generative-ai

(★ 17,607)

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

File Explorer

Download Latest Version (.zip)

Showing a partial file list — download the zip above to see everything.

- - bug-report.yml
  - config.yml
  - feature-request.yml
- - .flake8
  - .gitleaks.toml
  - .htmlhintrc
  - .jscpd.json
  - .jupyter-nbqa.toml
  - .markdown-lint.yml
  - .mypy.ini
  - .python-lint
  - .sqlfluff
  - .textlintrc
- - assign-issue.yaml
  - links.yaml
  - linter.yaml
  - spelling.yaml
- CODEOWNERS
- PULL_REQUEST_TEMPLATE.md
- settings.json
- - README.md
- - tutorial_a2a_on_agent_engine.ipynb
  - tutorial_bidi_stream_v2.ipynb
  - tutorial_claude_with_adk_on_agent_engine.ipynb
  - tutorial_deploy_your_containerised_agent.ipynb
  - tutorial_deploy_your_first_adk_agent_on_agent_engine.ipynb
  - tutorial_get_started_with_agent_engine_terraform_deployment.ipynb
  - tutorial_get_started_with_cloud_api_registry.ipynb
  - tutorial_get_started_with_code_execution.ipynb
  - tutorial_get_started_with_live_api_on_agent_engine.ipynb
  - tutorial_mcp_on_agent_engine.ipynb
  - tutorial_multi_agent_systems_on_vertexai_with_claude.ipynb
  - tutorial_multi_agent_systems_vertexai_llama_arize.ipynb
- - a2a_http_sample.ipynb
  - a2a_sdk_sample.ipynb
  - intro_gemini_data_analytics_http.ipynb
  - intro_gemini_data_analytics_sdk.ipynb
- - intro_managed_agents_curl.ipynb
  - intro_managed_agents_python.ipynb
  - managed_agents_world_cup_analysis.ipynb
- - .env.example
  - .gitignore
  - config.py
  - evaluation_rubric.md
  - evaluation_rubric_augmented.md
  - evaluation_scenarios_user_1.json
  - evaluation_scenarios_user_2.json
  - evaluation_scenarios_user_3.json
  - evaluation_scenarios_user_4.json
  - evaluation_scenarios_user_5.json
  - pyproject.toml
  - README.md
  - run_pipeline.sh
  - test_augmented_agent.py
  - test_deployed_agent.py
  - uv.lock
- - intro_skill_registry.ipynb
- README.md
- - README.md
- README.md
- anomaly_sampling_engine.ipynb
- bigquery-import.ipynb
- bigquery_ml_gemini_and_oss_text_embedding.ipynb
- embedding-similarity-visualization.ipynb
- hybrid-search.ipynb
- intro-textemb-vectorsearch.ipynb
- intro_embeddings_tuning.ipynb
- intro_multimodal_embeddings.ipynb
- large-embs-generation-for-vvs.ipynb
- README.md
- task-type-embedding.ipynb
- vector-search-2-intro.ipynb
- vector-search-2-quickstart.ipynb
- vector-search-quickstart.ipynb
- - agent_engine_express_mode.ipynb
  - evaluating_crewai_agent_engine_customized_template.ipynb
  - evaluating_langchain_agent_engine_prebuilt_template.ipynb
  - evaluating_langgraph_agent_engine_customized_template.ipynb
  - intro_agent_engine.ipynb
  - langchain_vertex_ai_session_service.ipynb
  - langgraph_human_in_the_loop.ipynb
  - README.md
  - tracing_agents_in_agent_engine.ipynb
  - tutorial_ag2_on_agent_engine.ipynb
  - tutorial_google_maps_agent.ipynb
  - tutorial_langgraph.ipynb
  - tutorial_langgraph_rag_agent.ipynb
  - tutorial_mcp_toolbox_for_databases.ipynb
  - tutorial_vertex_ai_search_rag_agent.ipynb
- - intro_batch_prediction.ipynb
  - monitor_batch_prediction_gemini_api.ipynb
- - intro_chat_completions_api.ipynb
- - intro_agentic_vision.ipynb
  - intro_code_execution.ipynb
  - README.md
- - intro_computer_use.ipynb
- - intro_context_caching.ipynb
- - intro_controlled_generation.ipynb
- - intro_deep_research.ipynb
- - agent_as_a_judge_eval.ipynb
  - create_agent_and_run_evaluation.ipynb
  - create_genai_agent_evaluation.ipynb
  - evaluate_gemini_structured_output.ipynb
  - evaluate_images_with_predefined_gecko.ipynb
  - evaluate_managed_agents.ipynb
  - evaluate_models_in_vertex_ai_studio_and_model_garden.ipynb
  - evaluate_videos_with_predefined_gecko.ipynb
  - evaluate_with_your_python_code.ipynb
  - evaluating_adk_agent.ipynb
  - evaluating_observability_datasets.ipynb
  - evaluating_third_party_llms_vertex_ai_gen_ai_eval_sdk.ipynb
  - model_migration_with_gen_ai_eval.ipynb
  - multi_agent_evals_with_arize_and_crewai.ipynb
  - multi_agent_state_verification_eval.ipynb
  - multi_turn_agent_evaluation_with_user_simulation_metric_registration_auto_loss_analysis.ipynb
  - quick_start_gen_ai_eval.ipynb
  - view_genai_agent_evaluation_run.ipynb
- - forced_function_calling.ipynb
  - function_calling_data_structures.ipynb
  - intro_function_calling.ipynb
  - multimodal_function_calling.ipynb
  - parallel_function_calling.ipynb
  - README.md
- - intro_gemini_2_5_flash.ipynb
  - intro_gemini_2_5_flash_lite.ipynb
  - intro_gemini_2_5_image_gen.ipynb
  - intro_gemini_2_5_pro.ipynb
  - intro_gemini_3_1_flash_image_gen.ipynb
  - intro_gemini_3_1_flash_lite.ipynb
  - intro_gemini_3_1_flash_lite_image_gen.ipynb
  - intro_gemini_3_1_pro.ipynb
  - intro_gemini_3_5_flash.ipynb
  - intro_gemini_3_5_flash_lite.ipynb
  - intro_gemini_3_6_flash.ipynb
  - intro_gemini_3_7_flash.ipynb
  - intro_gemini_3_image_gen.ipynb
  - intro_gemini_chat.ipynb
  - intro_gemini_curl.ipynb
  - intro_gemini_express.ipynb
  - README.md
- - grounding_with_vais.ipynb
  - intro-grounding-gemini.ipynb
- - intro_request_response_logging.ipynb
- - intro_logprobs.ipynb
- - intro_long_context.ipynb
- - intro_to_mcp.ipynb
- - intro_model_optimizer.ipynb
- - intro_vertex_ai_multimodal_dataset.ipynb
  - README.md
- - intro_live_api_native_audio.ipynb
  - intro_multimodal_live_api.ipynb
  - intro_multimodal_live_api_genai_sdk.ipynb
  - live_api_quickstart.ipynb
  - README.md
  - real_time_rag_bank_loans_gemini_2_0.ipynb
  - real_time_rag_retail_gemini_2_0.ipynb
- - nano_banana_recipes.ipynb
  - README.md
- - intro_langchain_gemini.ipynb
  - intro_langgraph_gemini.ipynb
  - langgraph_gemini_podcast.ipynb
  - langgraph_multi-agent-rag-and-self-correction.ipynb
  - llamaindex_workflows.ipynb
- - intro_prompt_design.ipynb
- - intro_rag_engine.ipynb
  - rag_engine_cross_corpus_retrieval.ipynb
  - rag_engine_eval_service_sdk.ipynb
  - rag_engine_evaluation.ipynb
  - rag_engine_feature_store.ipynb
  - rag_engine_pinecone.ipynb
  - rag_engine_vector_search.ipynb
  - rag_engine_vertex_ai_search.ipynb
  - rag_engine_weaviate.ipynb
- - README.md
- - gemini_prompt_attacks_mitigation_examples.ipynb
  - gemini_safety_ratings.ipynb
  - react_rag_attacks_mitigations_examples.ipynb
  - README.md
- - LICENSE
  - README.md
  - seq_flask.png
  - SETUP.md
- - intro_thought_signatures.ipynb
  - intro_thought_signatures_rest.ipynb
- - local_token_counting.ipynb
- - dpo_gemini_data_prep_tuning.ipynb
  - dpo_gemini_get_started.ipynb
  - sft_gemini_automatic_evaluation.ipynb
  - sft_gemini_custom_metric_evaluation.ipynb
  - sft_gemini_migration_recipe.ipynb
  - sft_gemini_on_image_captioning.ipynb
  - sft_gemini_on_multiple_images.ipynb
  - sft_gemini_predictive_maintenance.ipynb
  - sft_gemini_qa.ipynb
  - sft_gemini_summarization.ipynb
  - sft_gemini_visual_defect_detection.ipynb
- - intro_url_context.ipynb
- - intro_multimodal_use_cases.ipynb
  - README.md
- README.md
.editorconfig
.git-blame-ignore-revs
.gitignore
.gitleaksignore
.prettierrc
.repo-metadata.json
.ruff.toml
CODE_OF_CONDUCT.md
CONTRIBUTING.md
LICENSE
README.md
RESOURCES.md
SECURITY.md

# Installation Guide

1. Get the code

git clone https://github.com/GoogleCloudPlatform/generative-ai

Downloads the entire project code from GitHub to your computer.

cd generative-ai

Moves into the project folder you just downloaded.

2. Docker

Easy Recommended

Prerequisites

Git Needed to download the project code from GitHub.
Docker Desktop Needed to build and run containers. Install it and keep it running in the background.

⚠️ This is a large repository, so this method may point to an internal sub-package rather than the actual core product. Check the full README as well.

docker compose -f agents/adk/contract-compliance-pipeline/docker-compose.yml up -d --build

Runs the command against the services defined in the compose file.

✅ Run docker compose ps to check the containers are Up. If the README mentions a port, open http://localhost:PORT in your browser.

3. CMake

Medium

Prerequisites

Git Needed to download the project code from GitHub.
CMake The tool used to generate build configuration.
C/C++ 컴파일러 Windows needs Visual Studio (Community edition, free), macOS needs Xcode Command Line Tools, Linux needs the gcc/g++ package.

⚠️ This is a large repository, so this method may point to an internal sub-package rather than the actual core product. Check the full README as well.

cd gemini/sample-apps/photo-discovery/app/linux

This project's files live in a subfolder, so move into it first.

mkdir build && cd build

Creates a folder to hold the build output and moves into it.

cmake ..

Analyzes the source code and generates build configuration files (must be run inside the build folder).

make

Compiles the code based on the generated build configuration to produce an executable.

✅ Check that an executable was created inside the build folder, then run it directly (e.g. ./build/app_name).

4. Gradle (Java/Kotlin)

Medium

Prerequisites

Git Needed to download the project code from GitHub.
JDK (Java) Required to build and run Java/Kotlin projects.
Gradle If the repo includes gradlew (Gradle Wrapper), you don't need to install Gradle separately.

⚠️ This is a large repository, so this method may point to an internal sub-package rather than the actual core product. Check the full README as well.

cd gemini/sample-apps/photo-discovery/app/android/app

This project's files live in a subfolder, so move into it first.

./gradlew build

Builds the project using Gradle.

✅ A BUILD SUCCESSFUL message means it worked. The output is created under build/.

5. Node.js

Easy

Prerequisites

Git Needed to download the project code from GitHub.
Node.js Node.js must be installed to use npm. The LTS version is recommended.

⚠️ This is a large repository, so this method may point to an internal sub-package rather than the actual core product. Check the full README as well.

cd agents/adk/new-hire-onboarding/frontend/live-onboarding

This project's files live in a subfolder, so move into it first.

npm install

Downloads and installs the libraries listed in package.json.

npm start

Starts the development/run server.

✅ After running the command, open the address shown in the terminal (usually something like http://localhost:3000) in your browser.

6. Python

Easy

Prerequisites

Git Needed to download the project code from GitHub.
Python 3 On Windows, be sure to check 'Add Python to PATH' during installation.

⚠️ This is a large repository, so this method may point to an internal sub-package rather than the actual core product. Check the full README as well.

pip install -r agents/personalized-agent-swarms/augmented_assistant_agent/requirements.txt

Installs the Python libraries listed in requirements.txt (or similar).

jupyter notebook

Launches Jupyter in your browser so you can open and run the notebook (.ipynb) files.

✅ If it runs without errors and prints output in the terminal, it worked.

7. Go

Medium

Prerequisites

Git Needed to download the project code from GitHub.
Go The Go compiler and toolchain.

⚠️ This is a large repository, so this method may point to an internal sub-package rather than the actual core product. Check the full README as well.

cd agents/adk/contract-compliance-pipeline/go-compliance-agent

This project's files live in a subfolder, so move into it first.

go build ./...

Compiles the Go program into an executable.

go run .

Runs the Go program directly without a separate build step.

✅ If the build finishes without errors, it worked. If you used go run ., check the terminal output.

8. Make

Medium

Prerequisites

Git Needed to download the project code from GitHub.
Make Usually pre-installed on Linux/macOS. On Windows, install separately (e.g. via MSYS2 or WSL).

⚠️ This is a large repository, so this method may point to an internal sub-package rather than the actual core product. Check the full README as well.

cd gemini/sample-apps/image-bash-jam

This project's files live in a subfolder, so move into it first.

make

Compiles the code based on the generated build configuration to produce an executable.

✅ If it finishes without errors, it worked. Try running the generated executable directly.

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

generative-ai

File Explorer

# Installation Guide

2. Docker

3. CMake

4. Gradle (Java/Kotlin)

5. Node.js

6. Python

7. Go

8. Make

Today's picks

Was this content helpful?

Recent Feedback

generative-ai

File Explorer

# Installation Guide

2. Docker

3. CMake

4. Gradle (Java/Kotlin)

5. Node.js

6. Python

7. Go

8. Make

Today's picks

Was this content helpful?

Recent Feedback

Download README