Tutorial for prod-like Agentic RAG with Weaviate

[sohanmaheshwar]

Added tutorial for Agentic RAG with Weaviate

This example has a corpus of 50 documents and some hierarchy permissions to make the example more production-like

Testing

# 1. Clone the reference implementation
git clone https://github.com/authzed/agentic-rag-weaviate
cd agentic-rag-weaviate

# 2. Start services (Weaviate + SpiceDB)
docker-compose up -d

# 3. Install Python dependencies
python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt

# 4. Configure environment
cp .env.example .env
# Edit .env with your OpenAI API key

# 5. Initialize data (loads schema, relationships, and documents)
python3 examples/setup_environment.py

# 6. Run example queries via CLI
python3 examples/basic_example.py

# 7. (Optional) Launch the web UI
python3 run_ui.py
# Opens http://localhost:8000 automatically

[vercel]

Deployment failed with the following error:

You don't have permission to create a Preview Deployment for this Vercel project: docs.

View Documentation: https://vercel.com/docs/accounts/team-members-and-roles

[github-actions]

Preview deployment status for this pull request.

Name	Status	Preview	Updated (UTC)
docs	🟢 Ready	Visit Preview	Mar 20, 2026 01:48pm

[tstirrat15]

LGTM