GoogleCloudPlatform/generative-ai

Sample code and notebooks for Generative AI on Google Cloud, with Gemini Enterprise Agent Platform

What This Project Is

A public collection of notebooks, code samples, sample apps, and other resources that show how to build, use, and manage generative AI workflows on Google Cloud. It focuses on Google's Generative AI tools and the Agent Platform (a service for building AI agents).

What's Inside

The repository is organized into folders, each with a specific focus:

  • gemini/ — Starter notebooks, use cases, function calling, and sample apps for Gemini (Google's family of AI models). The README highlights that the latest Gemini models (e.g., Gemini 4 Argon) are available here.
  • search/ — For building search engines over websites and enterprise data using Agent Search, a Google-managed solution (formerly called "Enterprise Search on Generative AI App Builder").
  • rag-grounding/ — Resources on Retrieval Augmented Generation (RAG) and Grounding — techniques that help AI models pull from specific data sources. This folder is an index pointing to related notebooks and samples elsewhere in the repo.
  • vision/ — Building custom solutions from scratch using Imagen and Veo (Google's image and video generation models).
  • audio/ — Building custom solutions from scratch using Chirp, a version of Google's Universal Speech Model (USM) for speech.
  • setup-env/ — Instructions for setting up Google Cloud, the Gen AI Python SDK, and notebook environments on Google Colab and Workbench.
  • RESOURCES.md — A list of learning resources (blogs, YouTube playlists) about generative AI on Google Cloud.

Related Repositories

The README links to many other projects, including:

  • Agent Development Kit (ADK) Samples — Ready-to-use AI agents built on the Agent Development Kit, from simple chatbots to complex multi-agent workflows.
  • Agent Starter Pack — Production-ready generative AI agent templates for Google Cloud, addressing deployment, evaluation, customization, and observability.
  • Gemini Cookbook — A separate collection of Gemini examples.
  • genai-factory — Infrastructure blueprints for deploying generative AI setups on Google Cloud.
  • And many more (marketing use cases, developer productivity, Vertex AI samples, MLOps, document AI, etc.).

How to Contribute and Get Help

  • Contributing — Contributions are welcome; see the Contributing Guide linked in the README.
  • Getting help — Use the GitHub issues page for suggestions, feedback, or bug reports.

Important Disclaimer

This repository is not an officially supported Google product. The code is provided for demonstrative purposes only.

All information above is drawn directly from the project's README.

Related

  • Project
    LibreTranslate/LibreTranslate

    LibreTranslate is a self-hosted, open-source machine translation API that removes dependency on proprietary services like Google or Azure.

  • Project
    xx025/carrot

    A community-edited directory of freely accessible AI websites, organized by popularity and category, with labels for features like free usage or required login.

  • Project
    google-gemini/cookbook

    google-gemini/cookbook is a collection of hands-on Jupyter notebook tutorials for learning the Gemini API, organized into Quick Starts (step-by-step feature guides) and Examples (combined use cases). It covers models for text, image, video, music, speech, transcription, live streaming, agents, and more, with Colab buttons for running notebooks in the cloud. You need a Google account and an API key from Google AI Studio to get started.

  • Project
    Canner/WrenAI

    An open-source generative BI engine that provides a governed semantic layer for AI agents to turn business questions into correct SQL and deployable dashboards.