> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/b1ink0/vassist/llms.txt
> Use this file to discover all available pages before exploring further.

# AI Provider Configuration

> Configure Chrome AI, OpenAI, or Ollama for VAssist's language model

VAssist supports three AI providers for natural language processing. Choose the provider that best fits your needs.

## Provider Overview

<CardGroup cols={3}>
  <Card title="Chrome AI" icon="chrome">
    **Free, local, and private**

    Uses Google's Gemini Nano running entirely on your device. No API keys required.
  </Card>

  <Card title="OpenAI" icon="openai">
    **Powerful cloud models**

    Access GPT-4, GPT-4 Turbo, and other OpenAI models via API.
  </Card>

  <Card title="Ollama" icon="server">
    **Self-hosted flexibility**

    Run local LLMs (Llama 2, Mistral, etc.) on your own machine.
  </Card>
</CardGroup>

## Chrome AI (Default)

### Requirements

<Warning>
  **Chrome 138+** required with specific feature flags enabled.
</Warning>

Chrome AI uses Google's on-device Gemini Nano model. Configuration is done via `chrome://flags`:

### Required Flags

<Steps>
  <Step title="Enable Optimization Guide">
    Navigate to:

    ```
    chrome://flags/#optimization-guide-on-device-model
    ```

    Set to: **"Enabled BypassPerfRequirement"**

    This enables the on-device AI model to run without hardware restrictions.
  </Step>

  <Step title="Enable Prompt API">
    Navigate to:

    ```
    chrome://flags/#prompt-api-for-gemini-nano
    ```

    Set to: **"Enabled"**

    Activates the Language Model API for text generation.
  </Step>

  <Step title="Enable Multimodal Input">
    Navigate to:

    ```
    chrome://flags/#multimodal-input
    ```

    Set to: **"Enabled"**

    Required for audio/image support in Chrome AI.
  </Step>

  <Step title="Restart Chrome">
    After enabling all flags, **restart Chrome** for changes to take effect.
  </Step>
</Steps>

### Configuration

<ParamField path="provider" type="string" default="chrome-ai">
  Set provider to `chrome-ai` in AI Config settings.
</ParamField>

<ParamField path="chromeAi.temperature" type="number" default="1.0">
  Controls response randomness and creativity.

  * **Range**: 0.0 - 2.0
  * **Low (0.0-0.7)**: More focused and deterministic
  * **Medium (0.8-1.2)**: Balanced creativity
  * **High (1.3-2.0)**: More random and creative
</ParamField>

<ParamField path="chromeAi.topK" type="number" default="3">
  Number of top token candidates considered for each generation step.

  * **Range**: 1 - 128
  * **Lower**: More focused responses
  * **Higher**: More diverse vocabulary
</ParamField>

<ParamField path="chromeAi.outputLanguage" type="string" default="en">
  Preferred output language for responses.

  **Supported languages**:

  * `en` - English
  * `es` - Spanish
  * `ja` - Japanese
</ParamField>

<ParamField path="chromeAi.enableImageSupport" type="boolean" default="true">
  Enable multimodal image analysis capabilities.

  Requires the **Multimodal Input** flag enabled.
</ParamField>

<ParamField path="chromeAi.enableAudioSupport" type="boolean" default="true">
  Enable multimodal audio transcription.

  Requires the **Multimodal Input** flag enabled.
</ParamField>

### System Prompts

Customize the assistant's personality and behavior:

<Accordion title="Available Personalities">
  <ParamField path="chromeAi.systemPromptType" type="string" default="default">
    Select a pre-configured personality:

    * **`default`**: Helpful and concise assistant
    * **`professional`**: Formal, well-structured responses
    * **`friendly`**: Warm and conversational
    * **`technical`**: Expert technical guidance
    * **`creative`**: Imaginative and expressive
    * **`concise`**: Brief, to-the-point answers
    * **`teacher`**: Educational explanations
    * **`custom`**: Use your own custom prompt
  </ParamField>
</Accordion>

<ParamField path="chromeAi.systemPrompt" type="string" default="">
  Custom system prompt (only used when `systemPromptType` is `custom`).

  Example:

  ```
  You are a helpful coding assistant specializing in JavaScript and React.
  Provide clear, concise code examples and explanations.
  ```
</ParamField>

## OpenAI

### API Key Setup

<Steps>
  <Step title="Get API Key">
    1. Sign up at [platform.openai.com](https://platform.openai.com)
    2. Navigate to **API Keys** section
    3. Click **"Create new secret key"**
    4. Copy the key (starts with `sk-`)
  </Step>

  <Step title="Configure VAssist">
    1. Open **AI Config** settings
    2. Select **OpenAI** as provider
    3. Paste your API key
    4. Choose a model
  </Step>
</Steps>

### Configuration

<ParamField path="provider" type="string">
  Set to `openai` to use OpenAI models.
</ParamField>

<ParamField path="openai.apiKey" type="string" required>
  Your OpenAI API key.

  <Warning>
    Never share or commit your API key. It's stored locally in browser storage.
  </Warning>
</ParamField>

<ParamField path="openai.model" type="string" default="gpt-4-turbo-preview">
  OpenAI model to use for chat completions.

  **Recommended models**:

  * `gpt-4-turbo-preview` - Latest GPT-4 Turbo (best quality)
  * `gpt-4` - Standard GPT-4
  * `gpt-3.5-turbo` - Faster, more economical
  * `gpt-3.5-turbo-16k` - Extended context window
</ParamField>

<ParamField path="openai.temperature" type="number" default="0.7">
  Response creativity (0.0 - 2.0).

  * **0.0-0.3**: Focused, deterministic
  * **0.4-0.7**: Balanced (recommended)
  * **0.8-1.0**: Creative
  * **1.1-2.0**: Very creative/random
</ParamField>

<ParamField path="openai.maxTokens" type="number" default="2000">
  Maximum tokens in the response.

  * Higher values allow longer responses
  * Affects API costs
  * Typical range: 500-4000
</ParamField>

<ParamField path="openai.enableImageSupport" type="boolean" default="true">
  Enable GPT-4 Vision for image analysis.

  Requires `gpt-4-vision-preview` or similar vision-capable model.
</ParamField>

<ParamField path="openai.enableAudioSupport" type="boolean" default="true">
  Enable audio transcription via Whisper API.
</ParamField>

### System Prompts

<ParamField path="openai.systemPromptType" type="string" default="default">
  Choose from the same personality options as Chrome AI (default, professional, friendly, etc.).
</ParamField>

<ParamField path="openai.systemPrompt" type="string" default="">
  Custom system prompt when `systemPromptType` is `custom`.
</ParamField>

## Ollama (Local)

### Setup

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

    **Supported platforms**: macOS, Linux, Windows
  </Step>

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

    ```bash theme={null}
    # Llama 2 (7B)
    ollama pull llama2

    # Mistral (7B)
    ollama pull mistral

    # CodeLlama (7B)
    ollama pull codellama
    ```
  </Step>

  <Step title="Start Ollama Server">
    Ollama runs automatically after installation. Verify it's running:

    ```bash theme={null}
    curl http://localhost:11434/api/tags
    ```
  </Step>

  <Step title="Configure VAssist">
    1. Open **AI Config**
    2. Select **Ollama** as provider
    3. Set endpoint to `http://localhost:11434`
    4. Enter the model name (e.g., `llama2`)
  </Step>
</Steps>

### Configuration

<ParamField path="provider" type="string">
  Set to `ollama` for local Ollama models.
</ParamField>

<ParamField path="ollama.endpoint" type="string" default="http://localhost:11434">
  Ollama API endpoint.

  * **Default**: `http://localhost:11434`
  * **Custom**: If running on different port/host
</ParamField>

<ParamField path="ollama.model" type="string" default="llama2" required>
  Model name to use.

  **Popular models**:

  * `llama2` - Meta's Llama 2
  * `mistral` - Mistral 7B
  * `codellama` - Code-specialized Llama
  * `mixtral` - Mixtral 8x7B (larger, more capable)
  * `phi` - Microsoft Phi-2

  Run `ollama list` to see installed models.
</ParamField>

<ParamField path="ollama.temperature" type="number" default="0.7">
  Response creativity (0.0 - 2.0).
</ParamField>

<ParamField path="ollama.maxTokens" type="number" default="2000">
  Maximum tokens in response.
</ParamField>

<ParamField path="ollama.enableImageSupport" type="boolean" default="true">
  Enable image analysis (requires vision-capable model like `llava`).
</ParamField>

<ParamField path="ollama.enableAudioSupport" type="boolean" default="true">
  Enable audio transcription (experimental).
</ParamField>

### System Prompts

<ParamField path="ollama.systemPromptType" type="string" default="default">
  Personality selection (same options as Chrome AI and OpenAI).
</ParamField>

<ParamField path="ollama.systemPrompt" type="string" default="">
  Custom system prompt for `custom` personality type.
</ParamField>

## Provider Comparison

| Feature               | Chrome AI        | OpenAI                     | Ollama                    |
| --------------------- | ---------------- | -------------------------- | ------------------------- |
| **Cost**              | Free             | Pay per token              | Free (self-hosted)        |
| **Privacy**           | Local, private   | Cloud, data sent to OpenAI | Local, private            |
| **Setup**             | Chrome flags     | API key                    | Install + download models |
| **Performance**       | Fast, on-device  | Fast, cloud-powered        | Depends on hardware       |
| **Models**            | Gemini Nano      | GPT-4, GPT-3.5             | Llama 2, Mistral, etc.    |
| **Image Support**     | Yes (multimodal) | Yes (GPT-4 Vision)         | Yes (with llava)          |
| **Audio Support**     | Yes (multimodal) | Yes (Whisper)              | Limited                   |
| **Internet Required** | No               | Yes                        | No                        |

## Troubleshooting

<AccordionGroup>
  <Accordion title="Chrome AI not available">
    **Check**:

    1. Chrome version 138 or higher
    2. All three flags enabled in `chrome://flags`
    3. Chrome restarted after enabling flags
    4. Model downloaded (check `chrome://components`)

    **Model download**: Chrome downloads Gemini Nano automatically. This may take 10-30 minutes.
  </Accordion>

  <Accordion title="OpenAI API errors">
    **Common issues**:

    * **Invalid API key**: Double-check key in settings
    * **Rate limit**: Reduce request frequency or upgrade plan
    * **Model not found**: Verify model name spelling
    * **Insufficient quota**: Add credits to OpenAI account
  </Accordion>

  <Accordion title="Ollama connection failed">
    **Verify**:

    1. Ollama is running: `ollama list`
    2. Endpoint is correct: `http://localhost:11434`
    3. Model exists: `ollama list` shows your model
    4. No firewall blocking port 11434

    **Restart Ollama**:

    ```bash theme={null}
    # macOS/Linux
    ollama serve
    ```
  </Accordion>
</AccordionGroup>