Image Agent
Send an image to an OpenAI agent and combine vision with web search.
Code
from agno.agent import Agent
from agno.media import Image
from agno.models.openai import OpenAIChat
from agno.tools.websearch import WebSearchTools
agent = Agent(
model=OpenAIChat(id="gpt-4o"),
tools=[WebSearchTools()],
markdown=True,
)
agent.print_response(
"Tell me about this image and give me the latest news about it.",
images=[
Image(
url="https://upload.wikimedia.org/wikipedia/commons/0/0c/GoldenGateBridge-001.jpg"
)
],
stream=True,
)Usage
Set up your virtual environment
uv venv --python 3.12
source .venv/bin/activateSet your API key
export OPENAI_API_KEY=xxxInstall dependencies
uv pip install -U openai ddgs agnoRun Agent
Save the code above as image_agent.py, then run:
python image_agent.py