Getting Help¶

Documentation¶

This documentation is your primary resource. Use the search bar (press / or s) to find specific topics.

GitHub Issues¶

For bugs, feature requests, or questions:

:fontawesome-brands-github: Open an Issue

Before Opening an Issue¶

Search existing issues - Your problem may already be reported
Check the docs - The answer might be here
Prepare a minimal example - Help us reproduce the issue

Bug Report Template¶

## Description
[Clear description of the bug]

## Steps to Reproduce
1. Create agent with...
2. Call agent.run()...
3. Observe error...

## Expected Behavior
[What you expected to happen]

## Actual Behavior
[What actually happened]

## Environment
- pydantic-deep version: X.X.X
- Python version: 3.XX
- OS: [e.g., macOS 14.0]

Community Resources¶

Pydantic AI¶

pydantic-deep is built on Pydantic AI. Their documentation is an excellent resource:

Pydantic¶

For data validation and type hints:

Pydantic Documentation

FAQ¶

How is pydantic-deep different from LangChain?¶

pydantic-deep is built on Pydantic AI, which provides:

Type-safe agents with Pydantic models
Simpler, more pythonic API
Better IDE support and autocomplete
No complex chain abstractions

Can I use models other than Anthropic?¶

Yes! Pydantic AI supports multiple providers:

# OpenAI
agent = create_deep_agent(model="openai:gpt-4")

# Google
agent = create_deep_agent(model="google:gemini-1.5-pro")

# Anthropic (default)
agent = create_deep_agent(model="openai:gpt-4.1")

How do I run without API calls (for testing)?¶

Use TestModel from Pydantic AI:

from pydantic_ai.models.test import TestModel

agent = create_deep_agent(model=TestModel())

Can I use pydantic-deep with async frameworks?¶

Yes! pydantic-deep is fully async-native:

from fastapi import FastAPI
from pydantic_deep import create_deep_agent, DeepAgentDeps, StateBackend

app = FastAPI()
agent = create_deep_agent()

@app.post("/chat")
async def chat(prompt: str):
    deps = DeepAgentDeps(backend=StateBackend())
    result = await agent.run(prompt, deps=deps)
    return {"response": result.output}

How do I persist files between runs?¶

Use FilesystemBackend instead of StateBackend:

from pydantic_deep import FilesystemBackend

backend = FilesystemBackend("/path/to/workspace")
deps = DeepAgentDeps(backend=backend)