> ## Documentation Index
> Fetch the complete documentation index at: https://ikun.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# 具有结构化输出的代理

## 代码

```python cookbook/models/litellm/structured_output.py theme={null}
from typing import List

from agno.agent import Agent, RunResponse  # noqa
from agno.models.litellm import LiteLLM
from pydantic import BaseModel, Field
from rich.pretty import pprint  # noqa


class MovieScript(BaseModel):
    setting: str = Field(
        ..., description="为一部大片电影提供一个漂亮的场景。"
    )
    ending: str = Field(
        ...,
        description="电影的结局。如果不可用，请提供一个快乐的结局。",
    )
    genre: str = Field(
        ...,
        description="电影的类型。如果不可用，请选择动作片、惊悚片或浪漫喜剧。",
    )
    name: str = Field(..., description="为这部电影起个名字")
    characters: List[str] = Field(..., description="这部电影的角色名字。")
    storyline: str = Field(
        ..., description="这部电影的 3 句话故事情节。要令人兴奋！"
    )


json_mode_agent = Agent(
    model=LiteLLM(id="gpt-4o"),
    description="你负责写电影剧本。",
    response_model=MovieScript,
    debug_mode=True,
)

json_mode_agent.print_response("纽约")
```

## 使用方法

<Steps>
  <Snippet file="create-venv-step.mdx" />

  <Step title="设置你的 API 密钥">
    ```bash theme={null}
    export LITELLM_API_KEY=xxx
    ```
  </Step>

  <Step title="安装库">
    ```bash theme={null}
    pip install -U litellm openai agno
    ```
  </Step>

  <Step title="运行代理">
    <CodeGroup>
      ```bash Mac theme={null}
      python cookbook/models/litellm/structured_output.py
      ```

      ```bash Windows theme={null}
      python cookbook/models/litellm/structured_output.py
      ```
    </CodeGroup>
  </Step>
</Steps>