Image Agent

Send an image to a Groq vision model and stream the description.

Pass an Image to print_response() and use a vision-capable model such as qwen/qwen3.6-27b.

This example disables thinking with reasoning_effort="none" so the streamed output contains the image description. See Groq vision for current model support.

Code

from agno.agent import Agent
from agno.media import Image
from agno.models.groq import Groq

agent = Agent(model=Groq(id="qwen/qwen3.6-27b", request_params={"reasoning_effort": "none"}))

agent.print_response(
    "Tell me about this image",
    images=[
        Image(url="https://agno-public.s3.amazonaws.com/images/krakow_mariacki.jpg"),
    ],
    stream=True,
)

Usage

Set up your virtual environment

uv venv --python 3.12
source .venv/bin/activate

Set your API key

export GROQ_API_KEY=xxx

Install dependencies

uv pip install -U groq agno

Run Agent

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

python image_agent.py

Developer Resources