> ## 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.

# 结构化输出的 Agent

## 代码

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

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


class MovieScript(BaseModel):
    setting: str = Field(
        ..., description="为一部大片提供一个绝佳的场景。"
    )
    ending: str = Field(
        ...,
        description="电影的结局。如果不可用，请提供一个圆满的结局。",
    )
    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="给这部电影起个名字")
    characters: List[str] = Field(..., description="这部电影的角色名字。")
    storyline: str = Field(
        ..., description="电影的故事梗概，共 3 句话。要够刺激！"
    )


# 使用 JSON 模式的 Agent
json_mode_agent = Agent(
    model=OpenAIResponses(id="gpt-4o"),
    description="你负责编写电影剧本。",
    response_model=MovieScript,
    use_json_mode=True,
)

# 使用结构化输出的 Agent
structured_output_agent = Agent(
    model=OpenAIResponses(id="gpt-4o"),  
    description="你负责编写电影剧本。",
    response_model=MovieScript,
)


# 将响应获取到变量中
# json_mode_response: RunResponse = json_mode_agent.run("New York")
# pprint(json_mode_response.content)
# structured_output_response: RunResponse = structured_output_agent.run("New York")
# pprint(structured_output_response.content)

json_mode_agent.print_response("New York")
structured_output_agent.print_response("New York")
```

## 用法

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

  <Step title="设置您的 API 密钥">
    ```bash theme={null}
    export OPENAI_API_KEY=xxx
    ```
  </Step>

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

  <Step title="运行 Agent">
    <CodeGroup>
      ```bash Mac theme={null}
      python cookbook/models/openai/responses/structured_output.py
      ```

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