​
代码

cookbook/models/meta/structured_output.py
from typing import List
from pydantic import BaseModel, Field
from agno.agent import Agent
from agno.models.meta import Llama

class MovieScript(BaseModel):
    name: str = Field(..., description="电影名称。")
    setting: str = Field(..., description="为电影提供一个背景设定。")
    ending: str = Field(..., description="描述电影的结局。")
    genre: str = Field(..., description="电影的类型。")
    characters: List[str] = Field(..., description="角色列表。")
    storyline: str = Field(..., description="一个三句话的故事梗概。")

agent = Agent(
    model=Llama(id="Llama-3.3-70B"),
    response_model=MovieScript,
    markdown=True,
)

agent.print_response("为科幻冒险生成电影剧本大纲。")

​
用法

1

创建虚拟环境

打开 Terminal 并创建一个 python 虚拟环境。

python3 -m venv .venv
source .venv/bin/activate
2

设置您的 LLAMA API 密钥

export LLAMA_API_KEY=YOUR_API_KEY
3

安装库

pip install llama-api-client agno
4

运行代理

python cookbook/models/meta/structured_output.py