Groq Image Agent

image_agent.py

"""
Groq Image Agent
================

Cookbook example for `groq/image_agent.py`.
"""

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

# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------

agent = Agent(model=Groq(id="meta-llama/llama-4-scout-17b-16e-instruct"))

agent.print_response(
    "Tell me about this image",
    images=[
        Image(url="https://upload.wikimedia.org/wikipedia/commons/f/f2/LPU-v1-die.jpg"),
    ],
    stream=True,
)

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------

if __name__ == "__main__":
    pass

Run the Example

Set up your virtual environment

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

uv venv --python 3.12
.venv\Scripts\activate

Install dependencies

uv pip install -U agno groq

Export your Groq API key

export GROQ_API_KEY="your_groq_api_key_here"

$Env:GROQ_API_KEY="your_groq_api_key_here"

Run the example

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

python image_agent.py

Full source: cookbook/90_models/groq/image_agent.py

Deep Knowledge Knowledge

⌘I

Examples

Primitives

Context

Models

Tools

More

Groq Image Agent

Run the Example

​Run the Example

Run the Example