> ## Documentation Index
> Fetch the complete documentation index at: https://docs.xpander.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Local Model Integration with Ollama

> Learn how to integrate local LLM models using Ollama with Xpander SDK for privacy-focused AI applications

<AccordionGroup>
  <Accordion title="Prerequisites">
    ### Virtual Environment Setup

    ```bash setup.sh theme={"dark"}
    python3 -m venv .venv
    source .venv/bin/activate
    pip install "xpander-sdk[agno]"
    ```

    ### Environment Setup

    The `.env` file is created when you download your agent code:

    ```bash theme={"dark"}
    xpander init
    ```

    This downloads your agent code from the platform with the `.env` file pre-configured with your keys.

    ### Ollama Setup

    Install and start Ollama, then pull a model:

    ```bash setup_ollama.sh theme={"dark"}
    # Install Ollama (follow instructions at https://ollama.ai)
    # Pull a model
    ollama pull gpt-oss:20b
    ```
  </Accordion>
</AccordionGroup>

```python local_model_example.py theme={"dark"}
from dotenv import load_dotenv
load_dotenv()

from xpander_sdk import Backend
from agno.agent import Agent
from agno.models.ollama import Ollama

# Initialize backend
backend = Backend()

# Override model with local Ollama
agno_agent = Agent(**backend.get_args(override={
    'model': Ollama(id="gpt-oss:20b")
}))

# Test the local model
agno_agent.print_response(message="How to install xpander-cli?")
```

## How to Run

1. Make sure Ollama is running with your chosen model
2. Run the example:

```bash local_model_example.py theme={"dark"}
python local_model_example.py
```

This example shows model override capabilities where you can use local Ollama models while maintaining all Xpander backend benefits including configuration management, conversation memory, and storage. The hybrid architecture provides local privacy for inference while keeping cloud-based features for everything else.

## Production Deployment

For creating and deploying agents to production, see the [Setup and Deployment Guide](/Examples/00-setup-deployment).