Demo Gemma
Stream a 3-sentence fiction story from the Ollama gemma3:12b model given a local image as input.
Code
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="gemma3:12b"), markdown=True)
image_path = Path(__file__).parent.joinpath("super-agents.png")
agent.print_response(
"Write a 3 sentence fiction story about the image",
images=[Image(filepath=image_path)],
stream=True,
)
Usage
Set up your virtual environment
uv venv --python 3.12
source .venv/bin/activateStart 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_KEYPull the model
ollama pull gemma3:12bInstall dependencies
uv pip install -U ollama agnoAdd sample image
Place a sample image named super-agents.png in the same directory as the script, or update image_path to point to your own image.
Run Agent
Save the code above as demo_gemma.py, then run:
python demo_gemma.py