pydantic-ai

原文涵盖的主题

• PydanticAI — Typed AI Agents in Python
• Overview
• When to Use This Skill
• How It Works
• Step 1: Installation
• Step 2: A Minimal Agent
• Step 3: Structured Output with Pydantic Models
• Step 4: Tool Use

PydanticAI is a Python agent framework from the Pydantic team that brings the same type-safety and validation guarantees as Pydantic to LLM-based applications. It supports structured outputs (validated with Pydantic models), dependency injection for testability, streamed responses, multi-turn conversations, and tool use — across OpenAI, Anthropic, Google Gemini, Groq, Mistral, and Ollama. Use this skill when building production AI agents, chatbots, or LLM pipelines where correctness and testability matter. Use when building Python AI agents that call tools and return structured data Use when you need validated, typed LLM outputs (not raw strings) Use when you want to write unit tests for agent logic without hitting a real LLM Use when switching between LLM providers without rewriting agent code Use when the user asks about Agent, @agent.tool, RunContext, ModelRetry, or resulttype Register tools with @agent.tool — the LLM can call them during a run: Inject services (database, HTTP clients, config) into agents for testability: Write unit tests without real LLM calls: FunctionModel for deterministic test responses: ✅ Always define resulttype with a Pydantic model — avoid returning raw

这里只展示节选，请以完整原文和当前要求为准。