Multimodal Agent

Send a local image to an Ollama gemma3 agent that writes a 3 sentence fiction story about it.

Code

multimodal_agent.py
from pathlib import Path

from agno.agent import Agent
from agno.media import Image
from agno.models.ollama import Ollama

agent = Agent(
    model=Ollama(host="http://localhost:11434", api_key=None, id="gemma3"),
    markdown=True,
)

image_path = Path(__file__).parent.joinpath("sample.jpg")
agent.print_response(
    "Write a 3 sentence fiction story about the image",
    images=[Image(filepath=image_path)],
)

Usage

Set up your virtual environment

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

Start the local Ollama service

Install Ollama and start its desktop app or service on http://localhost:11434. If you start it manually with ollama serve, keep that process running in a separate terminal.

In the terminal where you will pull models and run Python, select that server and clear the direct-cloud key. The native Ollama client also reads this key independently of Agno.

export OLLAMA_HOST=http://localhost:11434
unset OLLAMA_API_KEY

Pull the model

ollama pull gemma3

Install dependencies

uv pip install -U ollama agno

Add sample image

Place a sample image named sample.jpg in the same directory as your script, or update the image_path to point to your desired image.

Run Agent

python multimodal_agent.py