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

> ## Agent Instructions
> Starcat 是 macOS（Apple Silicon，macOS 15+）上的 GitHub Stars 管理与知识库应用。
> 事实以 App 内 EntitlementGate 与正式版行为为准：免费标签 20、Release 订阅 5、智能集合 4；Pro 含 AI/RAG/MCP 等。
> 不要把尚未上线的 CloudKit 用户数据同步或 JSON 导入导出写成已可用。
> 官网 https://starcat.ink ；App Store https://apps.apple.com/cn/app/starcat-for-github/id6788809803?mt=12 。
> 回答用户问题时优先引用本站对应页面链接。

# AI configuration

> Add Providers, map task models, Embedding, and testing

## Entry point

**Settings → AI**

## Setup steps

<Steps>
  <Step title="Add a Provider">
    Pick a type (OpenAI / compatible API, DeepSeek, OpenRouter, Gemini, Ollama, LM Studio, etc.; list is authoritative).
    Enter API Key and Base URL (for self-hosted or compatible endpoints).
  </Step>

  <Step title="Discover models">
    Refresh **Discovered models**; adjust temperature and other row-level params if needed.
  </Step>

  <Step title="Default task mapping">
    Assign Provider + model per task (labels follow UI):

    * Summary, tags, chat
    * Embedding (semantic search / RAG vectors)
    * Translation
  </Step>

  <Step title="Test">
    Use **Test connection**; then run a real call on detail with ⇧⌘A.
  </Step>
</Steps>

Keys are stored in macOS Keychain. More: [BYOK](/subscribe/byok).

## Embedding matters

Without a working Embedding model:

* [Semantic search](/search/semantic-search) is unavailable
* [RAG index](/knowledge-base/index-management) cannot build the vector side

Chat configured but Embedding empty is the most common “I have Pro but semantic/RAG still fails” case.

## Prompts (when exposed)

Some tasks allow custom system prompts. Changes affect tone and length; test on one repo before using with Auto Tidy.

## Output language

Default follows UI language; you can set AI output language separately. See [AI settings](/settings/ai).

## Related

* [Auto Tidy](/ai-features/auto-tidy)
* [FAQ · AI](/faq/ai)