​
Code

cookbook/models/meta/async_tool_use.py
import asyncio

from agno.agent import Agent
from agno.models.meta import Llama
from agno.tools.duckduckgo import DuckDuckGoTools

agent = Agent(
    model=Llama(id="Llama-4-Maverick-17B-128E-Instruct-FP8"),
    tools=[DuckDuckGoTools()],
    show_tool_calls=True,
    markdown=True,
)

asyncio.run(
    agent.aprint_response("What's happening in France?", stream=True)
)

​
Usage

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

设置你的 LLAMA API 密钥

export LLAMA_API_KEY=YOUR_API_KEY
3

安装库

pip install llama-api-client duckduckgo-search agno
4

运行 Agent

python cookbook/models/meta/async_tool_use.py