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

# Setting

> Guide to Setting AI

<img className="rounded-2xl" src="https://mintcdn.com/blinko/AgHVAkfwbrWVbQ0E/images/2025-09-19-16-04-45.png?fit=max&auto=format&n=AgHVAkfwbrWVbQ0E&q=85&s=26332fe8c619e2f1b75a3f033813ef27" width="1594" height="1089" data-path="images/2025-09-19-16-04-45.png" />

## Basic Settings

<AccordionGroup>
  <Accordion icon="toggle-on" title="1. Enable AI" defaultOpen>
    * Locate the "**Use AI**" toggle in settings
    * Switch it to the enabled state (purple)
  </Accordion>

  <Accordion icon="server" title="2. Select Model Provider">
    Supported model providers:

    * **OpenAI**: Official models and API
    * **AzureOpenAI**: Microsoft Azure platform
    * **Anthropic**: Claude series models
    * **DeepSeek**: DeepSeek series models
    * **Gemini**: Google Gemini models
    * **Grok**: xAI Grok models
    * **Ollama**: Local deployment models
    * **OpenRouter**: Multi-model aggregation platform
  </Accordion>

  <Accordion icon="robot" title="3. Select AI Model">
    * Choose corresponding AI model based on provider
    * Recommended models:
      * OpenAI: gpt-4o, gpt-4o-mini
      * Anthropic: claude-3-5-sonnet
      * DeepSeek: deepseek-chat
  </Accordion>

  <Accordion icon="key" title="4. Configure API Key">
    * Enter API key in the "**API Key**" input field
    * Ensure key is valid and has necessary permissions
    * Different providers require different key formats
  </Accordion>

  <Accordion icon="link" title="5. Set API Endpoint (Optional)">
    * Custom API endpoint address
    * Used for proxy or self-deployed services
    * Leave empty to use default endpoint
  </Accordion>
</AccordionGroup>

## Embedding Settings

<img className="rounded-2xl" src="https://mintcdn.com/blinko/AgHVAkfwbrWVbQ0E/images/2025-09-19-16-05-21.png?fit=max&auto=format&n=AgHVAkfwbrWVbQ0E&q=85&s=a3b6dcc71f01c4472384ca0a317af07a" width="1603" height="1008" data-path="images/2025-09-19-16-05-21.png" />

<AccordionGroup>
  <Accordion icon="network-wired" title="Embedding Model" defaultOpen>
    * Select model for generating text embeddings
    * Support independent embedding API key and endpoint
    * Recommended models:
      * OpenAI: text-embedding-3-small, text-embedding-3-large
      * Voyage: voyage-3-lite, voyage-large-2
  </Accordion>

  <Accordion icon="arrows-rotate" title="Rebuild Embedding Index">
    * **Rebuild**: Incremental update of embedding index
    * **Force Rebuild**: Complete regeneration of all embeddings
    * Index rebuild required after changing embedding model
  </Accordion>

  <Accordion icon="microchip" title="Embedding Dimensions">
    * Set the dimension size of embedding vectors
    * Auto-detect dimensions for common models
    * Manual setting required for custom models
  </Accordion>
</AccordionGroup>

## Search Optimization Settings

**\[Search Settings Screenshot Needed]**

<AccordionGroup>
  <Accordion icon="list-ol" title="Embedding Top K">
    * Number of most relevant chunks returned by embedding search
    * Range: 1-20 (recommended: 3-5)
    * Higher values include more context
  </Accordion>

  <Accordion icon="chart-line" title="Embedding Score">
    * Minimum similarity score threshold for embedding search
    * Range: 0.0-1.0 (recommended: 0.4-0.7)
    * Higher values ensure more relevant matches
  </Accordion>

  <Accordion icon="robot" title="Rerank Model">
    * Use large language model for result reranking
    * Improve relevance and accuracy of search results
    * **Note**: Currently requires large language models, AI SDK framework doesn't support dedicated rerank models yet
  </Accordion>

  <Accordion icon="list-check" title="Rerank Settings">
    * **Rerank Top K**: Number of results processed by reranking
    * **Rerank Score**: Minimum score threshold after reranking
    * **Use Embedding Endpoint**: Whether to use independent embedding API endpoint
  </Accordion>
</AccordionGroup>

## Proxy Settings

<AccordionGroup>
  <Accordion icon="network-wired" title="HTTP Proxy">
    * Enable HTTP proxy to access AI services
    * Configure proxy host, port and authentication
    * Suitable for network-restricted environments
  </Accordion>
</AccordionGroup>

## Test Connection

<AccordionGroup>
  <Accordion icon="flask" title="Connection Test">
    * Click "Test Connection" to verify configuration
    * Check validity of API key and endpoint
    * Ensure network connection is working
  </Accordion>
</AccordionGroup>

<Warning>
  **Important Notes**:

  * Rerank model currently requires large language models (like GPT-4)
  * Future versions will support dedicated rerank models
  * Must rebuild index after changing embedding model
</Warning>