Prerequisites
- Python 3.10+
- uv package manager
- Anthropic API key (or another supported model provider)
- Snow Leopard Cloud API key
- A Snow Leopard Cloud instance with at least one data source connected
- Your instance ID, from the instance’s Connection Info tab
Don’t have data? Load the sample Northwind dataset into a PostgreSQL database that Snow Leopard Cloud can reach, such as a hosted Neon or Supabase database. Run the dataset’s
northwind.sql script against your database, then add the database as a data source in your instance.Start from scratch
Clone and run the complete working example:Bring your own agent
Already have a Pydantic AI agent? Add Snow Leopard data retrieval with these steps.1. Install dependencies
2. Create the Snow Leopard tool
Add a tool to your agent that calls Snow Leopard to retrieve data:3. Customize the tool description
The tool’s docstring tells the agent when and how to use it. Update it to describe your specific data:Next steps
- View the full example on GitHub
- See our full API documentation to learn about the Retrieve and Response endpoints
- Improve accuracy by giving Snow Leopard feedback about your business logic and terminology
- See this quickstart in action with the Data Agent recipe