Pydantic AI
GenAI Agent Framework, the Pydantic way
Pydantic AI is a Python agent framework designed to make it less painful to build production grade applications with Generative AI.
Available Resources
Overview
Coding Agent Skills
Pydantic AI Gateway
Getting Help
Installation
Troubleshooting
Core Concepts
Agents
Agent Specs
Capabilities
Dependencies
Direct Model Requests
Hooks
Messages and chat history
Output
Models & Providers
Anthropic
Bedrock
Cerebras
Cohere
Google
Groq
Hugging Face
Mistral
Ollama
OpenAI
OpenRouter
Overview
xAI
Tools & Toolsets
Common Tools
Deferred Tools
Native Tools
Third-Party Tools
Function Tools
Advanced Tool Features
Toolsets
Advanced Features
Image, Audio, Video & Document Input
HTTP Request Retries
Thinking
Guides
Embeddings
Extensibility
Multi-Agent Patterns
Testing
Web Chat UI
MCP
Client
Overview
Server
Pydantic AI Harness
Code Mode
Overview
Pydantic Evals
Overview
Built-in Evaluators
Custom Evaluators
Third-Party Integrations
LLM Judge
Overview
Report Evaluators
Span-Based
Simple Validation
Core Concepts
Quick Start
Concurrency & Performance
Dataset Management
Dataset Serialization
Case Lifecycle Hooks
Logfire Integration
Metrics & Attributes
Multi-Run Evaluation
Retry Strategies
Online Evaluation
Pydantic Graph
Decisions
Getting Started
Joins & Reducers
Parallel Execution
Steps
Overview
Integrations
Command Line Interface (CLI)
Apache Airflow
DBOS
Kitaru
Overview
Prefect
Restate
Temporal
Debugging & Monitoring with Pydantic Logfire
AG-UI
Overview
Vercel AI
Examples
Agent User Interaction (AG-UI)
Bank Support
Chat App with FastAPI
Data Analyst
RAG
SQL Generation
Flight Booking
Pydantic Model
Weather Agent
Setup
Slack Lead Qualifier with Modal
Stream Markdown
Stream Whales
API Reference
Link: [](
pydantic_ai.models.anthropic
pydantic_ai.models
pydantic_ai.models.bedrock
pydantic_ai.models.cerebras
pydantic_ai.models.cohere
pydantic_ai.models.fallback
pydantic_ai.models.function
pydantic_ai.models.google
pydantic_ai.models.groq
pydantic_ai.models.huggingface
pydantic_ai.models.instrumented
pydantic_ai.models.mcp_sampling
pydantic_ai.models.mistral
pydantic_ai.models.ollama
pydantic_ai.models.openai
pydantic_ai.models.openrouter
pydantic_ai.models.test
pydantic_ai.models.wrapper
pydantic_ai.models.xai
pydantic_ai.agent
pydantic_ai.capabilities
pydantic_ai.common_tools
pydantic_ai — Concurrency
pydantic_ai.direct
pydantic_ai.durable_exec
pydantic_ai.embeddings
pydantic_ai.exceptions
pydantic_ai.ext
pydantic_ai.format_prompt
pydantic_ai.function_signature
pydantic_ai.mcp
pydantic_ai.messages
pydantic_ai.native_tools
pydantic_ai.output
pydantic_ai.profiles
pydantic_ai.providers
pydantic_ai.result
pydantic_ai.retries
pydantic_ai.run
pydantic_ai.settings
pydantic_ai.tools
pydantic_ai.toolsets
pydantic_ai.usage
pydantic_evals.dataset
pydantic_evals.evaluators
pydantic_evals.generation
pydantic_evals.lifecycle
pydantic_evals.online
pydantic_evals.online_capability
pydantic_evals.otel
pydantic_evals.reporting
pydantic_graph.basenode
pydantic_graph.decision
pydantic_graph.exceptions
pydantic_graph.graph_builder
pydantic_graph.join
pydantic_graph.node
pydantic_graph.step
pydantic_graph.util
pydantic_ai.ui.ag_ui
pydantic_ai.ui
pydantic_ai.ui.vercel_ai
Project
Upgrade Guide
Contributing
Version Policy
How to Use This Skill
Reference these resources when working with Pydantic AI.