Pydantic 模型

使用PydanticAI从文本输入构造Pydantic模型的简单示例。

演示：

结构化 result_type

运行示例

pipuv

python -m pydantic_ai_examples.pydantic_model

uv run -m pydantic_ai_examples.pydantic_model

这个例子默认使用 openai:gpt-4o，但它与其他模型也能很好地配合，例如，你可以使用以下方式与 Gemini 一起运行它：

pipuv

PYDANTIC_AI_MODEL=gemini-1.5-pro python -m pydantic_ai_examples.pydantic_model

PYDANTIC_AI_MODEL=gemini-1.5-pro uv run -m pydantic_ai_examples.pydantic_model

（或 PYDANTIC_AI_MODEL=gemini-1.5-flash ...）

示例代码

pydantic_model.py

import os
from typing import cast

import logfire
from pydantic import BaseModel

from pydantic_ai import Agent
from pydantic_ai.models import KnownModelName

# 'if-token-present' means nothing will be sent (and the example will work) if you don't have logfire configured
logfire.configure(send_to_logfire='if-token-present')


class MyModel(BaseModel):
    city: str
    country: str


model = cast(KnownModelName, os.getenv('PYDANTIC_AI_MODEL', 'openai:gpt-4o'))
print(f'Using model: {model}')
agent = Agent(model, result_type=MyModel)

if __name__ == '__main__':
    result = agent.run_sync('The windy city in the US of A.')
    print(result.data)
    print(result.usage())