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

# Ollama

> Run local large language models securely with Ollama.

<Frame>
  <img src="https://mintcdn.com/arivu/piekGGEpY74vFGfF/images/ollama.png?fit=max&auto=format&n=piekGGEpY74vFGfF&q=85&s=25a91cb5c3ada50a3d293a0bc6701d58" alt="Ollama" width="1917" height="903" data-path="images/ollama.png" />
</Frame>

## Overview

Ollama is an open-source tool that allows you to run large language models locally. It is the premier choice for organizations that need strict data privacy or completely offline AI capabilities.

<CardGroup cols={2}>
  <Card title="Privacy First" icon="shield-halved">
    Your data never leaves your environment.
  </Card>

  <Card title="Ease of Use" icon="play">
    Execute models with a simple `ollama run <model>` command.
  </Card>
</CardGroup>

## Configuration

<Steps>
  <Step title="Install Ollama">
    Download and install the runner from [Ollama's website](https://ollama.com/), and pull a model (e.g., `ollama pull llama3`).
  </Step>

  <Step title="Configure Default URL">
    Ollama defaults to running its API engine on localhost port 11434:

    <CodeGroup>
      ```bash .env theme={null}
      OLLAMA_BASE_URL="http://localhost:11434"
      DEFAULT_MODEL="llama3"
      ```
    </CodeGroup>
  </Step>
</Steps>

<Warning>If Arivu is running inside a Docker container, your host might need to be referenced via `http://host.docker.internal:11434` instead of `localhost`.</Warning>