Llama OpenAI Image Input File

Attach a local image file to Llama 4 Maverick via the OpenAI-compatible client and stream a description.

image_input_file.py

"""
Meta Image Input File
=====================

Cookbook example for `meta/llama_openai/image_input_file.py`.
"""

from pathlib import Path

from agno.agent import Agent
from agno.media import Image
from agno.models.meta import LlamaOpenAI
from agno.utils.media import download_image

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

agent = Agent(
    model=LlamaOpenAI(id="Llama-4-Maverick-17B-128E-Instruct-FP8"),
    markdown=True,
)

image_path = Path(__file__).parent.joinpath("sample.jpg")

download_image(
    url="https://upload.wikimedia.org/wikipedia/commons/0/0c/GoldenGateBridge-001.jpg",
    output_path=str(image_path),
)

agent.print_response(
    "Tell me about this image?",
    images=[Image(filepath=image_path)],
    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 llama-api-client openai
   
3. Export your Meta Llama API key

   Mac/Linux

   export LLAMA_API_KEY="your_llama_api_key_here"
   

   $Env:LLAMA_API_KEY="your_llama_api_key_here"
   
4. Run the example

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

   python image_input_file.py
   

Full source: cookbook/90_models/meta/llama_openai/image_input_file.py