> ## Documentation Index
> Fetch the complete documentation index at: https://agno-v2.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Demo Gemma

> Stream a 3-sentence fiction story from the Ollama gemma3:12b model given a local image as input.

## Code

```python demo_gemma.py theme={null}
from pathlib import Path

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

agent = Agent(model=Ollama(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

<Snippet file="create-venv-step.mdx" />

**1. Install Ollama**

Follow the [Ollama installation guide](https://github.com/ollama/ollama?tab=readme-ov-file#macos) and run:

```bash theme={null}
ollama pull gemma3:12b
```

**2. Install dependencies**

```bash theme={null}
uv pip install -U ollama agno
```

**3. Add 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.

**4. Run Agent**

Save the code above as `demo_gemma.py`, then run:

```bash theme={null}
python demo_gemma.py
```


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.