Installation¶
Requirements¶
- Python 3.10+
- uv (recommended) or pip
Install with uv (recommended)¶
Install with pip¶
Optional Dependencies¶
pydantic-deep offers several optional dependency groups:
| Extra | Description | Use Case |
|---|---|---|
sandbox |
Docker container support | Isolated code execution |
cli |
CLI tools (typer, rich) | Interactive terminal apps |
web |
Web server (FastAPI, uvicorn) | Web-based agent interfaces |
dev |
Development tools | Testing and documentation |
all |
All optional dependencies | Everything |
Docker Sandbox¶
For isolated code execution in Docker containers:
Standalone Usage
Backends are also available separately as pydantic-ai-backend for use with any pydantic-ai agent.
CLI Tools¶
For building interactive terminal applications:
Includes: typer, rich, prompt-toolkit
Web Server¶
For web-based agent interfaces:
Includes: FastAPI, uvicorn
All Dependencies¶
Install everything:
Development¶
For running tests and building documentation:
Environment Setup¶
API Key¶
pydantic-deep uses Pydantic AI which supports multiple model providers. Set your API key:
Docker (optional)¶
For using DockerSandbox:
- Install Docker: Get Docker
- Ensure Docker daemon is running
- Pull the Python image:
Verify Installation¶
Python
import asyncio
from pydantic_deep import create_deep_agent, DeepAgentDeps, StateBackend
async def main():
agent = create_deep_agent()
deps = DeepAgentDeps(backend=StateBackend())
result = await agent.run("Say hello!", deps=deps)
print(result.output)
asyncio.run(main())
Troubleshooting¶
Import Errors¶
If you get import errors, ensure you have the correct Python version:
API Key Not Found¶
Make sure your API key is set in the environment:
Docker Permission Denied¶
On Linux, you may need to add your user to the docker group:
Then log out and back in.
Next Steps¶
- Core Concepts - Learn the fundamentals
- Basic Usage Example - Your first deep agent
- API Reference - Complete API documentation