Retrieval Demo

A Python demonstration project showcasing retrieval-augmented generation (RAG) using LangGraph, OpenAI embeddings, and Weaviate vector store.

Prerequisites

• Python 3.13.7 (see .tool-versions)
• uv package manager
• Docker and Docker Compose

Setup

1. Clone and install dependencies:

   uv sync --dev

2. Set up environment variables: Copy the example environment file and fill in your API keys:

   cp .env.example .env

   Edit .env with your OpenAI API key and other required variables.

3. Start the Weaviate vector store:

   docker compose up -d

4. Install pre-commit hooks:

   pre-commit install

Services

Weaviate Vector Store

• URL: http://localhost:8080
• API Documentation: http://localhost:8080/v1
• GraphQL Playground: http://localhost:8080/v1/graphql
• Configuration: Supports OpenAI embeddings with automatic sparse vectors for text fields

Usage

Run the main application:

uv run retrieval-demo

Development

Code Quality

# Format code
uv run ruff format

# Check linting
uv run ruff check

# Run tests
uv run pytest

# Run all pre-commit hooks
pre-commit run --all-files

Docker Services

# Start services
docker compose up -d

# View logs
docker compose logs -f

# Stop services
docker compose down

# Reset Weaviate data
docker compose down -v