wehub-resource-sync
ec2b666284
Continuous Integration / Pre-commit Linter (push) Waiting to run
Continuous Integration / Mypy Check (Python 3.10) (push) Waiting to run
Continuous Integration / Mypy Check (Python 3.11) (push) Waiting to run
Continuous Integration / Mypy Check (Python 3.12) (push) Waiting to run
Continuous Integration / Mypy Check (Python 3.13) (push) Waiting to run
Continuous Integration / Unit Tests (Python 3.10) (push) Waiting to run
Continuous Integration / Unit Tests (Python 3.11) (push) Waiting to run
Continuous Integration / Unit Tests (Python 3.12) (push) Waiting to run
Continuous Integration / Unit Tests (Python 3.13) (push) Waiting to run
Continuous Integration / Unit Tests (Python 3.14) (push) Waiting to run
Continuous Integration / A2A v0.3 Tests (Python 3.10) (push) Waiting to run
Continuous Integration / A2A v0.3 Tests (Python 3.11) (push) Waiting to run
Continuous Integration / A2A v0.3 Tests (Python 3.12) (push) Waiting to run
Continuous Integration / A2A v0.3 Tests (Python 3.13) (push) Waiting to run
Continuous Integration / A2A v0.3 Tests (Python 3.14) (push) Waiting to run
Copybara PR Handler / close-imported-pr (push) Waiting to run
1.6 KiB
1.6 KiB
Files Retrieval Agent
A sample agent that demonstrates using FilesRetrieval with the
gemini-embedding-2-preview embedding model for retrieval-augmented
generation (RAG) over local files.
What it does
This agent indexes local text files from the data/ directory using
FilesRetrieval (backed by LlamaIndex's VectorStoreIndex and Google's
gemini-embedding-2-preview embedding model), then answers user questions
by retrieving relevant documents before generating a response.
Prerequisites
- Python 3.10+
google-genai >= 1.64.0(required forgemini-embedding-2-previewsupport via the Vertex AIembedContentendpoint)llama-index-embeddings-google-genai >= 0.3.0
Install dependencies:
uv sync --all-extras
Authentication
Configure one of the following:
Google AI API:
export GOOGLE_API_KEY="your-api-key"
Vertex AI:
export GOOGLE_GENAI_USE_ENTERPRISE=1
export GOOGLE_CLOUD_PROJECT="your-project-id"
export GOOGLE_CLOUD_LOCATION="us-central1"
Note: gemini-embedding-2-preview is currently only available in
us-central1.
Usage
cd contributing/samples
# Interactive CLI
adk run files_retrieval_agent
# Web UI
adk web .
Example queries
- "What agent types does ADK support?"
- "How does FilesRetrieval work?"
- "What tools are available in ADK?"
File structure
files_retrieval_agent/
├── __init__.py
├── agent.py # Agent definition with FilesRetrieval tool
├── data/
│ ├── adk_overview.txt # ADK architecture overview
│ └── tools_guide.txt # ADK tools documentation
└── README.md