Azure Image Agent

Migrate an Azure AI Foundry image-URL agent from retired Llama 3.2 Vision to Llama 4 Scout.

The source-fidelity code uses a retired Azure AI Foundry model. Replace it with Llama 4 Scout before running the example.

Microsoft retired Llama-3.2-11B-Vision-Instruct on June 13, 2026. Deploy Llama-4-Scout-17B-16E-Instruct, point AZURE_ENDPOINT at that deployment, and replace the model ID before running. See the Azure model retirement schedule.

image_agent.py

"""
Azure Image Agent
=================

Cookbook example for `azure/ai_foundry/image_agent.py`.
"""

from agno.agent import Agent
from agno.media import Image
from agno.models.azure import AzureAIFoundry

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

agent = Agent(
    model=AzureAIFoundry(id="Llama-3.2-11B-Vision-Instruct"),
    markdown=True,
)

agent.print_response(
    "Tell me about this image.",
    images=[
        Image(
            url="https://raw.githubusercontent.com/Azure/azure-sdk-for-python/main/sdk/ai/azure-ai-inference/samples/sample1.png",
            detail="high",
        )
    ],
    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 aiohttp azure-ai-inference
   
3. Export environment variables

   Mac/Linux

   export AZURE_API_KEY="your_azure_api_key_here"
   export AZURE_ENDPOINT="your_azure_endpoint_here"
   

   $Env:AZURE_API_KEY="your_azure_api_key_here"
   $Env:AZURE_ENDPOINT="your_azure_endpoint_here"
   
4. Use Llama 4 Scout

   Deploy Llama-4-Scout-17B-16E-Instruct, update AZURE_ENDPOINT, and replace Llama-3.2-11B-Vision-Instruct in the saved file.

5. Run the example

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

   python image_agent.py
   

Full source: cookbook/90_models/azure/ai_foundry/image_agent.py