Skip to main content

​
Code

cookbook/models/meta/image_input.py
from agno.agent import Agent
from agno.media import Image
from agno.models.meta import Llama

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

agent.print_response(
    "Describe the scene in this image.",
    images=[Image(content=image_bytes)],
    stream=True,
)

​
Usage

1

Create a virtual environment

Open the Terminal and create a python virtual environment.
python3 -m venv .venv
source .venv/bin/activate
2

Set your LLAMA API key

export LLAMA_API_KEY=YOUR_API_KEY
3

Install libraries

pip install llama-api-client agno
4

Run Agent

python cookbook/models/meta/image_input.py