Image Agent

Send an image URL to a Grok vision model and search the web for context.

Code

from agno.agent import Agent
from agno.media import Image
from agno.models.xai import xAI
from agno.tools.websearch import WebSearchTools

agent = Agent(
    model=xAI(id="grok-4.5"),
    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/activate

Set your API key

export XAI_API_KEY=xxx

Install dependencies

uv pip install -U openai ddgs agno

Run Agent

Save the code above as image_agent.py, then run:

python image_agent.py