GoogleCloudPlatform/generative-aiPublic

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

AI summary: A comprehensive collection of sample code, notebooks, and tutorials for building generative AI applications on Google Cloud.

Star on GitHub

Stars: 17.6K; +8 today
Forks: 4.4K
Watchers: 279
Open issues: 71
Open PRs: 15
Contributors: ~305
Commits: 2.2K
Branches: 61

Jupyter NotebookApache-2.0Created May 5, 2023Last push 1d ago+38 stars this week+38 this month

Star history

since May 7, 2023

17.6K stars as of Aug 6, 2026, tracked back to May 7, 2023. Historical curve reconstructed from public GitHub event archives, calibrated to the current total.

Contribution activity

commits per day, last 52 weeks

457 commits in the last yearLessMore

Signals and awards

derived from tracked data

Widely adopted
17,557 stars
Actively maintained
Pushed within 48 hours
Community-driven
~305 contributors
Well documented
High community health score
Permissive license
Apache-2.0
Continuous integration
Automated checks passing

What generative-ai does

This repository serves as Google Cloud's official hub for generative AI examples and best practices. It provides developers with concrete, runnable code demonstrating how to integrate Google's foundation models (like Gemini) and AI infrastructure (like Vertex AI) into real-world applications. The repo covers a massive surface area, from simple prompt engineering and text generation to complex RAG (Retrieval-Augmented Generation) pipelines, multimodal analysis, and agentic workflows. By providing reference implementations in Python, Node.js, and Java, it helps teams bridge the gap between reading API documentation and deploying functional AI features in enterprise environments. It essentially acts as a living cookbook for the Google Cloud AI ecosystem.

This repository is intended for software engineers, data scientists, and cloud architects building applications on Google Cloud Platform. It requires familiarity with cloud concepts, basic machine learning principles, and programming in Python or Node.js.

Extensive Jupyter notebooks: Step-by-step tutorials for interacting with Vertex AI and Gemini APIs.
RAG implementations: Reference architectures for grounding LLMs in enterprise data using Vector Search.
Multimodal examples: Code showing how to process and analyze text, images, video, and audio simultaneously.
Agent and tool use: Demonstrations of connecting models to external APIs and databases for action-taking.
Multi-language support: Examples provided in Python, Node.js, Java, and Go.
Enterprise integration: Guides on using LangChain, LlamaIndex, and other frameworks within Google Cloud.

Where teams use it

Learning Vertex AI

Developers new to Google Cloud use the introductory notebooks to understand how to authenticate and call the Gemini API.

Building RAG systems

Enterprise teams copy reference architectures to build internal knowledge bots grounded in their own documents.

Multimodal processing pipelines

Engineers build systems that automatically extract metadata and summaries from uploaded videos and images.

Evaluating LLM outputs

Data scientists use provided scripts to benchmark different prompts and models against custom evaluation datasets.

Getting started: git clone https://github.com/GoogleCloudPlatform/generative-ai.git && cd generative-ai/gemini/getting-started

README

main branch

Generative AI on Google Cloud

The latest Gemini models are available! Try out Gemini 3.6 Flash and Gemini 3.5 Flash-Lite.

Gemini Enterprise Agent Platform, the latest evolution of Vertex AI, has been released!

Check out the Google-Cloud-AI/agent-platform repository for a curated list of assets for agent building on Google Cloud.

This repository contains notebooks, code samples, sample apps, and other resources that demonstrate how to use, develop and manage generative AI workflows using Generative AI with Agent Platform.

Intro Video

	Description
`gemini/`	Discover Gemini through starter notebooks, use cases, function calling, sample apps, and more.
`search/`	Use this folder if you're interested in using Agent Search, a Google-managed solution to help you rapidly build search engines for websites and across enterprise data. (Formerly known as Enterprise Search on Generative AI App Builder).
`rag-grounding/`	Use this folder for information on Retrieval Augmented Generation (RAG) and Grounding. This is an index of notebooks and samples across other directories focused on this topic.
`vision/`	Use this folder if you're interested in building your own solutions from scratch using features from Imagen and Veo.
`audio/`	Use this folder if you're interested in building your own solutions from scratch using features from Chirp, a version of Google's Universal Speech Model (USM).
`setup-env/`	Instructions on how to set up Google Cloud, the Gen AI Python SDK, and notebook environments on Google Colab and Workbench.
`RESOURCES.md`	Learning resources (e.g. blogs, YouTube playlists) about Generative AI on Google Cloud.

Related Repositories

✨ Agent Development Kit (ADK) Samples: This repository provides ready-to-use agents built on top of the Agent Development Kit, designed to accelerate your development process. These agents cover a range of common use cases and complexities, from simple conversational bots to complex multi-agent workflows.
🚀 Agent Starter Pack
- A collection of production-ready Generative AI Agent templates built for Google Cloud.
- It accelerates development by providing a holistic, production-ready solution, addressing common challenges (Deployment & Operations, Evaluation, Customization, Observability) in building and deploying Gen AI agents.
Gemini Cookbook
genai-factory - A collection of end-to-end infrastructure blueprints to deploy generative AI infrastructures in GCP, using IaC and following security best-practices.
Google Cloud Applied AI Engineering
Vertex AI GenMedia Creative Studio - Experience Google's generative media foundational models + custom workflows.
MCP Servers for GenMedia - Empower your agents with generative media tools.
Generative AI for Marketing using Google Cloud
Generative AI for Developer Productivity
Vertex AI Core
Conversational AI
- Contact Center AI Samples
- Reimagining Customer Experience 360
Document AI
- Document AI Samples
Gemini in Google Cloud
- Cymbal Superstore
Cloud Databases
- Gen AI Databases Retrieval App
Other

Contributing

Contributions welcome! See the Contributing Guide.

Getting help

Please use the issues page to provide suggestions, feedback or submit a bug report.

Disclaimer

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

View on GitHub

Recent activity

commits and pull requests

feat(ge-demo-generator): scale generated demos to zero with a Cloud Tasks workerOpen
#3026 by ryotat7 · updated 3d ago
chore(deps): bump the npm_and_yarn group across 9 directories with 9 updatesOpen
#3025 by dependabot[bot] · updated 3d ago
Add Agent Registry publishing options to the Gemini Data Analytics HTTP Colab notebook.Draft
#3023 by copybara-service[bot] · updated 3d ago
Add Agent Registry publishing options to the Gemini Data Analytics SDK Colab notebook.Draft
#3024 by copybara-service[bot] · updated 3d ago
feat(gemini-ent-group-license): add support for sub_idOpen
#3022 by GoogleCharles · updated 3d ago
feat(ge-demo-generator): support any managed remote MCP server, deliver A2UI cards reliably, and accept a browse URL in TEMPLATE_REPOMerged
#3021 by ryotat7 · updated 4d ago
feat(ge-demo-generator): support any managed remote MCP server, deliver A2UI cards reliably, and accept a browse URL in TEMPLATE_REPO (#3021
ryotat7 committed 055dd24 · 4d ago
fix(ge-demo-generator): accept a GitHub browse URL in TEMPLATE_REPO, and stop the docs from inviting oneClosed
#3020 by ryotat7 · updated 4d ago
fix(ge-demo-generator): report the real cause of a template-fetch failureMerged
#3018 by ryotat7 · updated 7d ago
fix(ge-demo-generator): report the real cause of a template-fetch failure (#3018)
ryotat7 committed 37e4bff · 7d ago
fix(group-licensing): doc updates and module rename (#3019)
williamsmt committed bf689e6 · 7d ago
refactor: migrate multimodal BQ notebook to end-user credentials, add AI.GENERATE_TABLE remote model, rebrand to Agent Platform, and add UTM
jeffonelson committed 8d03cb5 · 8d ago

Recent open issues

view all

[Bug]: Some Gemini models are not supported on single-region endpoints, can improve by separating Gemini region with other resources' region
#3004 · 13d ago · by ujsolon
[Bug]: The request-response loogging doesn't include the principal
#3003 · 15d ago · by lgbaeza

Discussions

all 44

Code frequency

additions and deletions

+429.7K lines added, -351.2K removed over the last year.

Commits per week

last 52 weeks

457 commits in the last 52 weeks.

When work happens

weekday and hour

Commit volume by weekday and hour (UTC). Larger dots mean more commits.

Date	List	Rank	Stars gained
Mar 9, 2026	daily	#14	+194
Mar 8, 2026	daily	#18	+252

affaan-m/ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
238.5K stars · JavaScript
affaan-m/ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
234.7K stars · JavaScript
NousResearch/hermes-agent
The agent that grows with you
227K stars · Python
Significant-Gravitas/AutoGPT
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
186.2K stars · Python
microsoft/markitdown
Python tool for converting files and office documents to Markdown.
172.2K stars · Python
f/prompts.chat
f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.
166.9K stars · HTML