Image analysis example using CometAPI with vision models

Stream an image description from a vision model through CometAPI.

image_agent.py

"""
Image analysis example using CometAPI with vision models.
"""

from agno.agent import Agent
from agno.media import Image
from agno.models.cometapi import CometAPI

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

# Use a vision-capable model from CometAPI
agent = Agent(
    model=CometAPI(id="gpt-4o"),  # GPT-4o has vision capabilities
    markdown=True,
)

agent.print_response(
    "Describe this image in detail and tell me what you can see",
    images=[
        Image(
            url="https://httpbin.org/image/png"  # Reliable test image
        )
    ],
    stream=True,
)

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

if __name__ == "__main__":
    pass

Run the Example

1. Set up your virtual environment

   Mac

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

   uv venv --python 3.12
   .venv\Scripts\activate
   
2. Install dependencies

   uv pip install -U agno openai
   
3. Export environment variables

   Mac/Linux

   export COMETAPI_KEY="your_cometapi_key_here"
   

   $Env:COMETAPI_KEY="your_cometapi_key_here"
   
4. Run the example

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

   python image_agent.py
   

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