// the find
GoogleCloudPlatform/generative-ai
Sample code and notebooks for Generative AI on Google Cloud, with Gemini Enterprise Agent Platform
A Google-maintained collection of Jupyter notebooks and sample code for building with Gemini and Vertex AI on Google Cloud. It covers everything from basic API usage to multi-agent systems, RAG, embeddings, and the new Agent Development Kit (ADK). If you're evaluating whether to build on Google's AI stack, this is your first stop.
The breadth of coverage is genuinely useful — notebooks span function calling, vector search, multi-agent coordination, TTS, image generation, and LangGraph/LangChain integrations, all with working GCP credentials wiring. The ADK samples (contract compliance pipeline, new-hire onboarding) are more production-shaped than typical demo code — they include Docker, FastAPI, eval sets, and actual unit tests. Google maintains this actively; the last push was yesterday, and the CI setup includes spell checking, linting, and gitleaks for secret detection. The cross-linking to specialized sibling repos (ADK samples, agent-starter-pack, genai-databases-retrieval-app) makes it a useful map of the whole ecosystem.
It's a sample repository, not a library — nothing here is importable or reusable without copy-pasting. The notebooks assume a live GCP project with billing enabled, so you can't run most of them locally or cheaply. There's no consistent abstraction layer; the quality and style varies wildly between notebooks because different Googlers wrote them at different times. The disclaimer that this is 'not an officially supported Google product' is a real caveat — if a notebook breaks against an API change, your bug report goes into a general issues queue with no SLA.