​
代码

from typing import Iterator

from agno.agent import Agent, RunResponse
from agno.models.openai import OpenAIChat
from agno.tools.dalle import DalleTools
from agno.utils.common import dataclass_to_dict
from rich.pretty import pprint

image_agent = Agent(
    model=OpenAIChat(id="gpt-4o"),
    tools=[DalleTools()],
    description="You are an AI agent that can create images using DALL-E.",
    instructions=[
        "When the user asks you to create an image, use the DALL-E tool to create an image.",
        "The DALL-E tool will return an image URL.",
        "Return the image URL in your response in the following format: `![image description](image URL)`",
    ],
    markdown=True,
)

run_stream: Iterator[RunResponse] = image_agent.run(
    "Create an image of a yellow siamese cat",
    stream=True,
    stream_intermediate_steps=True,
)
for chunk in run_stream:
    pprint(dataclass_to_dict(chunk, exclude={"messages"}))
    print("---" * 20)

​
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

设置你的 API 密钥

export OPENAI_API_KEY=xxx
3

安装库

pip install -U openai rich agno
4

运行 Agent

python cookbook/agent_concepts/multimodal/generate_image_with_intermediate_steps.py