{"id":15221553,"url":"https://github.com/googlecloudplatform/vertex-ai-samples","last_synced_at":"2025-10-18T20:23:45.634Z","repository":{"id":37005994,"uuid":"371198718","full_name":"GoogleCloudPlatform/vertex-ai-samples","owner":"GoogleCloudPlatform","description":"Notebooks, code samples, sample apps, and other resources that demonstrate how to use, develop and manage machine learning and generative AI workflows using Google Cloud Vertex AI.","archived":false,"fork":false,"pushed_at":"2025-05-12T19:53:07.000Z","size":102224,"stargazers_count":338,"open_issues_count":37,"forks_count":117,"subscribers_count":54,"default_branch":"main","last_synced_at":"2025-05-12T19:54:12.684Z","etag":null,"topics":["automl","colab","colab-enterprise","gemini","gemini-api","genai","generative-ai","google-cloud-platform","ml","mlops","model","model-garden","notebook","pipeline","predictions","samples","vertex-ai","vertexai","workbench"],"latest_commit_sha":null,"homepage":"https://cloud.google.com/vertex-ai","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/GoogleCloudPlatform.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":"CODEOWNERS","security":"SECURITY.md","support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2021-05-27T00:06:43.000Z","updated_at":"2025-05-12T18:55:36.000Z","dependencies_parsed_at":"2023-09-28T17:12:32.851Z","dependency_job_id":"31d2e808-9910-4371-9433-79b85deebf25","html_url":"https://github.com/GoogleCloudPlatform/vertex-ai-samples","commit_stats":{"total_commits":2559,"total_committers":164,"mean_commits":"15.603658536585366","dds":0.4869089488081282,"last_synced_commit":"7d7db7d2d724270f865763da7253d4368cd1806d"},"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GoogleCloudPlatform%2Fvertex-ai-samples","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GoogleCloudPlatform%2Fvertex-ai-samples/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GoogleCloudPlatform%2Fvertex-ai-samples/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GoogleCloudPlatform%2Fvertex-ai-samples/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/GoogleCloudPlatform","download_url":"https://codeload.github.com/GoogleCloudPlatform/vertex-ai-samples/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":254355333,"owners_count":22057354,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["automl","colab","colab-enterprise","gemini","gemini-api","genai","generative-ai","google-cloud-platform","ml","mlops","model","model-garden","notebook","pipeline","predictions","samples","vertex-ai","vertexai","workbench"],"created_at":"2024-09-28T15:05:50.080Z","updated_at":"2025-10-18T20:23:40.600Z","avatar_url":"https://github.com/GoogleCloudPlatform.png","language":"Jupyter Notebook","readme":"# Step-by-Step Demo\n\nThis demo showcase how to use (1) custom training, (2) custom hyperparameter\ntuning, and (3) custom prediction serving over endpoints with\n[Vertex AI](https://cloud.google.com/vertex-ai) to build a contextual bandits\nbased movie recommendation system. We implement the RL training and prediction\nlogic using the [TF-Agents](https://www.tensorflow.org/agents) library. We also\nillustrate how to use TensorBoard Profiler to track the training process and\nresources, allowing speed and scalability analysis.\n\n\u003cimg src=\"rl-training.png\" alt=\"RL Training Illustration\" width=\"600\"/\u003e\n\nWe use the\n[MovieLens 100K dataset](https://www.kaggle.com/prajitdatta/movielens-100k-dataset)\nto build a simulation environment that frames the recommendation problem:\n\n1.  User vectors are the environment observations;\n2.  Movie items to recommend are the agent actions applied on the environment;\n3.  Approximate user ratings are the environment rewards generated as feedback\n    to the observations and actions.\n\nFor custom training, we assume the system dynamically interacts with the\nenvironment in real time so that the target policy is the same as the behavior\npolicy: At each time step, we interact with the envionment to obtain an\nobservation, query the current policy for an action given said observation, and\nlastly obtain a reward from the environment given the aforementioned observation\nand action; then we use these pieces of data to train the policy.\n\nThe demo contains a notebook that carries out the full workflow and user\ninstructions, and a `src/` directory for Python modules and unit tests.\n\nRead more about problem framing, simulations, and adopting this demo in\nproduction and to other use cases in the notebook.\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgooglecloudplatform%2Fvertex-ai-samples","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgooglecloudplatform%2Fvertex-ai-samples","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgooglecloudplatform%2Fvertex-ai-samples/lists"}