> ## 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/ollama/structured_output.py theme={null}
import asyncio
from typing import List

from agno.agent import Agent
from agno.models.ollama import Ollama
from pydantic import BaseModel, Field


class MovieScript(BaseModel):
    name: str = Field(..., description="为这部电影起个名字")
    setting: str = Field(
        ..., description="为这部大片提供一个不错的场景设定。"
    )
    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、惊悚或浪漫喜剧。",
    )
    characters: List[str] = Field(..., description="这部电影的角色名字。")
    storyline: str = Field(
        ..., description="电影的故事情节，共3句话。要够刺激！"
    )


# 返回结构化输出的代理
structured_output_agent = Agent(
    model=Ollama(id="llama3.2"),
    description="你负责编写电影剧本。",
    response_model=MovieScript,
)

# 同步运行代理
structured_output_agent.print_response("Llamas ruling the world")


# 异步运行代理
async def run_agents_async():
    await structured_output_agent.aprint_response("Llamas ruling the world")


asyncio.run(run_agents_async())
```

## 使用方法

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

  <Step title="安装 Ollama">
    请遵循[安装指南](https://github.com/ollama/ollama?tab=readme-ov-file#macos)并运行：

    ```bash theme={null}
    ollama pull llama3.2
    ```
  </Step>

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

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

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