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,
)
Create a virtual environment
Terminal
and create a python virtual environment.python3 -m venv .venv
source .venv/bin/activate
Set your LLAMA API key
export LLAMA_API_KEY=YOUR_API_KEY
Install libraries
pip install llama-api-client agno
Run Agent
python cookbook/models/meta/image_input.py
Was this page helpful?