install.md

Installation

Pydantic AI is available on PyPI as pydantic-ai so installation is as simple as:

pip/uv-add pydantic-ai

(Requires Python 3.10+)

This installs the pydantic_ai package, core dependencies, and libraries required to use all the models included in Pydantic AI. If you want to install only those dependencies required to use a specific model, you can install the "slim" version of Pydantic AI.

Use with Pydantic Logfire

Pydantic AI has an excellent (but completely optional) integration with Pydantic Logfire to help you view and understand agent runs.

Logfire comes included with pydantic-ai (but not the "slim" version), so you can typically start using it immediately by following the Logfire setup docs.

Running Examples

We distribute the pydantic_ai_examples directory as a separate PyPI package (pydantic-ai-examples) to make examples extremely easy to customize and run.

To install examples, use the examples optional group:

pip/uv-add "pydantic-ai[examples]"

To run the examples, follow instructions in the examples docs.

Slim Install

If you know which model you're going to use and want to avoid installing superfluous packages, you can use the pydantic-ai-slim package. For example, if you're using just [OpenAIChatModel][pydantic_ai.models.openai.OpenAIChatModel], you would run:

pip/uv-add "pydantic-ai-slim[openai]"

pydantic-ai-slim has the following optional groups:

• logfire — installs Pydantic Logfire dependency logfire PyPI ↗{:target="_blank"}
• evals — installs Pydantic Evals dependency pydantic-evals PyPI ↗{:target="_blank"}
• openai — installs OpenAI Model dependency openai PyPI ↗{:target="_blank"}
• vertexai — installs GoogleVertexProvider dependencies google-auth PyPI ↗{:target="_blank"} and requests PyPI ↗{:target="_blank"}
• google — installs Google Model dependency google-genai PyPI ↗{:target="_blank"}
• anthropic — installs Anthropic Model dependency anthropic PyPI ↗{:target="_blank"}
• groq — installs Groq Model dependency groq PyPI ↗{:target="_blank"}
• mistral — installs Mistral Model dependency mistralai PyPI ↗{:target="_blank"}
• cohere - installs Cohere Model dependency cohere PyPI ↗{:target="_blank"}
• bedrock - installs Bedrock Model dependency boto3 PyPI ↗{:target="_blank"}
• huggingface - installs Hugging Face Model dependency huggingface-hub[inference] PyPI ↗{:target="_blank"}
• outlines-transformers - installs Outlines Model dependency outlines[transformers] PyPI ↗{:target="_blank"}
• outlines-llamacpp - installs Outlines Model dependency outlines[llamacpp] PyPI ↗{:target="_blank"}
• outlines-mlxlm - installs Outlines Model dependency outlines[mlxlm] PyPI ↗{:target="_blank"}
• outlines-sglang - installs Outlines Model dependency outlines[sglang] PyPI ↗{:target="_blank"}
• outlines-vllm-offline - installs Outlines Model dependencies outlines PyPI ↗{:target="_blank"} and vllm PyPI ↗{:target="_blank"}
• duckduckgo - installs DuckDuckGo Search Tool dependency ddgs PyPI ↗{:target="_blank"}
• tavily - installs Tavily Search Tool dependency tavily-python PyPI ↗{:target="_blank"}
• exa - installs Exa Search Tool dependency exa-py PyPI ↗{:target="_blank"}
• cli - installs CLI dependencies rich PyPI ↗{:target="_blank"}, prompt-toolkit PyPI ↗{:target="_blank"}, and argcomplete PyPI ↗{:target="_blank"}
• mcp - installs MCP dependency mcp PyPI ↗{:target="_blank"}
• fastmcp - installs FastMCP dependency fastmcp PyPI ↗{:target="_blank"}
• a2a - installs A2A dependency fasta2a PyPI ↗{:target="_blank"}
• ui - installs UI Event Streams dependency starlette PyPI ↗{:target="_blank"}
• ag-ui - installs AG-UI Event Stream Protocol dependencies ag-ui-protocol PyPI ↗{:target="_blank"} and starlette PyPI ↗{:target="_blank"}
• dbos - installs DBOS Durable Execution dependency dbos PyPI ↗{:target="_blank"}
• prefect - installs Prefect Durable Execution dependency prefect PyPI ↗{:target="_blank"}

You can also install dependencies for multiple models and use cases, for example:

pip/uv-add "pydantic-ai-slim[openai,google,logfire]"