​
代码

cookbook/models/nvidia/basic_stream.py
from agno.agent import Agent, RunResponse  # noqa
from agno.models.nvidia import Nvidia

agent = Agent(model=Nvidia(id="meta/llama-3.3-70b-instruct"), markdown=True)

# 将响应保存在变量中
# run_response: Iterator[RunResponse] = agent.run("Share a 2 sentence horror story", stream=True)
# for chunk in run_response:
#     print(chunk.content)

# 在终端打印响应
agent.print_response("Share a 2 sentence horror story", stream=True)

​
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 API 密钥

export NVIDIA_API_KEY=xxx
3

安装库

pip install -U openai agno
4

运行 Agent

python cookbook/models/nvidia/basic_stream.py