> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/pfrankov/obsidian-local-gpt/llms.txt
> Use this file to discover all available pages before exploring further.

# Installation

> Install Local GPT and its dependencies to start using AI in your Obsidian vault

## Prerequisites

Before installing Local GPT, ensure you have:

* **Obsidian** version 0.15.0 or higher
* An AI provider configured (Ollama, OpenAI, or OpenAI-compatible API)

<Note>
  Local GPT requires the **AI Providers** plugin as a dependency. We'll install this in the steps below.
</Note>

## Installation Steps

### Step 1: Install AI Providers Plugin

The AI Providers plugin acts as a central hub for managing AI connections in Obsidian.

<Steps>
  <Step title="Open Community Plugins">
    In Obsidian, open **Settings** → **Community plugins** → **Browse**
  </Step>

  <Step title="Search for AI Providers">
    Search for `AI Providers` in the plugin browser
  </Step>

  <Step title="Install and Enable">
    Click **Install**, then **Enable** the plugin
  </Step>
</Steps>

<Tip>
  You can also install AI Providers directly from the Obsidian plugin store: [AI Providers](https://obsidian.md/plugins?id=ai-providers)
</Tip>

### Step 2: Install Local GPT Plugin

<Tabs>
  <Tab title="Obsidian Plugin Store (Recommended)">
    <Steps>
      <Step title="Open Community Plugins">
        In Obsidian, go to **Settings** → **Community plugins** → **Browse**
      </Step>

      <Step title="Search for Local GPT">
        Type `Local GPT` in the search bar
      </Step>

      <Step title="Install and Enable">
        Click **Install**, then **Enable** to activate the plugin
      </Step>
    </Steps>

    <Card title="Direct Link" icon="link" href="https://obsidian.md/plugins?id=local-gpt">
      Open Local GPT in the Obsidian plugin store
    </Card>
  </Tab>

  <Tab title="BRAT (Beta Testing)">
    If you want to test beta features or development versions, use BRAT:

    <Steps>
      <Step title="Install BRAT">
        Install the [BRAT plugin](https://obsidian.md/plugins?id=obsidian42-brat) from the community plugins
      </Step>

      <Step title="Add Local GPT">
        In BRAT settings, click **Add Beta Plugin** and enter:

        ```
        pfrankov/obsidian-local-gpt
        ```
      </Step>

      <Step title="Enable the Plugin">
        Enable Local GPT in **Settings** → **Community plugins**
      </Step>
    </Steps>

    <Warning>
      BRAT installs pre-release versions that may contain bugs. Use this method only if you want to test new features.
    </Warning>
  </Tab>
</Tabs>

### Step 3: Configure an AI Provider

With both plugins installed, you need to configure at least one AI provider.

<AccordionGroup>
  <Accordion icon="robot" title="Option 1: Ollama (Local, Recommended)">
    **Ollama** runs AI models completely offline on your machine.

    <Steps>
      <Step title="Install Ollama">
        Download and install Ollama from [ollama.ai](https://ollama.ai)
      </Step>

      <Step title="Pull a Model">
        Open a terminal and run:

        ```bash theme={null}
        ollama pull gemma2
        ```

        Or try other models like `llama3`, `mistral`, `qwen2`, etc.
      </Step>

      <Step title="Configure in Obsidian">
        1. Open **Settings** → **AI Providers**
        2. Click **Add Provider** → **Ollama**
        3. Set the URL to `http://localhost:11434` (default)
        4. Select your model (e.g., `gemma2:latest`)
        5. Save the provider
      </Step>

      <Step title="Set as Main Provider">
        In **Settings** → **Local GPT**, select your Ollama provider as the **Main Provider**
      </Step>
    </Steps>

    <Tip>
      For vision support, pull a vision model:

      ```bash theme={null}
      ollama pull llava
      # or
      ollama pull bakllava
      ```

      Then configure it as the **Vision Provider** in Local GPT settings.
    </Tip>
  </Accordion>

  <Accordion icon="cloud" title="Option 2: OpenAI API">
    Use OpenAI's cloud models like GPT-4.

    <Steps>
      <Step title="Get API Key">
        Sign up at [platform.openai.com](https://platform.openai.com) and create an API key
      </Step>

      <Step title="Configure in Obsidian">
        1. Open **Settings** → **AI Providers**
        2. Click **Add Provider** → **OpenAI**
        3. Enter your API key
        4. Select a model (e.g., `gpt-4o-mini`)
        5. Save the provider
      </Step>

      <Step title="Set as Main Provider">
        In **Settings** → **Local GPT**, select your OpenAI provider as the **Main Provider**
      </Step>
    </Steps>

    <Warning>
      Using OpenAI's API sends your data to their servers and incurs usage costs.
    </Warning>
  </Accordion>

  <Accordion icon="server" title="Option 3: OpenAI-Compatible API">
    Connect to any OpenAI-compatible endpoint (LM Studio, LocalAI, etc.).

    <Steps>
      <Step title="Start Your Server">
        Ensure your OpenAI-compatible server is running (e.g., LM Studio, text-generation-webui with OpenAI extension)
      </Step>

      <Step title="Configure in Obsidian">
        1. Open **Settings** → **AI Providers**
        2. Click **Add Provider** → **OpenAI Compatible**
        3. Enter the base URL (e.g., `http://localhost:8080/v1`)
        4. Add API key if required
        5. Select or enter the model name
        6. Save the provider
      </Step>

      <Step title="Set as Main Provider">
        In **Settings** → **Local GPT**, select your provider as the **Main Provider**
      </Step>
    </Steps>
  </Accordion>
</AccordionGroup>

## Optional: Configure RAG (Enhanced Actions)

To enable context-aware responses using RAG, you need an embedding model:

<Steps>
  <Step title="Install an Embedding Model">
    For Ollama users, pull an embedding model:

    ```bash theme={null}
    # For English content
    ollama pull nomic-embed-text

    # For multilingual content
    ollama pull bge-m3
    ```
  </Step>

  <Step title="Configure Embedding Provider">
    1. In **Settings** → **AI Providers**, add a new Ollama provider
    2. Select your embedding model (e.g., `nomic-embed-text:latest`)
    3. In **Settings** → **Local GPT**, set this as the **Embedding Provider**
  </Step>
</Steps>

<Note>
  RAG features work by analyzing your linked notes, backlinks, and PDFs to provide more contextual AI responses. Learn more in the [RAG System guide](/advanced/rag-system).
</Note>

## Optional: Configure Hotkeys

Set up keyboard shortcuts for quick access to Local GPT features:

<Steps>
  <Step title="Open Hotkey Settings">
    Go to **Settings** → **Hotkeys**
  </Step>

  <Step title="Search for Local GPT">
    Type `Local` in the search bar to filter Local GPT commands
  </Step>

  <Step title="Assign Shortcuts">
    * **Local GPT: Show context menu** - e.g., `Cmd+M` or `Ctrl+M`
    * **Local GPT: Action Palette** - e.g., `Cmd+J` or `Ctrl+J`
  </Step>
</Steps>

## Verify Installation

To confirm everything is working:

<Steps>
  <Step title="Open a Note">
    Create or open any note in your vault
  </Step>

  <Step title="Select Text">
    Highlight a sentence or paragraph
  </Step>

  <Step title="Open Context Menu">
    Right-click the selection (or use your hotkey) and look for Local GPT actions
  </Step>

  <Step title="Test an Action">
    Try the **Summarize** action to verify your AI provider is working
  </Step>
</Steps>

<Check>
  If you see AI-generated content appear in your note, installation is complete!
</Check>

## Troubleshooting

<AccordionGroup>
  <Accordion title="No AI Providers showing up">
    Make sure the **AI Providers** plugin is installed and enabled. Restart Obsidian if needed.
  </Accordion>

  <Accordion title="Ollama connection failed">
    * Verify Ollama is running: `ollama list` in terminal
    * Check the URL is `http://localhost:11434`
    * Try pulling the model again: `ollama pull gemma2`
  </Accordion>

  <Accordion title="Actions not appearing in context menu">
    * Ensure Local GPT plugin is enabled
    * Check that you have at least one Main Provider configured
    * Try reloading Obsidian
  </Accordion>

  <Accordion title="Embedding provider errors">
    * Embedding providers are optional for basic functionality
    * Ensure you've pulled an embedding model: `ollama pull nomic-embed-text`
    * Verify the embedding provider is configured separately from the main provider
  </Accordion>
</AccordionGroup>

For more help, see the [Troubleshooting guide](/advanced/troubleshooting).

## Next Steps

<CardGroup cols={2}>
  <Card title="Quickstart Guide" icon="rocket" href="/quickstart">
    Learn how to use Local GPT effectively
  </Card>

  <Card title="AI Providers Setup" icon="gear" href="/guides/ai-providers-setup">
    Advanced provider configuration options
  </Card>

  <Card title="Create Custom Actions" icon="wand-magic-sparkles" href="/guides/creating-custom-actions">
    Build actions tailored to your workflow
  </Card>

  <Card title="Action Palette" icon="palette" href="/features/action-palette">
    Master the powerful Action Palette feature
  </Card>
</CardGroup>