID is None:\n",
         "    PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}\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)"
+        "print(\"Project ID: \", PROJECT_ID)"
       ]
     },
     {
@@ -320,7 +348,9 @@
       },
       "outputs": [],
       "source": [
-        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+        "REGION = \"[your-region]\"  # @param {type:\"string\"}\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
       ]
     },
     {
@@ -329,9 +359,9 @@
         "id": "timestamp"
       },
       "source": [
-        "#### Timestamp\n",
+        "#### UUID\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 the timestamp onto the name of resources you create in this tutorial."
+        "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 uuid for each instance session, and append it onto the name of resources you create in this tutorial."
       ]
     },
     {
@@ -342,9 +372,16 @@
       },
       "outputs": [],
       "source": [
-        "from datetime import datetime\n",
+        "import random\n",
+        "import string\n",
         "\n",
-        "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
+        "\n",
+        "# Generate a uuid of a specifed length(default=8)\n",
+        "def generate_uuid(length: int = 8) -> str:\n",
+        "    return \"\".join(random.choices(string.ascii_lowercase + string.digits, k=length))\n",
+        "\n",
+        "\n",
+        "UUID = generate_uuid()"
       ]
     },
     {
@@ -441,7 +478,7 @@
       "source": [
         "from google.cloud.aiplatform import Feature, Featurestore\n",
         "\n",
-        "FEATURESTORE_ID = \"movie_prediction\"\n",
+        "FEATURESTORE_ID = \"movie_prediction\" + UUID\n",
         "INPUT_CSV_FILE = \"gs://cloud-samples-data-us-central1/vertex-ai/feature-store/datasets/movie_prediction.csv\"\n",
         "ONLINE_STORE_FIXED_NODE_COUNT = 1"
       ]

notebooks/official/migration/UJ4 Vertex SDK AutoML Tabular Binary Classification.ipynb

@@ -55,7 +55,7 @@
       "source": [
         "### Dataset\n",
         "\n",
-        "The dataset used for this tutorial is the [Bank Marketing](https://pantheon.corp.google.com/storage/browser/_details/cloud-ml-tables-data/bank-marketing.csv) . This dataset does not require any feature engineering. The version of the dataset you will use in this tutorial is stored in a public Cloud Storage bucket."
+        "The dataset used for this tutorial is the Bank Marketing. This dataset does not require any feature engineering. The version of the dataset you will use in this tutorial is stored in a public Cloud Storage bucket."
       ]
     },
     {

notebooks/official/migration/UJ5 Vertex SDK AutoML Image Object Detection.ipynb

@@ -32,18 +32,26 @@
         "# Vertex AI: Vertex AI Migration: AutoML Image Object Detection\n",
         "\n",
         "<table align=\"left\">\n",
+        "\n",
         "  <td>\n",
-        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/ai-platform-samples/blob/master/vertex-ai-samples/tree/master/notebooks/official/migration/UJ5%20Vertex%20SDK%20AutoML%20Image%20Object%20Detection.ipynb\">\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/migration/UJ5 Vertex SDK AutoML Image Object Detection.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/ai-platform-samples/blob/master/vertex-ai-samples/tree/master/notebooks/official/migration/UJ5%20Vertex%20SDK%20AutoML%20Image%20Object%20Detection.ipynb\">\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/migration/UJ5 Vertex SDK AutoML Image Object Detection.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/official/migration/UJ5 Vertex SDK AutoML Image Object Detection.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",
+        "\n",
         "<br/><br/><br/>"
       ]
     },
@@ -119,7 +127,7 @@
       "source": [
         "## Installation\n",
         "\n",
-        "Install the latest version of Vertex SDK for Python."
+        "Install the latest version of Vertex AI SDK for Python."
       ]
     },
     {
@@ -138,7 +146,7 @@
         "else:\n",
         "    USER_FLAG = \"\"\n",
         "\n",
-        "! pip3 install --upgrade google-cloud-aiplatform $USER_FLAG"
+        "! pip3 install --upgrade google-cloud-aiplatform $USER_FLAG -q"
       ]
     },
     {
@@ -150,17 +158,6 @@
         "Install the latest GA version of *google-cloud-storage* library as well."
       ]
     },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "install_storage"
-      },
-      "outputs": [],
-      "source": [
-        "! pip3 install -U google-cloud-storage $USER_FLAG"
-      ]
-    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -169,8 +166,9 @@
       },
       "outputs": [],
       "source": [
-        "if os.getenv(\"IS_TESTING\"):\n",
-        "    ! pip3 install --upgrade tensorflow $USER_FLAG"
+        "! pip3 install -U google-cloud-storage $USER_FLAG -q\n",
+        "\n",
+        "! pip3 install --upgrade tensorflow $USER_FLAG -q"
       ]
     },
     {
@@ -297,7 +295,10 @@
       },
       "outputs": [],
       "source": [
-        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
+        "\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
       ]
     },
     {
@@ -306,9 +307,9 @@
         "id": "timestamp"
       },
       "source": [
-        "#### Timestamp\n",
+        "#### UUID\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 the timestamp onto the name of resources you create in this tutorial."
+        "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 uuid for each instance session, and append it onto the name of resources you create in this tutorial."
       ]
     },
     {
@@ -319,9 +320,16 @@
       },
       "outputs": [],
       "source": [
-        "from datetime import datetime\n",
+        "import random\n",
+        "import string\n",
         "\n",
-        "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
+        "\n",
+        "# Generate a uuid of a specifed length(default=8)\n",
+        "def generate_uuid(length: int = 8) -> str:\n",
+        "    return \"\".join(random.choices(string.ascii_lowercase + string.digits, k=length))\n",
+        "\n",
+        "\n",
+        "UUID = generate_uuid()"
       ]
     },
     {
@@ -332,7 +340,7 @@
       "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",
@@ -367,8 +375,11 @@
         "import os\n",
         "import sys\n",
         "\n",
-        "# If on Google Cloud Notebook, then don't execute this code\n",
-        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\"):\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
+        "IS_COLAB = \"google.colab\" in sys.modules\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
+        "    \"DL_ANACONDA_HOME\"\n",
+        "):\n",
         "    if \"google.colab\" in sys.modules:\n",
         "        from google.colab import auth as google_auth\n",
         "\n",
@@ -404,7 +415,8 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
+        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
+        "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
       ]
     },
     {
@@ -415,8 +427,9 @@
       },
       "outputs": [],
       "source": [
-        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"gs://[your-bucket-name]\":\n",
-        "    BUCKET_NAME = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
+        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"[your-bucket-name]\":\n",
+        "    BUCKET_NAME = PROJECT_ID + \"aip-\" + UUID\n",
+        "    BUCKET_URI = f\"gs://{BUCKET_NAME}\""
       ]
     },
     {
@@ -436,7 +449,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION $BUCKET_NAME"
+        "! gsutil mb -l $REGION -p $PROJECT_ID $BUCKET_URI"
       ]
     },
     {
@@ -456,7 +469,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil ls -al $BUCKET_NAME"
+        "! gsutil ls -al $BUCKET_URI"
       ]
     },
     {
@@ -501,7 +514,7 @@
       },
       "outputs": [],
       "source": [
-        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_NAME)"
+        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_URI)"
       ]
     },
     {
@@ -603,7 +616,7 @@
       "outputs": [],
       "source": [
         "dataset = aip.ImageDataset.create(\n",
-        "    display_name=\"Salads\" + \"_\" + TIMESTAMP,\n",
+        "    display_name=\"Salads\" + \"_\" + UUID,\n",
         "    gcs_source=[IMPORT_FILE],\n",
         "    import_schema_uri=aip.schema.dataset.ioformat.image.bounding_box,\n",
         ")\n",
@@ -688,7 +701,7 @@
       "outputs": [],
       "source": [
         "dag = aip.AutoMLImageTrainingJob(\n",
-        "    display_name=\"salads_\" + TIMESTAMP,\n",
+        "    display_name=\"salads_\" + UUID,\n",
         "    prediction_type=\"object_detection\",\n",
         "    multi_label=False,\n",
         "    model_type=\"CLOUD\",\n",
@@ -742,7 +755,7 @@
       "source": [
         "model = dag.run(\n",
         "    dataset=dataset,\n",
-        "    model_display_name=\"salads_\" + TIMESTAMP,\n",
+        "    model_display_name=\"salads_\" + UUID,\n",
         "    training_fraction_split=0.8,\n",
         "    validation_fraction_split=0.1,\n",
         "    test_fraction_split=0.1,\n",
@@ -815,7 +828,7 @@
       "outputs": [],
       "source": [
         "# Get model resource ID\n",
-        "models = aip.Model.list(filter=\"display_name=salads_\" + TIMESTAMP)\n",
+        "models = aip.Model.list(filter=\"display_name=salads_\" + UUID)\n",
         "\n",
         "# Get a reference to the Model Service client\n",
         "client_options = {\"api_endpoint\": f\"{REGION}-aiplatform.googleapis.com\"}\n",
@@ -945,11 +958,11 @@
         "file_1 = test_item_1.split(\"/\")[-1]\n",
         "file_2 = test_item_2.split(\"/\")[-1]\n",
         "\n",
-        "! gsutil cp $test_item_1 $BUCKET_NAME/$file_1\n",
-        "! gsutil cp $test_item_2 $BUCKET_NAME/$file_2\n",
+        "! gsutil cp $test_item_1 $BUCKET_URI/$file_1\n",
+        "! gsutil cp $test_item_2 $BUCKET_URI/$file_2\n",
         "\n",
-        "test_item_1 = BUCKET_NAME + \"/\" + file_1\n",
-        "test_item_2 = BUCKET_NAME + \"/\" + file_2"
+        "test_item_1 = BUCKET_URI + \"/\" + file_1\n",
+        "test_item_2 = BUCKET_URI + \"/\" + file_2"
       ]
     },
     {
@@ -982,7 +995,7 @@
         "\n",
         "import tensorflow as tf\n",
         "\n",
-        "gcs_input_uri = BUCKET_NAME + \"/test.jsonl\"\n",
+        "gcs_input_uri = BUCKET_URI + \"/test.jsonl\"\n",
         "with tf.io.gfile.GFile(gcs_input_uri, \"w\") as f:\n",
         "    data = {\"content\": test_item_1, \"mime_type\": \"image/jpeg\"}\n",
         "    f.write(json.dumps(data) + \"\\n\")\n",
@@ -1018,9 +1031,9 @@
       "outputs": [],
       "source": [
         "batch_predict_job = model.batch_predict(\n",
-        "    job_display_name=\"salads_\" + TIMESTAMP,\n",
+        "    job_display_name=\"salads_\" + UUID,\n",
         "    gcs_source=gcs_input_uri,\n",
-        "    gcs_destination_prefix=BUCKET_NAME,\n",
+        "    gcs_destination_prefix=BUCKET_URI,\n",
         "    sync=False,\n",
         ")\n",
         "\n",
@@ -1378,60 +1391,25 @@
       },
       "outputs": [],
       "source": [
-        "delete_all = True\n",
+        "# Delete the dataset using the Vertex dataset object\n",
         "\n",
-        "if delete_all:\n",
-        "    # Delete the dataset using the Vertex dataset object\n",
-        "    try:\n",
-        "        if \"dataset\" in globals():\n",
-        "            dataset.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
+        "dataset.delete()\n",
         "\n",
-        "    # Delete the model using the Vertex model object\n",
-        "    try:\n",
-        "        if \"model\" in globals():\n",
-        "            model.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
+        "# Delete the model using the Vertex model object\n",
+        "model.delete()\n",
         "\n",
-        "    # Delete the endpoint using the Vertex endpoint object\n",
-        "    try:\n",
-        "        if \"endpoint\" in globals():\n",
-        "            endpoint.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
+        "# Delete the endpoint using the Vertex endpoint object\n",
+        "endpoint.delete()\n",
         "\n",
-        "    # Delete the AutoML or Pipeline trainig job\n",
-        "    try:\n",
-        "        if \"dag\" in globals():\n",
-        "            dag.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
+        "# Delete the AutoML or Pipeline trainig job\n",
         "\n",
-        "    # Delete the custom trainig job\n",
-        "    try:\n",
-        "        if \"job\" in globals():\n",
-        "            job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
+        "dag.delete()\n",
         "\n",
-        "    # Delete the batch prediction job using the Vertex batch prediction object\n",
-        "    try:\n",
-        "        if \"batch_predict_job\" in globals():\n",
-        "            batch_predict_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
+        "# Delete the batch prediction job using the Vertex batch prediction object\n",
+        "batch_predict_job.delete()\n",
         "\n",
-        "    # Delete the hyperparameter tuning job using the Vertex hyperparameter tuning object\n",
-        "    try:\n",
-        "        if \"hpt_job\" in globals():\n",
-        "            hpt_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    if \"BUCKET_NAME\" in globals():\n",
-        "        ! gsutil rm -r $BUCKET_NAME"
+        "if \"BUCKET_NAME\" in globals():\n",
+        "    ! gsutil rm -r $BUCKET_URI"
       ]
     }
   ],

notebooks/official/model-registry/bqml-vertexai-model-registry.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/official/bigquery-ml/bqml-vertexai-model-registry.ipynb\" target=\"_blank\">\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/model-registry/bqml-vertexai-model-registry.ipynb\" target=\"_blank\">\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/official/bigquery-ml/bqml-vertexai-model-registry.ipynb\" target=\"_blank\">\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/model-registry/bqml-vertexai-model-registry.ipynb\" target=\"_blank\">\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/official/bigquery-ml/bqml-vertexai-model-registry.ipynb\" target=\"_blank\">\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/official/model-registry/bqml-vertexai-model-registry.ipynb\" target=\"_blank\">\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",
@@ -677,7 +677,7 @@
       "source": [
         "### Find the model in the Vertex Model Registry\n",
         "\n",
-        "You can use the `Vertex AI Model list()` method with a filter query to find the automatically registered model."
+        "You can use the `Vertex AI Model()` method with `model_name` parameter to find the automatically registered model."
       ]
     },
     {

notebooks/official/model_monitoring/model_monitoring.ipynb

@@ -223,12 +223,22 @@
         "if IS_WORKBENCH_NOTEBOOK:\n",
         "    USER_FLAG = \"--user\"\n",
         "\n",
+        "# Don't bother installing tensorflow or explainable_ai_sdk on Colab\n",
+        "extra_pkgs = \"tensorflow explainable_ai_sdk\"\n",
+        "if \"google.colab\" in sys.modules:\n",
+        "  extra_pkgs = \"\"\n",
+        "\n",
         "# Install required packages.\n",
-        "! pip3 install {USER_FLAG} --quiet --upgrade google-cloud-aiplatform\n",
-        "! pip3 install {USER_FLAG} --quiet --upgrade tensorflow\n",
-        "! pip3 install {USER_FLAG} --quiet --upgrade explainable_ai_sdk\n",
-        "! pip3 install {USER_FLAG} --quiet --upgrade google-api-python-client google-auth-oauthlib google-auth-httplib2 oauth2client requests\n",
-        "! pip3 install {USER_FLAG} --quiet --upgrade google-cloud-storage==1.32.0"
+        "! pip3 install {USER_FLAG} \\\n",
+        "    google-cloud-aiplatform \\\n",
+        "    explainable_ai_sdk \\\n",
+        "    $extra_pkgs \\\n",
+        "    google-api-python-client \\\n",
+        "    google-auth-oauthlib \\\n",
+        "    google-auth-httplib2 \\\n",
+        "    oauth2client \\\n",
+        "    requests \\\n",
+        "    google-cloud-storage==1.32.0"
       ]
     },
     {
@@ -562,7 +572,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "init_aip:mbsdk,region"
+        "id": "wGa5T9eRR8Mz"
       },
       "outputs": [],
       "source": [

notebooks/official/pipelines/google_cloud_pipeline_components_dataproc_tabular.ipynb

@@ -29,7 +29,7 @@
         "id": "JAPoU8Sm5E6e"
       },
       "source": [
-        "# Vertex AI Pipelines: Loan eligibility prediction using google-cloud-pipeline-components and Spark ML\n",
+        "# Vertex AI Pipelines: Loan eligibility prediction using `google-cloud-pipeline-components` and Spark ML\n",
         "\n",
         "<table align=\"left\">\n",
         "\n",
@@ -206,7 +206,7 @@
         "    \n",
         "!pip3 install {USER_FLAG} --upgrade google-cloud-aiplatform==1.11.0 \\\n",
         "                                    kfp==1.8.11 \\\n",
-        "                                    google-cloud-pipeline-components==1.0.1 --quiet --no-warn-conflicts"
+        "                                    google-cloud-pipeline-components==1.0.18 --quiet --no-warn-conflicts"
       ]
     },
     {
@@ -733,9 +733,7 @@
         "from pathlib import Path as path\n",
         "from typing import NamedTuple\n",
         "\n",
-        "# Part 1 - ML Training\n",
         "from google.cloud import aiplatform as vertex_ai\n",
-        "from google_cloud_pipeline_components import aiplatform as vertex_ai_components\n",
         "from kfp.v2 import compiler, dsl\n",
         "from kfp.v2.dsl import (Artifact, ClassificationMetrics, Condition, Input,\n",
         "                        Metrics, Output, component)"
@@ -763,14 +761,14 @@
         "PIPELINE_ROOT = f\"{BUCKET_URI}/pipelines\"\n",
         "PIPELINE_PACKAGE_PATH = str(BUILD_PATH / f\"pipeline_{UUID}.json\")\n",
         "RUNTIME_CONTAINER_IMAGE = f\"gcr.io/{PROJECT_ID}/{RUNTIME_IMAGE}:{IMAGE_TAG}\"\n",
-        "ML_APPLICATION = \"spark\"\n",
-        "TASK = \"classifier\"\n",
+        "ML_APPLICATION = \"loan-eligibility\"\n",
+        "TASK = \"sparkml\"\n",
         "MODEL_TYPE = \"rfor\"\n",
         "VERSION = \"1.0.0\"\n",
         "MODEL_NAME = f\"{ML_APPLICATION}-{TASK}-{MODEL_TYPE}-{VERSION}\"\n",
+        "ARTIFACT_URI = f\"{BUCKET_URI}/deliverables/bundle/{UUID}\"\n",
         "\n",
         "# Preprocessing\n",
-        "PREPROCESSING_BATCH_ID = f\"data-preprocessing-{UUID}\"\n",
         "PREPROCESSING_PYTHON_FILE_URI = f\"{BUCKET_URI}/src/data_preprocessing.py\"\n",
         "PROCESSED_DATA_URI = f\"{BUCKET_URI}/data/processed\"\n",
         "PREPROCESSING_ARGS = [\n",
@@ -785,7 +783,6 @@
         "GCS_PREPROCESSED_URI = f\"{PROCESSED_DATA_URI}/*/?.csv\"\n",
         "\n",
         "# Training\n",
-        "TRAINING_BATCH_ID = f\"model-training-{UUID}\"\n",
         "TRAINING_PYTHON_FILE_URI = f\"{BUCKET_URI}/src/model_training.py\"\n",
         "MODEL_URI = f\"{BUCKET_URI}/deliverables/model/rfor/{UUID}/train_model\"\n",
         "METRICS_URI = f\"{BUCKET_URI}/deliverables/metrics/rfor/{UUID}/train_metrics.json\"\n",
@@ -800,10 +797,9 @@
         "\n",
         "# Condition\n",
         "AUPR_THRESHOLD = 0.5\n",
-        "AUPR_HYPERTUNE_CONDITION = \"[AUPR_HYPERTUNE]\"\n",
+        "AUPR_HYPERTUNE_CONDITION = \"hypertune\"\n",
         "\n",
         "# Hypertuning\n",
-        "HPT_TRAINING_BATCH_ID = f\"hyper-tuning-{UUID}\"\n",
         "HPT_PYTHON_FILE_URI = f\"{BUCKET_URI}/src/hp_tuning.py\"\n",
         "HPT_MODEL_URI = f\"{BUCKET_URI}/deliverables/model/rfor/{UUID}/model\"\n",
         "HPT_METRICS_URI = f\"{BUCKET_URI}/deliverables/metrics/rfor/{UUID}/metrics.json\"\n",
@@ -814,7 +810,24 @@
         "    HPT_MODEL_URI,\n",
         "    \"--metrics-path\",\n",
         "    HPT_METRICS_URI,\n",
-        "]"
+        "]\n",
+        "HPT_BUNDLE_URI = f\"{ARTIFACT_URI}/model.zip\"\n",
+        "HPT_ARGS = [\n",
+        "    \"--train-path\",\n",
+        "    PROCESSED_DATA_URI,\n",
+        "    \"--model-path\",\n",
+        "    HPT_MODEL_URI,\n",
+        "    \"--metrics-path\",\n",
+        "    HPT_METRICS_URI,\n",
+        "    \"--bundle-path\",\n",
+        "    HPT_BUNDLE_URI,\n",
+        "]\n",
+        "HPT_RUNTIME_PROPERTIES = {\n",
+        "    \"spark.jars.packages\": \"ml.combust.mleap:mleap-spark-base_2.12:0.20.0,ml.combust.mleap:mleap-spark_2.12:0.20.0\"\n",
+        "}\n",
+        "\n",
+        "# Deploy\n",
+        "SERVING_IMAGE_URI = f\"{REGION}-docker.pkg.dev/{PROJECT_ID}/{REPO_NAME}/spark-ml-serving\""
       ]
     },
     {
@@ -843,7 +856,7 @@
         "id": "LB2aM7VyRyZG"
       },
       "source": [
-        "## PART I - Build the Vertex Pipeline to train and deploy a Spark model\n",
+        "## Build the Vertex Pipeline to train and deploy a Spark model\n",
         "\n",
         "In this case, the ML pipeline includes the following steps:\n",
         "\n",
@@ -851,10 +864,16 @@
         "2.   Train an `RandomForestClassifier` with `DataprocPySparkBatchOp`\n",
         "3.   Run a custom component in order to evaluate the model\n",
         "\n",
-        "If the model respects the performance condition, then\n",
+        "If the model respects the performance condition, then:\n",
         "\n",
         "4.   Hypertune the `RandomForestClassifier` with `DataprocPySparkBatchOp`\n",
-        "5.   Register the model in the Vertex AI Model Registry\n"
+        "5.   Serializes the model to MLeap format to use the model outside of Spark.\n",
+        "\n",
+        "If the `deploy_model` pipeline parameter is set to `True`:\n",
+        "\n",
+        "6.   Upload the model to Vertex AI Model Registry.\n",
+        "7.   Creates a Vertex AI endpoint.\n",
+        "8.   Deploys the model to the Vertex AI endpoint for serving online prediction requests.\n"
       ]
     },
     {
@@ -1430,7 +1449,9 @@
         "\n",
         "- `--train-path`: The GCS path of the training sample.\n",
         "- `--model-path`: The GCS path to store the trained model.\n",
-        "- `--metrics-path`: The GCS path to store the metrics of model."
+        "- `--metrics-path`: The GCS path to store the metrics of model.\n",
+        "\n",
+        "The hyperparameter tuning job will also serialize the best performing model to an MLeap bundle, which can be imported to Vertex AI as a model for serving predictions - see the *Serve your model in Vertex AI* section further below."
       ]
     },
     {
@@ -1467,6 +1488,9 @@
         "except ImportError as e:\n",
         "    print('WARN: Something wrong with pyspark library. Please check configuration settings!')\n",
         "    print(e)\n",
+        "    \n",
+        "import mleap.pyspark\n",
+        "from mleap.pyspark.spark_support import SimpleSparkSerializer\n",
         "\n",
         "from pyspark.sql.types import StructType, DoubleType, StringType\n",
         "from pyspark.sql.functions import col, udf\n",
@@ -1572,6 +1596,16 @@
         "        ''',\n",
         "        type=str,\n",
         "        required=True)\n",
+        "    args_parser.add_argument(\n",
+        "        '--bundle-path',\n",
+        "        help='''\n",
+        "        The GCS path to store the exported MLeap bundle. \n",
+        "        Format: \n",
+        "        - locally: /path/to/dir\n",
+        "        - cloud: gs://bucket/path\n",
+        "        ''',\n",
+        "        type=str,\n",
+        "        required=True)\n",
         "    return args_parser.parse_args()\n",
         "\n",
         "\n",
@@ -1728,6 +1762,7 @@
         "    train_path = args.train_path\n",
         "    model_path = args.model_path\n",
         "    metrics_path = args.metrics_path\n",
+        "    bundle_path = args.bundle_path\n",
         "\n",
         "    try:\n",
         "        logger.info('initializing pipeline training.')\n",
@@ -1759,10 +1794,20 @@
         "        logger.info(f'load model pipeline in {model_path}.')\n",
         "        pipeline_model.write().overwrite().save(model_path)\n",
         "\n",
-        "        logger.info(f'Upload metrics under {metrics_path}.')\n",
+        "        logger.info(f'upload metrics under {metrics_path}.')\n",
         "        bucket = urlparse(model_path).netloc\n",
         "        metrics_file_path = urlparse(metrics_path).path.strip('/')\n",
         "        write_metrics(bucket, metrics, metrics_file_path)\n",
+        "        \n",
+        "        logger.info('export MLeap bundle to temporary location')\n",
+        "        pipeline_model.bestModel.serializeToBundle(f'jar:file:/tmp/bundle.zip', predictions)\n",
+        "        \n",
+        "        logger.info(f'upload MLeap bundle to {bundle_path}')\n",
+        "        bundle_file_path = urlparse(bundle_path).path.strip('/')\n",
+        "        bucket = urlparse(bundle_path).netloc\n",
+        "        logger.info(f'Copying /tmp/bundle.zip to bucket {bucket} using object name {bundle_file_path} ...')\n",
+        "        upload_file(bucket, '/tmp/bundle.zip', bundle_file_path)\n",
+        "        \n",
         "    except RuntimeError as main_error:\n",
         "        logger.error(main_error)\n",
         "    else:\n",
@@ -1807,11 +1852,11 @@
         "id": "68nYBB5GS9TB"
       },
       "source": [
-        "### Build a custom dataproc serverless image\n",
+        "### Build a custom Dataproc Serverless container image\n",
         "\n",
-        "The `DataprocPySparkBatchOp` allows you to pass custom image that you use when the [provided Dataproc Serverless runtime versions](https://cloud.google.com/dataproc-serverless/docs/concepts/versions/spark-runtime-versions) does not respect your requirements. \n",
+        "Dataproc Serverless provides [default runtime images](https://cloud.google.com/dataproc-serverless/docs/concepts/versions/spark-runtime-versions). You can also use custom container images for your Dataproc Serverless workloads. \n",
         "\n",
-        "**Note:** This step is optional and is included here for general awareness."
+        "The steps in this section builds a custom container image that includes additional dependencies. The custom container image can be specified when using the `DataprocPySparkBatchOp` component to launch the workload within a pipeline."
       ]
     },
     {
@@ -1820,7 +1865,7 @@
         "id": "GF9_5IGYqLAX"
       },
       "source": [
-        "#### Define the Dataproc serverless custom runtime image"
+        "#### Define the Dataproc Serverless custom runtime image"
       ]
     },
     {
@@ -1891,7 +1936,8 @@
         "      python \\\n",
         "      scikit-image \\\n",
         "      scikit-learn \\\n",
-        "      scipy  \n",
+        "      scipy \\\n",
+        "      mleap\n",
         "\n",
         "# (Required) Create the 'spark' group/user.\n",
         "# The GID and UID must be 1099. Home directory is required.\n",
@@ -1927,7 +1973,9 @@
         "id": "ZXzI2xInqb3V"
       },
       "source": [
-        "#### Build the Dataproc serverless custom runtime using Google Cloud Build"
+        "#### Build the Dataproc Serverless custom runtime using Google Cloud Build\n",
+        "\n",
+        "**Note:** this step may take approximately 5 to 10 minutes to complete."
       ]
     },
     {
@@ -2104,12 +2152,12 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "1-Ccx4uLDz4N"
+        "id": "28f3d22dd97f"
       },
       "source": [
-        "#### Model registration custom component\n",
+        "#### Create component for passing args to hyperparameter tuning component\n",
         "\n",
-        "Define a component to create a model resource for the trained model on Vertex AI Model registry."
+        "The following component passes the args `--train-path`, `--model-path` and `--metrics-path`, and `--bundle-path` in the required format for the hyperparamter tuning function defined earlier."
       ]
     },
     {
@@ -2120,22 +2168,230 @@
       },
       "outputs": [],
       "source": [
-        "# TODO: Build a custom compiler using Spark docker image to compile the Mleap bundle\n",
-        "\n",
-        "\n",
         "@component(base_image=\"python:3.8-slim\")\n",
-        "def register_model(\n",
-        "    artifact_uri: str,\n",
-        "    model: Output[Artifact],\n",
-        ") -> NamedTuple(\"Outputs\", [(\"uri\", str)]):\n",
+        "def build_hpt_args(\n",
+        "    dataset_uri: Input[Artifact],\n",
+        "    train_path: str,\n",
+        "    model_path: str,\n",
+        "    metrics_path: str,\n",
+        "    bundle_path: str,\n",
+        ") -> list:\n",
+        "    return [\n",
+        "        \"--train-path\",\n",
+        "        train_path,\n",
+        "        \"--model-path\",\n",
+        "        model_path,\n",
+        "        \"--metrics-path\",\n",
+        "        metrics_path,\n",
+        "        \"--bundle-path\",\n",
+        "        bundle_path,\n",
+        "    ]"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0db73fff95b3"
+      },
+      "source": [
+        "### (Optional) Serve your model using Vertex AI\n",
         "\n",
-        "    component_outputs = NamedTuple(\n",
-        "        \"Outputs\",\n",
-        "        [\n",
-        "            (\"uri\", str),\n",
-        "        ],\n",
-        "    )\n",
-        "    return component_outputs(artifact_uri)"
+        "The hyperparameter tuning task exports the best performing model as an MLeap bundle. The MLeap bundle can be imported into the Vertex AI Model Registry and used for prediction serving. See [Serving Spark ML model using Vertex AI](https://cloud.google.com/architecture/spark-ml-model-with-vertexai) for more information.\n",
+        "\n",
+        "Enable import of the MLeap bundle into the Vertex AI Model Registry and online prediction serving."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "2d7e7c8fc21b"
+      },
+      "outputs": [],
+      "source": [
+        "# Set DEPLOY_MODEL to True\n",
+        "DEPLOY_MODEL = False"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0bb792622d9f"
+      },
+      "source": [
+        "### Build the model serving container image\n",
+        "\n",
+        "A *serving container image* is required to import your model into the Model Registry. The serving container image provides the model serving implementation for the model. The following replicates the instructions from [Serving Spark ML model using Vertex AI](https://cloud.google.com/architecture/spark-ml-model-with-vertexai) to build the serving container image.\n",
+        "\n",
+        "**Note:** this step may take approximately 5 to 10 minutes to complete."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "4703a0f969a3"
+      },
+      "outputs": [],
+      "source": [
+        "DEPLOY_MODEL_CONDITION = 'deploy'\n",
+        "\n",
+        "if DEPLOY_MODEL:\n",
+        "\n",
+        "    import os\n",
+        "    \n",
+        "    CWD = os.getcwd()\n",
+        "\n",
+        "    # Clone and build the scala-sbt cloud builder\n",
+        "    ! git clone https://github.com/GoogleCloudPlatform/cloud-builders-community.git\n",
+        "    ! cd ${CWD}/cloud-builders-community/scala-sbt && \\\n",
+        "        gcloud builds submit .\n",
+        "\n",
+        "    # Clone and build the serving container code\n",
+        "    ! cd {CWD} && git clone https://github.com/GoogleCloudPlatform/vertex-ai-spark-ml-serving.git\n",
+        "    ! cd {CWD}/vertex-ai-spark-ml-serving && \\\n",
+        "        gcloud builds submit --config=cloudbuild.yaml \\\n",
+        "            --substitutions=\"_LOCATION={REGION},_REPOSITORY={REPO_NAME},_IMAGE=spark-ml-serving\" ."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "947b51adc087"
+      },
+      "source": [
+        "### Create component for importing a model artifact into a pipeline\n",
+        "\n",
+        "The pipeline uses the `ModelImportOp` component to import (upload) a model to Vertex AI Model Registry.\n",
+        "\n",
+        "The `import_model_artifact` python component creates a model artifact that can be passed to the `ModelImportOp` component."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "2ed96e7ad046"
+      },
+      "outputs": [],
+      "source": [
+        "@dsl.component(\n",
+        "    base_image=\"python:3.8-slim\",\n",
+        "    packages_to_install=[\"google-cloud-aiplatform\"],\n",
+        ")\n",
+        "def import_model_artifact(\n",
+        "    model: dsl.Output[dsl.Artifact], artifact_uri: str, serving_image_uri: str\n",
+        "):\n",
+        "    model.metadata[\"containerSpec\"] = {\n",
+        "        \"imageUri\": serving_image_uri,\n",
+        "        \"healthRoute\": \"/health\",\n",
+        "        \"predictRoute\": \"/predict\",\n",
+        "    }\n",
+        "    model.uri = artifact_uri"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0d83d9e80923"
+      },
+      "source": [
+        "The serving container requires the model schema in JSON format, which is read during container startup. See [Provide the model schema](https://cloud.google.com/architecture/spark-ml-model-with-vertexai#provide_the_model_schema) for more information.\n",
+        "\n",
+        "Write the model schema file:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "521d2f4d7992"
+      },
+      "outputs": [],
+      "source": [
+        "%%writefile $SRC/schema.json\n",
+        "{\n",
+        "  \"input\": [\n",
+        "    {\n",
+        "      \"name\": \"loan_amount\",\n",
+        "      \"type\": \"DOUBLE\"\n",
+        "    },\n",
+        "    {\n",
+        "      \"name\": \"loan_term\",\n",
+        "      \"type\": \"STRING\"\n",
+        "    },\n",
+        "    {\n",
+        "      \"name\": \"property_area\",\n",
+        "      \"type\": \"STRING\"\n",
+        "    },\n",
+        "    {\n",
+        "      \"name\": \"feature_7\",\n",
+        "      \"type\": \"DOUBLE\"\n",
+        "    },\n",
+        "    {\n",
+        "      \"name\": \"feature_3\",\n",
+        "      \"type\": \"DOUBLE\"\n",
+        "    },\n",
+        "    {\n",
+        "      \"name\": \"feature_1\",\n",
+        "      \"type\": \"DOUBLE\"\n",
+        "    },\n",
+        "    {\n",
+        "      \"name\": \"feature_9\",\n",
+        "      \"type\": \"DOUBLE\"\n",
+        "    },\n",
+        "    {\n",
+        "      \"name\": \"feature_5\",\n",
+        "      \"type\": \"DOUBLE\"\n",
+        "    },\n",
+        "    {\n",
+        "      \"name\": \"feature_0\",\n",
+        "      \"type\": \"DOUBLE\"\n",
+        "    },\n",
+        "    {\n",
+        "      \"name\": \"feature_8\",\n",
+        "      \"type\": \"DOUBLE\"\n",
+        "    },\n",
+        "    {\n",
+        "      \"name\": \"feature_4\",\n",
+        "      \"type\": \"DOUBLE\"\n",
+        "    },\n",
+        "    {\n",
+        "      \"name\": \"feature_2\",\n",
+        "      \"type\": \"DOUBLE\"\n",
+        "    },\n",
+        "    {\n",
+        "      \"name\": \"feature_6\",\n",
+        "      \"type\": \"DOUBLE\"\n",
+        "    }\n",
+        "  ],\n",
+        "  \"output\": [\n",
+        "    {\n",
+        "      \"name\": \"prediction\",\n",
+        "      \"type\": \"DOUBLE\"\n",
+        "    }\n",
+        "  ]\n",
+        "}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "d0b88e26570a"
+      },
+      "source": [
+        "Copy the model schema configuration file to GCS. The serving container reads the model schema file location from the `AIP_STORAGE_URI` environment at startup. See [Import the model into Vertex AI](https://cloud.google.com/architecture/spark-ml-model-with-vertexai#import-the-model-into-vertex-ai) for more information."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "b7763bb558f3"
+      },
+      "outputs": [],
+      "source": [
+        "! gsutil cp $SRC/schema.json $ARTIFACT_URI/schema.json"
       ]
     },
     {
@@ -2159,30 +2415,35 @@
       "source": [
         "@dsl.pipeline(name=PIPELINE_NAME, description=\"A pipeline to train a PySpark model.\")\n",
         "def pipeline(\n",
-        "    preprocessing_batch_id: str = PREPROCESSING_BATCH_ID,\n",
         "    preprocessing_main_python_file_uri: str = PREPROCESSING_PYTHON_FILE_URI,\n",
         "    train_data_path: str = FEATURES_TRAIN_URI,\n",
         "    preprocessed_data_path: str = PROCESSED_DATA_URI,\n",
         "    dataset_name: str = DATASET_NAME,\n",
         "    dataset_uri: str = GCS_PREPROCESSED_URI,\n",
-        "    training_batch_id: str = TRAINING_BATCH_ID,\n",
         "    training_main_python_file_uri: str = TRAINING_PYTHON_FILE_URI,\n",
         "    train_path: str = PROCESSED_DATA_URI,\n",
         "    model_path: str = MODEL_URI,\n",
         "    metrics_path: str = METRICS_URI,\n",
         "    threshold: float = AUPR_THRESHOLD,\n",
-        "    hpt_batch_id: str = HPT_TRAINING_BATCH_ID,\n",
         "    hpt_main_python_file_uri: str = HPT_PYTHON_FILE_URI,\n",
         "    hpt_model_path: str = HPT_MODEL_URI,\n",
         "    hpt_metrics_path: str = HPT_METRICS_URI,\n",
+        "    hpt_bundle_path: str = HPT_BUNDLE_URI,\n",
         "    custom_container_image: str = RUNTIME_CONTAINER_IMAGE,\n",
         "    model_name: str = MODEL_NAME,\n",
         "    project_id: str = PROJECT_ID,\n",
         "    location: str = REGION,\n",
+        "    deploy_model: bool = DEPLOY_MODEL,\n",
+        "    artifact_uri: str = ARTIFACT_URI,\n",
+        "    serving_image_uri: str = SERVING_IMAGE_URI,\n",
         "):\n",
-        "\n",
-        "    from google_cloud_pipeline_components.experimental.dataproc import \\\n",
+        "    from google_cloud_pipeline_components.v1.dataproc import \\\n",
         "        DataprocPySparkBatchOp\n",
+        "    from google_cloud_pipeline_components.v1.dataset import \\\n",
+        "        TabularDatasetCreateOp\n",
+        "    from google_cloud_pipeline_components.v1.endpoint import (EndpointCreateOp,\n",
+        "                                                              ModelDeployOp)\n",
+        "    from google_cloud_pipeline_components.v1.model import ModelUploadOp\n",
         "\n",
         "    # build preprocessed data args\n",
         "    build_preprocessing_args_op = build_preprocessing_args(\n",
@@ -2194,13 +2455,12 @@
         "        project=project_id,\n",
         "        location=location,\n",
         "        container_image=custom_container_image,\n",
-        "        batch_id=preprocessing_batch_id,\n",
         "        main_python_file_uri=preprocessing_main_python_file_uri,\n",
         "        args=build_preprocessing_args_op.output,\n",
         "    ).after(build_preprocessing_args_op)\n",
         "\n",
         "    # create dataset\n",
-        "    create_dataset_op = vertex_ai_components.TabularDatasetCreateOp(\n",
+        "    create_dataset_op = TabularDatasetCreateOp(\n",
         "        display_name=dataset_name,\n",
         "        gcs_source=dataset_uri,\n",
         "        project=project_id,\n",
@@ -2220,7 +2480,6 @@
         "        project=project_id,\n",
         "        location=location,\n",
         "        container_image=custom_container_image,\n",
-        "        batch_id=training_batch_id,\n",
         "        main_python_file_uri=training_main_python_file_uri,\n",
         "        args=build_training_args_op.output,\n",
         "    ).after(build_training_args_op)\n",
@@ -2233,11 +2492,12 @@
         "        name=AUPR_HYPERTUNE_CONDITION,\n",
         "    ):\n",
         "\n",
-        "        build_hpt_args_op = build_training_args(\n",
+        "        build_hpt_args_op = build_hpt_args(\n",
         "            dataset_uri=create_dataset_op.output,\n",
         "            train_path=train_path,\n",
         "            model_path=hpt_model_path,\n",
         "            metrics_path=hpt_metrics_path,\n",
+        "            bundle_path=hpt_bundle_path,\n",
         "        ).after(evaluate_model_op)\n",
         "\n",
         "        # hyperparameter tuning\n",
@@ -2245,13 +2505,46 @@
         "            project=project_id,\n",
         "            location=location,\n",
         "            container_image=custom_container_image,\n",
-        "            batch_id=hpt_batch_id,\n",
         "            main_python_file_uri=hpt_main_python_file_uri,\n",
         "            args=build_hpt_args_op.output,\n",
+        "            runtime_config_properties=HPT_RUNTIME_PROPERTIES,\n",
         "        ).after(model_traning_op)\n",
         "\n",
-        "        # upload model\n",
-        "        register_model(artifact_uri=hpt_model_path).after(hyperparameter_tuning_op)"
+        "        # evaluate condition to upload and deploy model to Vertex AI\n",
+        "        with Condition(\n",
+        "            # kfp casts `bool` parameter to `str`\n",
+        "            deploy_model == \"True\",\n",
+        "            name=DEPLOY_MODEL_CONDITION,\n",
+        "        ):\n",
+        "            # import the model into the pipeline as a kfp model artifact\n",
+        "            import_model_artifact_op = import_model_artifact(\n",
+        "                artifact_uri=artifact_uri,\n",
+        "                serving_image_uri=serving_image_uri,\n",
+        "            )\n",
+        "\n",
+        "            # upload model to Vertex AI\n",
+        "            model_upload_op = ModelUploadOp(\n",
+        "                project=project_id,\n",
+        "                location=location,\n",
+        "                display_name=model_name,\n",
+        "                unmanaged_container_model=import_model_artifact_op.outputs[\"model\"],\n",
+        "            ).after(hyperparameter_tuning_op)\n",
+        "\n",
+        "            # create a serving endpoint\n",
+        "            endpoint_op = EndpointCreateOp(\n",
+        "                project=project_id,\n",
+        "                location=location,\n",
+        "                display_name=model_name,\n",
+        "            ).after(model_upload_op)\n",
+        "\n",
+        "            # deploy  model to the serving endpoint\n",
+        "            _ = ModelDeployOp(\n",
+        "                model=model_upload_op.outputs[\"model\"],\n",
+        "                endpoint=endpoint_op.outputs[\"endpoint\"],\n",
+        "                dedicated_resources_machine_type=\"n1-standard-2\",\n",
+        "                dedicated_resources_min_replica_count=1,\n",
+        "                dedicated_resources_max_replica_count=1,\n",
+        "            ).after(endpoint_op)"
       ]
     },
     {
@@ -2327,6 +2620,65 @@
         "pipeline.wait()"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "b584afa5a1b1"
+      },
+      "source": [
+        "### (Optional) Get online predictions from the deployed model\n",
+        "\n",
+        "You can request online predictions if the model was deployed to a Vertex AI endpoint. Use the `google-cloud-aiplatform` client library to request predictions, or use `curl` as per below:\n",
+        "\n",
+        "Create the prediction request payload with the instances that you want to predict:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "12d068e1877c"
+      },
+      "outputs": [],
+      "source": [
+        "%%writefile instances.json\n",
+        "{\n",
+        "    \"instances\": [\n",
+        "        [214.0, \"360\", \"Rural\", 2.13, 2.21, 0.0, 0.0, 2.31, 2.01, 0.0, 0.0, 0.0, 0.0],\n",
+        "        [213.0, \"360\", \"Semiurban\", 2.03, 2.11, 0.0, 0.0, 2.13, 2.02, 0.0, 0.0, 0.0, 0.0]\n",
+        "    ]\n",
+        "}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "b7cbfec4537d"
+      },
+      "source": [
+        "Use `curl` to send the prediction request to the Vertex AI endpoint. The response contains the predicted label (`0 == not eligible`, `1 == eligible`) for each instance sent in the request payload."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "b1617d6e8a3d"
+      },
+      "outputs": [],
+      "source": [
+        "ENDPOINT_ID=!(gcloud ai endpoints list \\\n",
+        "              --region={REGION} \\\n",
+        "              --filter=display_name={MODEL_NAME} \\\n",
+        "              --format='value(name)')\n",
+        "\n",
+        "!curl -X POST \\\n",
+        "   -H \"Authorization: Bearer $(gcloud auth print-access-token)\" \\\n",
+        "   -H \"Content-Type: application/json\" \\\n",
+        "   https://{REGION}-aiplatform.googleapis.com/v1/projects/{PROJECT_ID}/locations/us-central1/endpoints/{ENDPOINT_ID[-1]}:predict \\\n",
+        "   -d \"@instances.json\""
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -2352,8 +2704,14 @@
         "# Delete pipeline\n",
         "pipeline.delete()\n",
         "\n",
+        "# Delete endpoints\n",
+        "endpoint_list = vertex_ai.Endpoint.list(filter=f'display_name=\"{MODEL_NAME}\"')\n",
+        "for endpoint in endpoint_list:\n",
+        "    endpoint.undeploy_all()\n",
+        "    endpoint.delete()\n",
+        "\n",
         "# Delete model\n",
-        "model_list = vertex_ai.TabularDataset.list(filter=f'display_name=\"{MODEL_NAME}\"')\n",
+        "model_list = vertex_ai.Model.list(filter=f'display_name=\"{MODEL_NAME}\"')\n",
         "for model in model_list:\n",
         "    model.delete()\n",
         "\n",

notebooks/official/pipelines/metrics_viz_run_compare_kfp.ipynb

@@ -64,30 +64,6 @@
         "This notebook shows how to use [the Kubeflow Pipelines (KFP) SDK](https://www.kubeflow.org/docs/components/pipelines/) to build [Vertex AI Pipelines](https://cloud.google.com/vertex-ai/docs/pipelines) that generate model metrics and metrics visualizations, and comparing pipeline runs."
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "dataset:wine,lcn,sklearn"
-      },
-      "source": [
-        "### Datasets\n",
-        "\n",
-        "The dataset used for this tutorial is the [Wine dataset](https://archive.ics.uci.edu/ml/datasets/wine) from [Scikit-learn builtin datasets](https://scikit-learn.org/stable/datasets.html).\n",
-        "\n",
-        "The dataset predicts the origin of a wine."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "dataset:iris,lcn,sklearn"
-      },
-      "source": [
-        "The dataset used for this tutorial is the [Iris dataset](https://scikit-learn.org/stable/auto_examples/datasets/plot_iris_dataset.html) from [Scikit-learn builtin datasets](https://scikit-learn.org/stable/datasets.html).\n",
-        "\n",
-        "The dataset predicts the type of Iris flower species from a class of three species: setosa, virginica, or versicolor."
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -112,6 +88,30 @@
         "- Compare metrics across pipeline runs"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "dataset:wine,lcn,sklearn"
+      },
+      "source": [
+        "### Datasets\n",
+        "\n",
+        "The dataset used for this tutorial is the [Wine dataset](https://archive.ics.uci.edu/ml/datasets/wine) from [Scikit-learn builtin datasets](https://scikit-learn.org/stable/datasets.html).\n",
+        "\n",
+        "The dataset predicts the origin of a wine."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "dataset:iris,lcn,sklearn"
+      },
+      "source": [
+        "The dataset used for this tutorial is the [Iris dataset](https://scikit-learn.org/stable/auto_examples/datasets/plot_iris_dataset.html) from [Scikit-learn builtin datasets](https://scikit-learn.org/stable/datasets.html).\n",
+        "\n",
+        "The dataset predicts the type of Iris flower species from a class of three species: setosa, virginica, or versicolor."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -202,7 +202,7 @@
         "! pip3 install {USER_FLAG} kfp google-cloud-pipeline-components --upgrade -q\n",
         "\n",
         "if os.getenv(\"IS_TESTING\"):\n",
-        "    ! pip3 install --upgrade matplotlib $USER_FLAG"
+        "    ! pip3 install --upgrade matplotlib $USER_FLAG -q"
       ]
     },
     {
@@ -240,6 +240,8 @@
         "id": "check_versions"
       },
       "source": [
+        "### KFP SDK version\n",
+        "\n",
         "Check the versions of the packages you installed.  The KFP SDK version should be >=1.6."
       ]
     },
@@ -349,7 +351,10 @@
       },
       "outputs": [],
       "source": [
-        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
+        "\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
       ]
     },
     {
@@ -358,9 +363,9 @@
         "id": "timestamp"
       },
       "source": [
-        "#### Timestamp\n",
+        "#### UUID\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 the timestamp onto the name of resources you create in this tutorial."
+        "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 uuid for each instance session, and append it onto the name of resources you create in this tutorial."
       ]
     },
     {
@@ -371,9 +376,16 @@
       },
       "outputs": [],
       "source": [
-        "from datetime import datetime\n",
+        "import random\n",
+        "import string\n",
         "\n",
-        "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
+        "\n",
+        "# Generate a uuid of a specifed length(default=8)\n",
+        "def generate_uuid(length: int = 8) -> str:\n",
+        "    return \"\".join(random.choices(string.ascii_lowercase + string.digits, k=length))\n",
+        "\n",
+        "\n",
+        "UUID = generate_uuid()"
       ]
     },
     {
@@ -384,7 +396,7 @@
       "source": [
         "### Authenticate your Google Cloud account\n",
         "\n",
-        "**If you are using Vertex AI Workbench Notebook**, your environment is already authenticated. Skip this step.\n",
+        "**If you are using Vertex AI Workbench Notebook**, your environment is already authenticated.\n",
         "\n",
         "**If you are using Colab**, run the cell below and follow the instructions\n",
         "when prompted to authenticate your account via oAuth.\n",
@@ -479,7 +491,7 @@
       "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_NAME = PROJECT_ID + \"aip-\" + UUID\n",
         "    BUCKET_URI = \"gs://\" + BUCKET_NAME"
       ]
     },
@@ -553,6 +565,10 @@
       },
       "outputs": [],
       "source": [
+        "import sys\n",
+        "\n",
+        "IS_COLAB = \"google.colab\" in sys.modules\n",
+        "\n",
         "if (\n",
         "    SERVICE_ACCOUNT == \"\"\n",
         "    or SERVICE_ACCOUNT is None\n",
@@ -912,12 +928,12 @@
       },
       "outputs": [],
       "source": [
-        "DISPLAY_NAME = \"iris_\" + TIMESTAMP\n",
+        "DISPLAY_NAME = \"iris_\" + UUID\n",
         "\n",
         "job = aip.PipelineJob(\n",
         "    display_name=DISPLAY_NAME,\n",
         "    template_path=\"tabular classification_pipeline.json\".replace(\" \", \"_\"),\n",
-        "    job_id=f\"tabular classification-v2{TIMESTAMP}-1\".replace(\" \", \"\"),\n",
+        "    job_id=f\"tabular classification-v2{UUID}-1\".replace(\" \", \"\"),\n",
         "    pipeline_root=PIPELINE_ROOT,\n",
         "    parameter_values={\"seed\": 7, \"splits\": 10},\n",
         ")\n",
@@ -950,7 +966,18 @@
         "\n",
         "Next, generate another pipeline run that uses a different `seed` and `split` for the `iris_logregression` step.\n",
         "\n",
-        "Submit the new pipeline run:"
+        "Submit the new pipeline run:\n",
+        "\n",
+        "\n",
+        "**pipeline_root :**   Specify a Cloud Storage URI that your pipelines service account can access. The artifacts of your pipeline runs are stored within the pipeline root. \n",
+        "\n",
+        "**display_name :**  The name of the pipeline, this will show up in the Google Cloud console. \n",
+        "\n",
+        "**parameter_values :**  The pipeline parameters to pass to this run. For example, create a dict() with the parameter names as the dictionary keys and the parameter values as the dictionary values. \n",
+        "\n",
+        "**job_id :**  A unique identifier for this pipeline run. If the job ID is not specified, Vertex AI Pipelines creates a job ID for you using the pipeline name and the timestamp of when the pipeline run was started. \n",
+        "\n",
+        "**template_path :**  complete pipeline path"
       ]
     },
     {
@@ -962,9 +989,9 @@
       "outputs": [],
       "source": [
         "job = aip.PipelineJob(\n",
-        "    display_name=\"iris_\" + TIMESTAMP,\n",
+        "    display_name=\"iris_\" + UUID,\n",
         "    template_path=\"tabular classification_pipeline.json\".replace(\" \", \"_\"),\n",
-        "    job_id=f\"tabular classification-pipeline-v2{TIMESTAMP}-2\".replace(\" \", \"\"),\n",
+        "    job_id=f\"tabular classification-pipeline-v2{UUID}-2\".replace(\" \", \"\"),\n",
         "    pipeline_root=PIPELINE_ROOT,\n",
         "    parameter_values={\"seed\": 5, \"splits\": 7},\n",
         ")\n",
@@ -1081,16 +1108,7 @@
         "To clean up all Google Cloud resources used in this project, you can [delete the Google Cloud\n",
         "project](https://cloud.google.com/resource-manager/docs/creating-managing-projects#shutting_down_projects) you used for the tutorial.\n",
         "\n",
-        "Otherwise, you can delete the individual resources you created in this tutorial -- *Note:* this is auto-generated and not all resources may be applicable for this tutorial:\n",
-        "\n",
-        "- Dataset\n",
-        "- Pipeline\n",
-        "- Model\n",
-        "- Endpoint\n",
-        "- Batch Job\n",
-        "- Custom Job\n",
-        "- Hyperparameter Tuning Job\n",
-        "- Cloud Storage Bucket"
+        "Otherwise, you can delete the individual resources you created in this tutorial -- *Note:* this is auto-generated and not all resources may be applicable for this tutorial:"
       ]
     },
     {
@@ -1101,94 +1119,9 @@
       },
       "outputs": [],
       "source": [
-        "delete_dataset = True\n",
-        "delete_pipeline = True\n",
-        "delete_model = True\n",
-        "delete_endpoint = True\n",
-        "delete_batchjob = True\n",
-        "delete_customjob = True\n",
-        "delete_hptjob = True\n",
-        "delete_bucket = True\n",
-        "\n",
-        "try:\n",
-        "    if delete_model and \"DISPLAY_NAME\" in globals():\n",
-        "        models = aip.Model.list(\n",
-        "            filter=f\"display_name={DISPLAY_NAME}\", order_by=\"create_time\"\n",
-        "        )\n",
-        "        model = models[0]\n",
-        "        aip.Model.delete(model)\n",
-        "        print(\"Deleted model:\", model)\n",
-        "except Exception as e:\n",
-        "    print(e)\n",
-        "\n",
-        "try:\n",
-        "    if delete_endpoint and \"DISPLAY_NAME\" in globals():\n",
-        "        endpoints = aip.Endpoint.list(\n",
-        "            filter=f\"display_name={DISPLAY_NAME}_endpoint\", order_by=\"create_time\"\n",
-        "        )\n",
-        "        endpoint = endpoints[0]\n",
-        "        endpoint.undeploy_all()\n",
-        "        aip.Endpoint.delete(endpoint.resource_name)\n",
-        "        print(\"Deleted endpoint:\", endpoint)\n",
-        "except Exception as e:\n",
-        "    print(e)\n",
-        "\n",
-        "if delete_dataset and \"DISPLAY_NAME\" in globals():\n",
-        "    if \"tabular\" == \"tabular\":\n",
-        "        try:\n",
-        "            datasets = aip.TabularDataset.list(\n",
-        "                filter=f\"display_name={DISPLAY_NAME}\", order_by=\"create_time\"\n",
-        "            )\n",
-        "            dataset = datasets[0]\n",
-        "            aip.TabularDataset.delete(dataset.resource_name)\n",
-        "            print(\"Deleted dataset:\", dataset)\n",
-        "        except Exception as e:\n",
-        "            print(e)\n",
-        "\n",
-        "    if \"tabular\" == \"image\":\n",
-        "        try:\n",
-        "            datasets = aip.ImageDataset.list(\n",
-        "                filter=f\"display_name={DISPLAY_NAME}\", order_by=\"create_time\"\n",
-        "            )\n",
-        "            dataset = datasets[0]\n",
-        "            aip.ImageDataset.delete(dataset.resource_name)\n",
-        "            print(\"Deleted dataset:\", dataset)\n",
-        "        except Exception as e:\n",
-        "            print(e)\n",
-        "\n",
-        "    if \"tabular\" == \"text\":\n",
-        "        try:\n",
-        "            datasets = aip.TextDataset.list(\n",
-        "                filter=f\"display_name={DISPLAY_NAME}\", order_by=\"create_time\"\n",
-        "            )\n",
-        "            dataset = datasets[0]\n",
-        "            aip.TextDataset.delete(dataset.resource_name)\n",
-        "            print(\"Deleted dataset:\", dataset)\n",
-        "        except Exception as e:\n",
-        "            print(e)\n",
-        "\n",
-        "    if \"tabular\" == \"video\":\n",
-        "        try:\n",
-        "            datasets = aip.VideoDataset.list(\n",
-        "                filter=f\"display_name={DISPLAY_NAME}\", order_by=\"create_time\"\n",
-        "            )\n",
-        "            dataset = datasets[0]\n",
-        "            aip.VideoDataset.delete(dataset.resource_name)\n",
-        "            print(\"Deleted dataset:\", dataset)\n",
-        "        except Exception as e:\n",
-        "            print(e)\n",
-        "\n",
-        "try:\n",
-        "    if delete_pipeline and \"DISPLAY_NAME\" in globals():\n",
-        "        pipelines = aip.PipelineJob.list(\n",
-        "            filter=f\"display_name={DISPLAY_NAME}\", order_by=\"create_time\"\n",
-        "        )\n",
-        "        pipeline = pipelines[0]\n",
-        "        aip.PipelineJob.delete(pipeline.resource_name)\n",
-        "        print(\"Deleted pipeline:\", pipeline)\n",
-        "except Exception as e:\n",
-        "    print(e)\n",
+        "delete_bucket = False\n",
         "\n",
+        "job.delete()\n",
         "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
         "    ! gsutil rm -r $BUCKET_URI"
       ]

notebooks/official/pipelines/pipelines_intro_kfp.ipynb

@@ -81,7 +81,6 @@
         "The steps performed include:\n",
         "\n",
         "- Define and compile a `Vertex AI` pipeline.\n",
-        "- Schedule a recurring pipeline run.\n",
         "- Specify which service account to use for a pipeline run."
       ]
     },
@@ -97,13 +96,9 @@
         "\n",
         "* Vertex AI\n",
         "* Cloud Storage\n",
-        "* Cloud Functions\n",
-        "* Cloud Scheduler\n",
         "\n",
         "Learn about [Vertex AI pricing](https://cloud.google.com/vertex-ai/pricing),\n",
         "[Cloud Storage pricing](https://cloud.google.com/storage/pricing),\n",
-        "[Cloud Functions pricing](ttps://cloud.google.com/functions/pricing), and\n",
-        "[Clould Scheduler pricing]((https://cloud.google.com/scheduler/pricing)),\n",
         "and use the [Pricing\n",
         "Calculator](https://cloud.google.com/products/calculator/)\n",
         "to generate a cost estimate based on your projected usage."
@@ -926,69 +921,6 @@
         "job.delete()"
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "schedule_pipeline_run"
-      },
-      "source": [
-        "## Recurring pipeline runs: create a scheduled pipeline job\n",
-        "\n",
-        "This section shows how to create a **scheduled pipeline job**.  You do this using the pipeline you already defined.\n",
-        "\n",
-        "Under the hood, the scheduled jobs are supported by the Cloud Scheduler and a Cloud Functions function.  Check first that the APIs for both of these services are enabled.\n",
-        "You will need to first enable the [enable the Cloud Scheduler API](http://console.cloud.google.com/apis/library/cloudscheduler.googleapis.com) and the [Cloud Functions and Cloud Build APIs](https://console.cloud.google.com/flows/enableapi?apiid=cloudfunctions,cloudbuild.googleapis.com) if you have not already done so.\n",
-        "Note:you need to [create an App Engine app for your project](https://cloud.google.com/scheduler/docs/quickstart) if one does not already exist.\n",
-        "\n",
-        "\n",
-        "See the [Cloud Scheduler](https://cloud.google.com/scheduler/docs/configuring/cron-job-schedules) documentation for more on the cron syntax.\n",
-        "\n",
-        "Create a scheduled pipeline job, passing as an argument the job specification file that you compiled above.\n",
-        "\n",
-        "*Note:* You can pass a `parameter_values` dict that specifies the pipeline input parameters you want to use."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "Ty5hDoNX2Ou8"
-      },
-      "outputs": [],
-      "source": [
-        "if not os.getenv(\"IS_TESTING\"):\n",
-        "    from kfp.v2.google.client import AIPlatformClient  # noqa: F811\n",
-        "\n",
-        "    api_client = AIPlatformClient(project_id=PROJECT_ID, region=REGION)\n",
-        "\n",
-        "    # adjust time zone and cron schedule as necessary\n",
-        "    response = api_client.create_schedule_from_job_spec(\n",
-        "        job_spec_path=\"intro_pipeline.json\",\n",
-        "        schedule=\"2 * * * *\",\n",
-        "        time_zone=\"America/Los_Angeles\",  # change this as necessary\n",
-        "        parameter_values={\"text\": \"Hello world!\"},\n",
-        "        # pipeline_root=PIPELINE_ROOT  # this argument is necessary if you did not specify PIPELINE_ROOT as part of the pipeline definition.\n",
-        "    )"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "J8AP1viy2Ou8"
-      },
-      "source": [
-        "Once the scheduled job is created, you can see it listed in the [Cloud Scheduler](https://console.cloud.google.com/cloudscheduler/) panel in the Console.\n",
-        "\n",
-        "<a href=\"https://storage.googleapis.com/amy-jo/images/kf-pls/pipelines_scheduler.png\" target=\"_blank\"><img src=\"https://storage.googleapis.com/amy-jo/images/kf-pls/pipelines_scheduler.png\" width=\"95%\"/></a>\n",
-        "\n",
-        "You can test the setup from the Cloud Scheduler panel by clicking 'RUN NOW'.\n",
-        "\n",
-        "> **Note**: The implementation is using a Cloud Functions function, which you can see listed in the [Cloud Functions](https://console.cloud.google.com/functions/list) panel in the console as `templated_http_request-v1`.\n",
-        "Don't delete this function, as it will prevent the Cloud Scheduler jobs from actually kicking off the pipeline run.  If you do delete it, create a new scheduled job in order to recreate the function.\n",
-        "\n",
-        "When you're done experimenting, you probably want to **PAUSE** your scheduled job from the Cloud Scheduler panel, so that the recurrent jobs do not keep running."
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -1222,7 +1154,7 @@
       "outputs": [],
       "source": [
         "delete_pipeline = True\n",
-        "delete_bucket = True\n",
+        "delete_bucket = False\n",
         "\n",
         "try:\n",
         "    if delete_pipeline and \"DISPLAY_NAME\" in globals():\n",

notebooks/official/workbench/fraud_detection/fraud-detection-model.ipynb

@@ -1,14 +1,5 @@
 {
   "cells": [
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "c4b363e1330b"
-      },
-      "source": [
-        "# Build a fraud detection model on Vertex AI"
-      ]
-    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -38,6 +29,8 @@
         "id": "05c670d35496"
       },
       "source": [
+        "# Build a fraud detection model on Vertex AI\n",
+        "\n",
         "<table align=\"left\">\n",
         "\n",
         "  <td>\n",
@@ -60,28 +53,6 @@
         "</table>"
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "4c5fb7f2090f"
-      },
-      "source": [
-        "## Table of contents\n",
-        "\n",
-        "* [Overview](#section-1)\n",
-        "* [Dataset](#section-2)\n",
-        "* [Objective](#section-3)\n",
-        "* [Costs](#section-4)\n",
-        "* [Analyze the dataset](#section-5)\n",
-        "* [Fit a random forest model](#section-6)\n",
-        "* [Analyzing results](#section-7)\n",
-        "* [Save the model to a Cloud Storagae path](#section-8)\n",
-        "* [Create a model in Vertex AI](#section-9)\n",
-        "* [Create an Endpoint](#section-10)  \n",
-        "* [What-If Tool ](#section-11)\n",
-        "* [Clean up](#section-12)"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -94,19 +65,6 @@
         "This tutorial shows you how to build, deploy, and analyze predictions from a simple [random forest](https://en.wikipedia.org/wiki/Random_forest) model using tools like scikit-learn, Vertex AI, and the [What-IF Tool (WIT)](https://cloud.google.com/ai-platform/prediction/docs/using-what-if-tool) on a synthetic fraud transaction dataset to solve a financial fraud detection problem.\n"
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "9625185ccee9"
-      },
-      "source": [
-        "## Dataset\n",
-        "<a name=\"section-2\"></a>\n",
-        "\n",
-        "\n",
-        "The dataset used in this tutorial is publicly available at Kaggle. See [Synthetic Financial Datasets For Fraud Detection](https://www.kaggle.com/ealaxi/paysim1)."
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -118,6 +76,13 @@
         "\n",
         "This tutorial demonstrates data analysis and model-building using a synthetic financial dataset. The model is trained on identifying fraudulent cases among the transactions. Then, the trained model is deployed on a Vertex AI Endpoint and analyzed using the What-If Tool. The steps taken in this tutorial are as follows: \n",
         "\n",
+        "This tutorial uses the following Google Cloud ML services and resources:\n",
+        "\n",
+        "- Vertex AI Model\n",
+        "- Vertex AI Endpoint\n",
+        "\n",
+        "The steps performed include:\n",
+        "\n",
         "- Installation of required libraries\n",
         "- Reading the dataset from a Cloud Storage bucket\n",
         "- Performing exploratory analysis on the dataset\n",
@@ -129,6 +94,19 @@
         "- Un-deploying the model and cleaning up the model resources"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "3037523e7523"
+      },
+      "source": [
+        "## Dataset\n",
+        "<a name=\"section-2\"></a>\n",
+        "\n",
+        "\n",
+        "The dataset used in this tutorial is publicly available at Kaggle. See [Synthetic Financial Datasets For Fraud Detection](https://www.kaggle.com/ealaxi/paysim1)."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -154,21 +132,15 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "1ba37fa1511f"
+        "id": "cd1bc75a1cb2"
       },
       "source": [
         "### Set up your local development environment\n",
         "\n",
         "**If you are using Colab or Google Cloud Notebooks**, your environment already meets\n",
-        "all the requirements to run this notebook. You can skip this step."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "cd1bc75a1cb2"
-      },
-      "source": [
+        "all the requirements to run this notebook. You can skip this step.\n",
+        "\n",
+        "\n",
         "**Otherwise**, make sure your environment meets this notebook's requirements.\n",
         "You need the following:\n",
         "\n",
@@ -211,142 +183,44 @@
     },
     {
       "cell_type": "code",
-      "execution_count": null,
+      "execution_count": 1,
       "metadata": {
         "id": "172533a994ad"
       },
-      "outputs": [],
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n",
+            "flake8 4.0.1 requires importlib-metadata<4.3; python_version < \"3.8\", but you have importlib-metadata 4.12.0 which is incompatible.\u001b[0m\u001b[31m\n",
+            "\u001b[0m"
+          ]
+        }
+      ],
       "source": [
         "import os\n",
         "\n",
-        "import google.auth\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",
-        "# Google Cloud Notebook requires dependencies to be installed with '--user'\n",
-        "if \"default\" in dir(google.auth):\n",
-        "    USER_FLAG = \"--user\""
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "a465cf9367de"
-      },
-      "source": [
-        "Install the latest version of the Vertex AI client library.\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
         "\n",
-        "Run the following command in your notebook environment to install the Vertex SDK for Python:"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "6380f7ee5f54"
-      },
-      "outputs": [],
-      "source": [
-        "! pip install {USER_FLAG} --upgrade google-cloud-aiplatform"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "1969a1cc46cf"
-      },
-      "source": [
-        "Run the following command in your notebook environment to install witwidget:"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "8b10e59b0911"
-      },
-      "outputs": [],
-      "source": [
-        "! pip install {USER_FLAG} witwidget"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "4099ce79705a"
-      },
-      "source": [
-        "Run the following command in your notebook environment to install joblib:"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "1e56d524753a"
-      },
-      "outputs": [],
-      "source": [
-        "! pip install {USER_FLAG} joblib"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "b87ee3041f7d"
-      },
-      "source": [
-        "Run the following command in your notebook environment to install scikit-learn:"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "c3ebecd9bd72"
-      },
-      "outputs": [],
-      "source": [
-        "! pip install {USER_FLAG} scikit-learn"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "b624b5163531"
-      },
-      "source": [
-        "Run the following command in your notebook environment to install fsspec:"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "79c7a64b04de"
-      },
-      "outputs": [],
-      "source": [
-        "! pip install {USER_FLAG} fsspec"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "5593090dcf0a"
-      },
-      "source": [
-        "Run the following command in your notebook environment to install gcsfs:"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "7bf981bc5bf6"
-      },
-      "outputs": [],
-      "source": [
-        "! pip install {USER_FLAG} gcsfs"
+        "# Install the latest version of the Vertex AI client library.\n",
+        "! pip3 install --upgrade google-cloud-aiplatform {USER_FLAG} -q\n",
+        "\n",
+        "# Install additional libraries\n",
+        "! pip3 install {USER_FLAG} witwidget -q\n",
+        "! pip3 install {USER_FLAG} joblib -q\n",
+        "! pip3 install {USER_FLAG} scikit-learn -q\n",
+        "! pip3 install {USER_FLAG} fsspec -q\n",
+        "! pip3 install {USER_FLAG} gcsfs -q"
       ]
     },
     {
@@ -378,21 +252,14 @@
         "    app.kernel.do_shutdown(True)"
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "2d9b3731b3e0"
-      },
-      "source": [
-        "## Before you begin"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
         "id": "7a5cb1df1ef7"
       },
       "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",
@@ -426,19 +293,26 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "b27f37ed1ccf"
+        "id": "dcdfccf50581"
       },
       "outputs": [],
       "source": [
-        "import os\n",
-        "\n",
-        "PROJECT_ID = \"\"\n",
-        "\n",
-        "# Get your Google Cloud project ID from gcloud\n",
-        "if not os.getenv(\"IS_TESTING\"):\n",
-        "    shell_output = !gcloud config list --format 'value(core.project)' 2>/dev/null\n",
+        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "5bf9979b96ff"
+      },
+      "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)"
+        "    print(\"Project ID:\", PROJECT_ID)"
       ]
     },
     {
@@ -450,18 +324,6 @@
         "Otherwise, set your project ID here."
       ]
     },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "3dbdf6a5c539"
-      },
-      "outputs": [],
-      "source": [
-        "if PROJECT_ID == \"\" or PROJECT_ID is None:\n",
-        "    PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
-      ]
-    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -473,15 +335,49 @@
         "! gcloud config set project $PROJECT_ID"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "264543a144ad"
+      },
+      "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. It is recommended 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": "3281bedf6d3c"
+      },
+      "outputs": [],
+      "source": [
+        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
+        "\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
         "id": "e663bd062c6f"
       },
       "source": [
-        "#### Timestamp\n",
+        "#### UUID\n",
         "\n",
-        "If you are in a live tutorial session, you might be using a shared test account or project. To avoid name collisions between users on resources created, you create a timestamp for each instance session, and append it onto the name of resources you create in this tutorial."
+        "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 uuid for each instance session, and append it onto the name of resources you create in this tutorial."
       ]
     },
     {
@@ -492,21 +388,16 @@
       },
       "outputs": [],
       "source": [
-        "from datetime import datetime\n",
+        "import random\n",
+        "import string\n",
         "\n",
-        "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "0c7f603fcdcf"
-      },
-      "source": [
-        "### Authenticate your Google Cloud account\n",
         "\n",
-        "**If you are using Google Cloud Notebooks**, your environment is already\n",
-        "authenticated. Skip this step."
+        "# Generate a uuid of length 8\n",
+        "def generate_uuid():\n",
+        "    return \"\".join(random.choices(string.ascii_lowercase + string.digits, k=8))\n",
+        "\n",
+        "\n",
+        "UUID = generate_uuid()"
       ]
     },
     {
@@ -515,6 +406,11 @@
         "id": "72bf8f7c9ab3"
       },
       "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already\n",
+        "authenticated. Skip this step.\n",
+        "\n",
         "**If you are using Colab**, run the cell below and follow the instructions\n",
         "when prompted to authenticate your account via oAuth.\n",
         "\n",
@@ -547,19 +443,19 @@
       },
       "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",
@@ -601,27 +497,25 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "f56c52ba662c"
+        "id": "5e9a782f5608"
       },
       "outputs": [],
       "source": [
         "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
-        "REGION = \"[your-region]\"  # @param {type:\"string\"}"
+        "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "68d1f4908641"
+        "id": "6d0729c4ae94"
       },
       "outputs": [],
       "source": [
         "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"[your-bucket-name]\":\n",
-        "    BUCKET_NAME = PROJECT_ID + \"-vertex-ai-\" + TIMESTAMP\n",
-        "BUCKET_URI = f\"gs://{BUCKET_NAME}\"\n",
-        "if REGION == \"[your-region]\":\n",
-        "    REGION = \"us-central1\""
+        "    BUCKET_NAME = PROJECT_ID + \"aip-\" + UUID\n",
+        "    BUCKET_URI = f\"gs://{BUCKET_NAME}\""
       ]
     },
     {
@@ -697,6 +591,7 @@
         "import numpy as np\n",
         "import pandas as pd\n",
         "from google.cloud import aiplatform, storage\n",
+        "from IPython.display import display\n",
         "from sklearn.ensemble import RandomForestClassifier\n",
         "from sklearn.metrics import (average_precision_score, classification_report,\n",
         "                             confusion_matrix, f1_score)\n",
@@ -706,6 +601,15 @@
         "warnings.filterwarnings(\"ignore\")"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "fdcb614c716f"
+      },
+      "source": [
+        "## Load dataset"
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -714,7 +618,6 @@
       },
       "outputs": [],
       "source": [
-        "# Load dataset\n",
         "df = pd.read_csv(\n",
         "    \"gs://cloud-samples-data/vertex-ai/managed_notebooks/fraud_detection/fraud_detection_data.csv\"\n",
         ")"
@@ -1031,6 +934,8 @@
         "\n",
         "# Upload the saved model file to Cloud Storage\n",
         "BLOB_PATH = \"[your-blob-path]\"\n",
+        "if BLOB_PATH == \"[your-blob-path]\":\n",
+        "    BLOB_PATH = \"fraud-detection-model-path\"\n",
         "BLOB_NAME = os.path.join(BLOB_PATH, FILE_NAME)\n",
         "\n",
         "bucket = storage.Client(PROJECT_ID).bucket(BUCKET_NAME)\n",
@@ -1057,6 +962,8 @@
       "outputs": [],
       "source": [
         "MODEL_DISPLAY_NAME = \"[your-model-display-name]\"\n",
+        "if MODEL_DISPLAY_NAME == \"[your-model-display-name]\":\n",
+        "    MODEL_DISPLAY_NAME = \"fraud-detection-model-display-name\"\n",
         "ARTIFACT_GCS_PATH = f\"{BUCKET_URI}/{BLOB_PATH}\"\n",
         "SERVING_CONTAINER_IMAGE_URI = (\n",
         "    \"us-docker.pkg.dev/vertex-ai/prediction/sklearn-cpu.1-0:latest\"\n",
@@ -1105,7 +1012,9 @@
       },
       "outputs": [],
       "source": [
-        "ENDPOINT_DISPLAY_NAME = \"[your-endpoint-display-name]\""
+        "ENDPOINT_DISPLAY_NAME = \"[your-endpoint-display-name]\"\n",
+        "if ENDPOINT_DISPLAY_NAME == \"[your-endpoint-display-name]\":\n",
+        "    ENDPOINT_DISPLAY_NAME = \"fraud-detection-endpoint\""
       ]
     },
     {
@@ -1143,6 +1052,8 @@
       "outputs": [],
       "source": [
         "DEPLOYED_MODEL_NAME = \"[your-deployed-model-name]\"\n",
+        "if DEPLOYED_MODEL_NAME == \"[your-deployed-model-name]\":\n",
+        "    DEPLOYED_MODEL_NAME = \"fraud-detection-deployed-model\"\n",
         "MACHINE_TYPE = \"n1-standard-2\""
       ]
     },
@@ -1224,34 +1135,33 @@
       },
       "outputs": [],
       "source": [
-        "# define target and labels\n",
-        "TARGET_FEATURE = \"isFraud\"\n",
-        "LABEL_VOCAB = [\"not-fraud\", \"fraud\"]\n",
+        "if not IS_COLAB:\n",
+        "    # define target and labels\n",
+        "    TARGET_FEATURE = \"isFraud\"\n",
+        "    LABEL_VOCAB = [\"not-fraud\", \"fraud\"]\n",
         "\n",
-        "# define the function to adjust the predictions\n",
+        "    # define the function to adjust the predictions\n",
         "\n",
+        "    def adjust_prediction(pred):\n",
+        "        return [1 - pred, pred]\n",
         "\n",
-        "def adjust_prediction(pred):\n",
-        "    return [1 - pred, pred]\n",
-        "\n",
-        "\n",
-        "# Combine the features and labels into one array for the What-If Tool\n",
-        "test_examples = np.hstack(\n",
-        "    (test_samples_X.to_numpy(), test_samples_y.to_numpy().reshape(-1, 1))\n",
-        ")\n",
-        "\n",
-        "# Configure the WIT to run on the locally trained model\n",
-        "config_builder = (\n",
-        "    WitConfigBuilder(\n",
-        "        test_examples.tolist(), test_samples_X.columns.tolist() + [\"isFraud\"]\n",
+        "    # Combine the features and labels into one array for the What-If Tool\n",
+        "    test_examples = np.hstack(\n",
+        "        (test_samples_X.to_numpy(), test_samples_y.to_numpy().reshape(-1, 1))\n",
         "    )\n",
-        "    .set_custom_predict_fn(forest.predict_proba)\n",
-        "    .set_target_feature(TARGET_FEATURE)\n",
-        "    .set_label_vocab(LABEL_VOCAB)\n",
-        ")\n",
         "\n",
-        "# display the WIT widget\n",
-        "WitWidget(config_builder, height=600)"
+        "    # Configure the WIT to run on the locally trained model\n",
+        "    config_builder = (\n",
+        "        WitConfigBuilder(\n",
+        "            test_examples.tolist(), test_samples_X.columns.tolist() + [\"isFraud\"]\n",
+        "        )\n",
+        "        .set_custom_predict_fn(forest.predict_proba)\n",
+        "        .set_target_feature(TARGET_FEATURE)\n",
+        "        .set_label_vocab(LABEL_VOCAB)\n",
+        "    )\n",
+        "\n",
+        "    # display the WIT widget\n",
+        "    display(WitWidget(config_builder, height=600))"
       ]
     },
     {
@@ -1271,36 +1181,35 @@
       },
       "outputs": [],
       "source": [
-        "# configure the target and class-labels\n",
-        "TARGET_FEATURE = \"isFraud\"\n",
-        "LABEL_VOCAB = [\"not-fraud\", \"fraud\"]\n",
+        "if not IS_COLAB:\n",
+        "    # configure the target and class-labels\n",
+        "    TARGET_FEATURE = \"isFraud\"\n",
+        "    LABEL_VOCAB = [\"not-fraud\", \"fraud\"]\n",
         "\n",
-        "# function to return predictions from the deployed Model\n",
+        "    # function to return predictions from the deployed Model\n",
         "\n",
+        "    def endpoint_predict_sample(instances: list):\n",
+        "        prediction = endpoint.predict(instances=instances)\n",
+        "        preds = [[1 - i, i] for i in prediction.predictions]\n",
+        "        return preds\n",
         "\n",
-        "def endpoint_predict_sample(instances: list):\n",
-        "    prediction = endpoint.predict(instances=instances)\n",
-        "    preds = [[1 - i, i] for i in prediction.predictions]\n",
-        "    return preds\n",
-        "\n",
-        "\n",
-        "# Combine the features and labels into one array for the What-If Tool\n",
-        "test_examples = np.hstack(\n",
-        "    (test_samples_X.to_numpy(), test_samples_y.to_numpy().reshape(-1, 1))\n",
-        ")\n",
-        "\n",
-        "# Configure the WIT with the prediction function\n",
-        "config_builder = (\n",
-        "    WitConfigBuilder(\n",
-        "        test_examples.tolist(), test_samples_X.columns.tolist() + [\"isFraud\"]\n",
+        "    # Combine the features and labels into one array for the What-If Tool\n",
+        "    test_examples = np.hstack(\n",
+        "        (test_samples_X.to_numpy(), test_samples_y.to_numpy().reshape(-1, 1))\n",
         "    )\n",
-        "    .set_custom_predict_fn(endpoint_predict_sample)\n",
-        "    .set_target_feature(TARGET_FEATURE)\n",
-        "    .set_label_vocab(LABEL_VOCAB)\n",
-        ")\n",
         "\n",
-        "# run the WIT-widget\n",
-        "WitWidget(config_builder, height=400)"
+        "    # Configure the WIT with the prediction function\n",
+        "    config_builder = (\n",
+        "        WitConfigBuilder(\n",
+        "            test_examples.tolist(), test_samples_X.columns.tolist() + [\"isFraud\"]\n",
+        "        )\n",
+        "        .set_custom_predict_fn(endpoint_predict_sample)\n",
+        "        .set_target_feature(TARGET_FEATURE)\n",
+        "        .set_label_vocab(LABEL_VOCAB)\n",
+        "    )\n",
+        "\n",
+        "    # run the WIT-widget\n",
+        "    display(WitWidget(config_builder, height=400))"
       ]
     },
     {