Merge branch 'master' into feat/topk_splitter

2026-06-02 03:55:55 +00:00 · 2025-07-23 16:37:27 +08:00
parent e986a0acaf 6754666845
commit d651d956d6
116 changed files with 2556 additions and 1333 deletions
--- a/.github/pull_request_template.md
+++ b/.github/pull_request_template.md
@@ -9,7 +9,7 @@

 *请在方括号间写`x`以打勾 / Please tick the box with `x`*

- [ ] 阅读仓库[贡献指引](https://github.com/RockChinQ/LangBot/blob/master/CONTRIBUTING.md)了吗？ / Have you read the [contribution guide](https://github.com/RockChinQ/LangBot/blob/master/CONTRIBUTING.md)?
+- [ ] 阅读仓库[贡献指引](https://github.com/langbot-app/LangBot/blob/master/CONTRIBUTING.md)了吗？ / Have you read the [contribution guide](https://github.com/langbot-app/LangBot/blob/master/CONTRIBUTING.md)?
 - [ ] 与项目所有者沟通过了吗？ / Have you communicated with the project maintainer?
 - [ ] 我确定已自行测试所作的更改，确保功能符合预期。 / I have tested the changes and ensured they work as expected.

--- a/README.md
+++ b/README.md
@@ -1,50 +1,38 @@

 <p align="center">
 <a href="https://langbot.app">
-<img src="https://docs.langbot.app/social.png" alt="LangBot"/>
+<img src="https://docs.langbot.app/social_zh.png" alt="LangBot"/>
 </a>

 <div align="center">

-<a href="https://trendshift.io/repositories/12901" target="_blank"><img src="https://trendshift.io/api/badge/repositories/12901" alt="RockChinQ%2FLangBot | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
+简体中文 / [English](README_EN.md) / [日本語](README_JP.md) / (PR for your language)
+
+[![Discord](https://img.shields.io/discord/1335141740050649118?logo=discord&labelColor=%20%235462eb&logoColor=%20%23f5f5f5&color=%20%235462eb)](https://discord.gg/wdNEHETs87)
+[![QQ Group](https://img.shields.io/badge/%E7%A4%BE%E5%8C%BAQQ%E7%BE%A4-966235608-blue)](https://qm.qq.com/q/JLi38whHum)
+[![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/langbot-app/LangBot)
+[![GitHub release (latest by date)](https://img.shields.io/github/v/release/langbot-app/LangBot)](https://github.com/langbot-app/LangBot/releases/latest)
+<img src="https://img.shields.io/badge/python-3.10 ~ 3.13 -blue.svg" alt="python">
+[![star](https://gitcode.com/RockChinQ/LangBot/star/badge.svg)](https://gitcode.com/RockChinQ/LangBot)

 <a href="https://langbot.app">项目主页</a> ｜
 <a href="https://docs.langbot.app/zh/insight/guide.html">部署文档</a> ｜
 <a href="https://docs.langbot.app/zh/plugin/plugin-intro.html">插件介绍</a> ｜
-<a href="https://github.com/RockChinQ/LangBot/issues/new?assignees=&labels=%E7%8B%AC%E7%AB%8B%E6%8F%92%E4%BB%B6&projects=&template=submit-plugin.yml&title=%5BPlugin%5D%3A+%E8%AF%B7%E6%B1%82%E7%99%BB%E8%AE%B0%E6%96%B0%E6%8F%92%E4%BB%B6">提交插件</a>
+<a href="https://github.com/langbot-app/LangBot/issues/new?assignees=&labels=%E7%8B%AC%E7%AB%8B%E6%8F%92%E4%BB%B6&projects=&template=submit-plugin.yml&title=%5BPlugin%5D%3A+%E8%AF%B7%E6%B1%82%E7%99%BB%E8%AE%B0%E6%96%B0%E6%8F%92%E4%BB%B6">提交插件</a>

-<div align="center">
-😎高稳定、🧩支持扩展、🦄多模态 - 大模型原生即时通信机器人平台🤖  
-</div>
-
-<br/>
-
-[![Discord](https://img.shields.io/discord/1335141740050649118?logo=discord&labelColor=%20%235462eb&logoColor=%20%23f5f5f5&color=%20%235462eb)](https://discord.gg/wdNEHETs87)
-[![QQ Group](https://img.shields.io/badge/%E7%A4%BE%E5%8C%BAQQ%E7%BE%A4-966235608-blue)](https://qm.qq.com/q/JLi38whHum)
-[![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/RockChinQ/LangBot)
-[![GitHub release (latest by date)](https://img.shields.io/github/v/release/RockChinQ/LangBot)](https://github.com/RockChinQ/LangBot/releases/latest)
-<img src="https://img.shields.io/badge/python-3.10 ~ 3.13 -blue.svg" alt="python">
-[![star](https://gitcode.com/RockChinQ/LangBot/star/badge.svg)](https://gitcode.com/RockChinQ/LangBot)
-
-简体中文 / [English](README_EN.md) / [日本語](README_JP.md) / (PR for your language)

 </div>

 </p>

-## ✨ 特性
-
- 💬 大模型对话、Agent：支持多种大模型，适配群聊和私聊；具有多轮对话、工具调用、多模态能力，并深度适配 [Dify](https://dify.ai)。目前支持 QQ、QQ频道、企业微信、个人微信、飞书、Discord、Telegram 等平台。
- 🛠️ 高稳定性、功能完备：原生支持访问控制、限速、敏感词过滤等机制；配置简单，支持多种部署方式。支持多流水线配置，不同机器人用于不同应用场景。
- 🧩 插件扩展、活跃社区：支持事件驱动、组件扩展等插件机制；适配 Anthropic [MCP 协议](https://modelcontextprotocol.io/)；目前已有数百个插件。
- 😻 Web 管理面板：支持通过浏览器管理 LangBot 实例，不再需要手动编写配置文件。
+LangBot 是一个开源的大语言模型原生即时通信机器人开发平台，旨在提供开箱即用的 IM 机器人开发体验，具有 Agent、RAG、MCP 等多种 LLM 应用功能，适配全球主流即时通信平台，并提供丰富的 API 接口，支持自定义开发。

 ## 📦 开始使用

 #### Docker Compose 部署

 ```bash
-git clone https://github.com/RockChinQ/LangBot
+git clone https://github.com/langbot-app/LangBot
 cd LangBot
 docker compose up -d
 ```
@@ -71,23 +59,25 @@ docker compose up -d

 直接使用发行版运行，查看文档[手动部署](https://docs.langbot.app/zh/deploy/langbot/manual.html)。

-## 📸 效果展示
+## 😎 保持更新

-<img alt="bots" src="https://docs.langbot.app/webui/bot-page.png" width="450px"/>
+点击仓库右上角 Star 和 Watch 按钮，获取最新动态。

-<img alt="bots" src="https://docs.langbot.app/webui/create-model.png" width="450px"/>
+![star gif](https://docs.langbot.app/star.gif)

-<img alt="bots" src="https://docs.langbot.app/webui/edit-pipeline.png" width="450px"/>
+## ✨ 特性

-<img alt="bots" src="https://docs.langbot.app/webui/plugin-market.png" width="450px"/>
+- 💬 大模型对话、Agent：支持多种大模型，适配群聊和私聊；具有多轮对话、工具调用、多模态能力，自带 RAG（知识库）实现，并深度适配 [Dify](https://dify.ai)。
+- 🤖 多平台支持：目前支持 QQ、QQ频道、企业微信、个人微信、飞书、Discord、Telegram 等平台。
+- 🛠️ 高稳定性、功能完备：原生支持访问控制、限速、敏感词过滤等机制；配置简单，支持多种部署方式。支持多流水线配置，不同机器人用于不同应用场景。
+- 🧩 插件扩展、活跃社区：支持事件驱动、组件扩展等插件机制；适配 Anthropic [MCP 协议](https://modelcontextprotocol.io/)；目前已有数百个插件。
+- 😻 Web 管理面板：支持通过浏览器管理 LangBot 实例，不再需要手动编写配置文件。

-<img alt="回复效果（带有联网插件）" src="https://docs.langbot.app/QChatGPT-0516.png" width="500px"/>
+详细规格特性请访问[文档](https://docs.langbot.app/zh/insight/features.html)。

- WebUI Demo: https://demo.langbot.dev/
-    - 登录信息：邮箱：`demo@langbot.app` 密码：`langbot123456`
-    - 注意：仅展示webui效果，公开环境，请不要在其中填入您的任何敏感信息。
-
-## 🔌 组件兼容性
+或访问 demo 环境：https://demo.langbot.dev/  
+  - 登录信息：邮箱：`demo@langbot.app` 密码：`langbot123456`
+  - 注意：仅展示 WebUI 效果，公开环境，请不要在其中填入您的任何敏感信息。

 ### 消息平台

@@ -104,10 +94,6 @@ docker compose up -d
 | Discord | ✅ |  |
 | Telegram | ✅ |  |
 | Slack | ✅ |  |
-| LINE | 🚧 |  |
-| WhatsApp | 🚧 |  |
-
-🚧: 正在开发中

 ### 大模型能力

@@ -149,14 +135,8 @@ docker compose up -d

 ## 😘 社区贡献

-感谢以下[代码贡献者](https://github.com/RockChinQ/LangBot/graphs/contributors)和社区里其他成员对 LangBot 的贡献：
+感谢以下[代码贡献者](https://github.com/langbot-app/LangBot/graphs/contributors)和社区里其他成员对 LangBot 的贡献：

-<a href="https://github.com/RockChinQ/LangBot/graphs/contributors">
-  <img src="https://contrib.rocks/image?repo=RockChinQ/LangBot" />
+<a href="https://github.com/langbot-app/LangBot/graphs/contributors">
+  <img src="https://contrib.rocks/image?repo=langbot-app/LangBot" />
 </a>
-
-## 😎 保持更新
-
-点击仓库右上角 Star 和 Watch 按钮，获取最新动态。
-
-![star gif](https://docs.langbot.app/star.gif)
--- a/README_EN.md
+++ b/README_EN.md
@@ -1,48 +1,34 @@
 <p align="center">
 <a href="https://langbot.app">
-<img src="https://docs.langbot.app/social.png" alt="LangBot"/>
+<img src="https://docs.langbot.app/social_en.png" alt="LangBot"/>
 </a>

 <div align="center">

-<a href="https://trendshift.io/repositories/12901" target="_blank"><img src="https://trendshift.io/api/badge/repositories/12901" alt="RockChinQ%2FLangBot | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
+[简体中文](README.md) / English / [日本語](README_JP.md) / (PR for your language)
+
+[![Discord](https://img.shields.io/discord/1335141740050649118?logo=discord&labelColor=%20%235462eb&logoColor=%20%23f5f5f5&color=%20%235462eb)](https://discord.gg/wdNEHETs87)
+[![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/langbot-app/LangBot)
+[![GitHub release (latest by date)](https://img.shields.io/github/v/release/langbot-app/LangBot)](https://github.com/langbot-app/LangBot/releases/latest)
+<img src="https://img.shields.io/badge/python-3.10 ~ 3.13 -blue.svg" alt="python">

 <a href="https://langbot.app">Home</a> ｜
 <a href="https://docs.langbot.app/en/insight/guide.html">Deployment</a> ｜
 <a href="https://docs.langbot.app/en/plugin/plugin-intro.html">Plugin</a> ｜
-<a href="https://github.com/RockChinQ/LangBot/issues/new?assignees=&labels=%E7%8B%AC%E7%AB%8B%E6%8F%92%E4%BB%B6&projects=&template=submit-plugin.yml&title=%5BPlugin%5D%3A+%E8%AF%B7%E6%B1%82%E7%99%BB%E8%AE%B0%E6%96%B0%E6%8F%92%E4%BB%B6">Submit Plugin</a>
-
-<div align="center">
-😎High Stability, 🧩Extension Supported, 🦄Multi-modal - LLM Native Instant Messaging Bot Platform🤖  
-</div>
-
-<br/>
-
-
-[![Discord](https://img.shields.io/discord/1335141740050649118?logo=discord&labelColor=%20%235462eb&logoColor=%20%23f5f5f5&color=%20%235462eb)](https://discord.gg/wdNEHETs87)
-[![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/RockChinQ/LangBot)
-[![GitHub release (latest by date)](https://img.shields.io/github/v/release/RockChinQ/LangBot)](https://github.com/RockChinQ/LangBot/releases/latest)
-<img src="https://img.shields.io/badge/python-3.10 ~ 3.13 -blue.svg" alt="python">
-
-[简体中文](README.md) / English / [日本語](README_JP.md) / (PR for your language)
+<a href="https://github.com/langbot-app/LangBot/issues/new?assignees=&labels=%E7%8B%AC%E7%AB%8B%E6%8F%92%E4%BB%B6&projects=&template=submit-plugin.yml&title=%5BPlugin%5D%3A+%E8%AF%B7%E6%B1%82%E7%99%BB%E8%AE%B0%E6%96%B0%E6%8F%92%E4%BB%B6">Submit Plugin</a>

 </div>

 </p>

-## ✨ Features
-
- 💬 Chat with LLM / Agent: Supports multiple LLMs, adapt to group chats and private chats; Supports multi-round conversations, tool calls, and multi-modal capabilities. Deeply integrates with [Dify](https://dify.ai). Currently supports QQ, QQ Channel, WeCom, personal WeChat, Lark, DingTalk, Discord, Telegram, etc.
- 🛠️ High Stability, Feature-rich: Native access control, rate limiting, sensitive word filtering, etc. mechanisms; Easy to use, supports multiple deployment methods. Supports multiple pipeline configurations, different bots can be used for different scenarios.
- 🧩 Plugin Extension, Active Community: Support event-driven, component extension, etc. plugin mechanisms; Integrate Anthropic [MCP protocol](https://modelcontextprotocol.io/); Currently has hundreds of plugins.
- 😻 [New] Web UI: Support management LangBot instance through the browser. No need to manually write configuration files.
+LangBot is an open-source LLM native instant messaging robot development platform, aiming to provide out-of-the-box IM robot development experience, with Agent, RAG, MCP and other LLM application functions, adapting to global instant messaging platforms, and providing rich API interfaces, supporting custom development.

 ## 📦 Getting Started

 #### Docker Compose Deployment

 ```bash
-git clone https://github.com/RockChinQ/LangBot
+git clone https://github.com/langbot-app/LangBot
 cd LangBot
 docker compose up -d
 ```
@@ -69,23 +55,25 @@ Community contributed Zeabur template.

 Directly use the released version to run, see the [Manual Deployment](https://docs.langbot.app/en/deploy/langbot/manual.html) documentation.

-## 📸 Demo
+## 😎 Stay Ahead

-<img alt="bots" src="https://docs.langbot.app/webui/bot-page.png" width="400px"/>
+Click the Star and Watch button in the upper right corner of the repository to get the latest updates.

-<img alt="bots" src="https://docs.langbot.app/webui/create-model.png" width="400px"/>
+![star gif](https://docs.langbot.app/star.gif)

-<img alt="bots" src="https://docs.langbot.app/webui/edit-pipeline.png" width="400px"/>
+## ✨ Features

-<img alt="bots" src="https://docs.langbot.app/webui/plugin-market.png" width="400px"/>
+- 💬 Chat with LLM / Agent: Supports multiple LLMs, adapt to group chats and private chats; Supports multi-round conversations, tool calls, and multi-modal capabilities. Built-in RAG (knowledge base) implementation, and deeply integrates with [Dify](https://dify.ai).
+- 🤖 Multi-platform Support: Currently supports QQ, QQ Channel, WeCom, personal WeChat, Lark, DingTalk, Discord, Telegram, etc.
+- 🛠️ High Stability, Feature-rich: Native access control, rate limiting, sensitive word filtering, etc. mechanisms; Easy to use, supports multiple deployment methods. Supports multiple pipeline configurations, different bots can be used for different scenarios.
+- 🧩 Plugin Extension, Active Community: Support event-driven, component extension, etc. plugin mechanisms; Integrate Anthropic [MCP protocol](https://modelcontextprotocol.io/); Currently has hundreds of plugins.
+- 😻 Web UI: Support management LangBot instance through the browser. No need to manually write configuration files.

-<img alt="Reply Effect (with Internet Plugin)" src="https://docs.langbot.app/QChatGPT-0516.png" width="500px"/>
+For more detailed specifications, please refer to the [documentation](https://docs.langbot.app/en/insight/features.html).

- WebUI Demo: https://demo.langbot.dev/
-    - Login information: Email: `demo@langbot.app` Password: `langbot123456`
-    - Note: Only the WebUI effect is shown, please do not fill in any sensitive information in the public environment.
-
-## 🔌 Component Compatibility
+Or visit the demo environment: https://demo.langbot.dev/
+  - Login information: Email: `demo@langbot.app` Password: `langbot123456`
+  - Note: For WebUI demo only, please do not fill in any sensitive information in the public environment.

 ### Message Platform

@@ -101,10 +89,6 @@ Directly use the released version to run, see the [Manual Deployment](https://do
 | Discord | ✅ |  |
 | Telegram | ✅ |  |
 | Slack | ✅ |  |
-| LINE | 🚧 |  |
-| WhatsApp | 🚧 |  |
-
-🚧: In development

 ### LLMs

@@ -132,14 +116,8 @@ Directly use the released version to run, see the [Manual Deployment](https://do

 ## 🤝 Community Contribution

-Thank you for the following [code contributors](https://github.com/RockChinQ/LangBot/graphs/contributors) and other members in the community for their contributions to LangBot:
+Thank you for the following [code contributors](https://github.com/langbot-app/LangBot/graphs/contributors) and other members in the community for their contributions to LangBot:

-<a href="https://github.com/RockChinQ/LangBot/graphs/contributors">
-  <img src="https://contrib.rocks/image?repo=RockChinQ/LangBot" />
+<a href="https://github.com/langbot-app/LangBot/graphs/contributors">
+  <img src="https://contrib.rocks/image?repo=langbot-app/LangBot" />
 </a>
-
-## 😎 Stay Ahead
-
-Click the Star and Watch button in the upper right corner of the repository to get the latest updates.
-
-![star gif](https://docs.langbot.app/star.gif)
--- a/README_JP.md
+++ b/README_JP.md
@@ -1,47 +1,34 @@
 <p align="center">
 <a href="https://langbot.app">
-<img src="https://docs.langbot.app/social.png" alt="LangBot"/>
+<img src="https://docs.langbot.app/social_en.png" alt="LangBot"/>
 </a>

 <div align="center">

-<a href="https://trendshift.io/repositories/12901" target="_blank"><img src="https://trendshift.io/api/badge/repositories/12901" alt="RockChinQ%2FLangBot | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
+[简体中文](README.md) / [English](README_EN.md) / 日本語 / (PR for your language)
+
+[![Discord](https://img.shields.io/discord/1335141740050649118?logo=discord&labelColor=%20%235462eb&logoColor=%20%23f5f5f5&color=%20%235462eb)](https://discord.gg/wdNEHETs87)
+[![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/langbot-app/LangBot)
+[![GitHub release (latest by date)](https://img.shields.io/github/v/release/langbot-app/LangBot)](https://github.com/langbot-app/LangBot/releases/latest)
+<img src="https://img.shields.io/badge/python-3.10 ~ 3.13 -blue.svg" alt="python">

 <a href="https://langbot.app">ホーム</a> ｜
 <a href="https://docs.langbot.app/en/insight/guide.html">デプロイ</a> ｜
 <a href="https://docs.langbot.app/en/plugin/plugin-intro.html">プラグイン</a> ｜
-<a href="https://github.com/RockChinQ/LangBot/issues/new?assignees=&labels=%E7%8B%AC%E7%AB%8B%E6%8F%92%E4%BB%B6&projects=&template=submit-plugin.yml&title=%5BPlugin%5D%3A+%E8%AF%B7%E6%B1%82%E7%99%BB%E8%AE%B0%E6%96%B0%E6%8F%92%E4%BB%B6">プラグインの提出</a>
-
-<div align="center">
-😎高い安定性、🧩拡張サポート、🦄マルチモーダル - LLMネイティブインスタントメッセージングボットプラットフォーム🤖  
-</div>
-
-<br/>
-
-[![Discord](https://img.shields.io/discord/1335141740050649118?logo=discord&labelColor=%20%235462eb&logoColor=%20%23f5f5f5&color=%20%235462eb)](https://discord.gg/wdNEHETs87)
-[![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/RockChinQ/LangBot)
-[![GitHub release (latest by date)](https://img.shields.io/github/v/release/RockChinQ/LangBot)](https://github.com/RockChinQ/LangBot/releases/latest)
-<img src="https://img.shields.io/badge/python-3.10 ~ 3.13 -blue.svg" alt="python">
-
-[简体中文](README_CN.md) / [English](README.md) / [日本語](README_JP.md) / (PR for your language)
+<a href="https://github.com/langbot-app/LangBot/issues/new?assignees=&labels=%E7%8B%AC%E7%AB%8B%E6%8F%92%E4%BB%B6&projects=&template=submit-plugin.yml&title=%5BPlugin%5D%3A+%E8%AF%B7%E6%B1%82%E7%99%BB%E8%AE%B0%E6%96%B0%E6%8F%92%E4%BB%B6">プラグインの提出</a>

 </div>

 </p>

-## ✨ 機能
-
- 💬 LLM / エージェントとのチャット: 複数のLLMをサポートし、グループチャットとプライベートチャットに対応。マルチラウンドの会話、ツールの呼び出し、マルチモーダル機能をサポート。 [Dify](https://dify.ai) と深く統合。現在、QQ、QQ チャンネル、WeChat、個人 WeChat、Lark、DingTalk、Discord、Telegram など、複数のプラットフォームをサポートしています。
- 🛠️ 高い安定性、豊富な機能: ネイティブのアクセス制御、レート制限、敏感な単語のフィルタリングなどのメカニズムをサポート。使いやすく、複数のデプロイ方法をサポート。複数のパイプライン設定をサポートし、異なるボットを異なる用途に使用できます。
- 🧩 プラグイン拡張、活発なコミュニティ: イベント駆動、コンポーネント拡張などのプラグインメカニズムをサポート。適配 Anthropic [MCP プロトコル](https://modelcontextprotocol.io/)；豊富なエコシステム、現在数百のプラグインが存在。
- 😻 Web UI: ブラウザを通じてLangBotインスタンスを管理することをサポート。
+LangBot は、エージェント、RAG、MCP などの LLM アプリケーション機能を備えた、オープンソースの LLM ネイティブのインスタントメッセージングロボット開発プラットフォームです。世界中のインスタントメッセージングプラットフォームに適応し、豊富な API インターフェースを提供し、カスタム開発をサポートします。

 ## 📦 始め方

 #### Docker Compose デプロイ

 ```bash
-git clone https://github.com/RockChinQ/LangBot
+git clone https://github.com/langbot-app/LangBot
 cd LangBot
 docker compose up -d
 ```
@@ -50,7 +37,7 @@ http://localhost:5300 にアクセスして使用を開始します。

 詳細なドキュメントは[Dockerデプロイ](https://docs.langbot.app/en/deploy/langbot/docker.html)を参照してください。

-#### BTPanelでのワンクリックデプロイ
+#### Panelでのワンクリックデプロイ

 LangBotはBTPanelにリストされています。BTPanelをインストールしている場合は、[ドキュメント](https://docs.langbot.app/en/deploy/langbot/one-click/bt.html)を使用して使用できます。

@@ -68,23 +55,25 @@ LangBotはBTPanelにリストされています。BTPanelをインストール

 リリースバージョンを直接使用して実行します。[手動デプロイ](https://docs.langbot.app/en/deploy/langbot/manual.html)のドキュメントを参照してください。

-## 📸 デモ
+## 😎 最新情報を入手

-<img alt="bots" src="https://docs.langbot.app/webui/bot-page.png" width="400px"/>
+リポジトリの右上にある Star と Watch ボタンをクリックして、最新の更新を取得してください。

-<img alt="bots" src="https://docs.langbot.app/webui/create-model.png" width="400px"/>
+![star gif](https://docs.langbot.app/star.gif)

-<img alt="bots" src="https://docs.langbot.app/webui/edit-pipeline.png" width="400px"/>
+## ✨ 機能

-<img alt="bots" src="https://docs.langbot.app/webui/plugin-market.png" width="400px"/>
+- 💬 LLM / エージェントとのチャット: 複数のLLMをサポートし、グループチャットとプライベートチャットに対応。マルチラウンドの会話、ツールの呼び出し、マルチモーダル機能をサポート、RAG（知識ベース）を組み込み、[Dify](https://dify.ai) と深く統合。
+- 🤖 多プラットフォーム対応: 現在、QQ、QQ チャンネル、WeChat、個人 WeChat、Lark、DingTalk、Discord、Telegram など、複数のプラットフォームをサポートしています。
+- 🛠️ 高い安定性、豊富な機能: ネイティブのアクセス制御、レート制限、敏感な単語のフィルタリングなどのメカニズムをサポート。使いやすく、複数のデプロイ方法をサポート。複数のパイプライン設定をサポートし、異なるボットを異なる用途に使用できます。
+- 🧩 プラグイン拡張、活発なコミュニティ: イベント駆動、コンポーネント拡張などのプラグインメカニズムをサポート。適配 Anthropic [MCP プロトコル](https://modelcontextprotocol.io/)；豊富なエコシステム、現在数百のプラグインが存在。
+- 😻 Web UI: ブラウザを通じてLangBotインスタンスを管理することをサポート。

-<img alt="返信効果（インターネットプラグイン付き）" src="https://docs.langbot.app/QChatGPT-0516.png" width="500px"/>
+詳細な仕様については、[ドキュメント](https://docs.langbot.app/en/insight/features.html)を参照してください。

- WebUIデモ: https://demo.langbot.dev/
-    - ログイン情報: メール: `demo@langbot.app` パスワード: `langbot123456`
-    - 注意: WebUIの効果のみを示しています。公開環境では、機密情報を入力しないでください。
-
-## 🔌 コンポーネントの互換性
+または、デモ環境にアクセスしてください: https://demo.langbot.dev/
+  - ログイン情報: メール: `demo@langbot.app` パスワード: `langbot123456`
+  - 注意: WebUI のデモンストレーションのみの場合、公開環境では機密情報を入力しないでください。

 ### メッセージプラットフォーム

@@ -100,10 +89,6 @@ LangBotはBTPanelにリストされています。BTPanelをインストール
 | Discord | ✅ |  |
 | Telegram | ✅ |  |
 | Slack | ✅ |  |
-| LINE | 🚧 |  |
-| WhatsApp | 🚧 |  |
-
-🚧: 開発中

 ### LLMs

@@ -131,14 +116,8 @@ LangBotはBTPanelにリストされています。BTPanelをインストール

 ## 🤝 コミュニティ貢献

-LangBot への貢献に対して、以下の [コード貢献者](https://github.com/RockChinQ/LangBot/graphs/contributors) とコミュニティの他のメンバーに感謝します。
+LangBot への貢献に対して、以下の [コード貢献者](https://github.com/langbot-app/LangBot/graphs/contributors) とコミュニティの他のメンバーに感謝します。

-<a href="https://github.com/RockChinQ/LangBot/graphs/contributors">
-  <img src="https://contrib.rocks/image?repo=RockChinQ/LangBot" />
+<a href="https://github.com/langbot-app/LangBot/graphs/contributors">
+  <img src="https://contrib.rocks/image?repo=langbot-app/LangBot" />
 </a>
-
-## 😎 最新情報を入手
-
-リポジトリの右上にある Star と Watch ボタンをクリックして、最新の更新を取得してください。
-
-![star gif](https://docs.langbot.app/star.gif)
--- a/main.py
+++ b/main.py
@@ -11,7 +11,7 @@ asciiart = r"""
 |____\__,_|_||_\__, |___/\___/\__|
               |___/              

-⭐️ Open Source 开源地址: https://github.com/RockChinQ/LangBot
+⭐️ Open Source 开源地址: https://github.com/langbot-app/LangBot
 📖 Documentation 文档地址: https://docs.langbot.app
 """

--- a/pkg/api/http/controller/group.py
+++ b/pkg/api/http/controller/group.py
@@ -11,7 +11,7 @@ from ....core import app


 preregistered_groups: list[type[RouterGroup]] = []
-"""RouterGroup 的预注册列表"""
+"""Pre-registered list of RouterGroup"""


 def group_class(name: str, path: str) -> typing.Callable[[typing.Type[RouterGroup]], typing.Type[RouterGroup]]:
@@ -27,7 +27,7 @@ def group_class(name: str, path: str) -> typing.Callable[[typing.Type[RouterGrou


 class AuthType(enum.Enum):
-    """认证类型"""
+    """Authentication type"""

    NONE = 'none'
    USER_TOKEN = 'user-token'
@@ -56,7 +56,7 @@ class RouterGroup(abc.ABC):
        auth_type: AuthType = AuthType.USER_TOKEN,
        **options: typing.Any,
    ) -> typing.Callable[[RouteCallable], RouteCallable]:  # decorator
-        """注册一个路由"""
+        """Register a route"""

        def decorator(f: RouteCallable) -> RouteCallable:
            nonlocal rule
@@ -64,11 +64,11 @@ class RouterGroup(abc.ABC):

            async def handler_error(*args, **kwargs):
                if auth_type == AuthType.USER_TOKEN:
-                    # 从Authorization头中获取token
+                    # get token from Authorization header
                    token = quart.request.headers.get('Authorization', '').replace('Bearer ', '')

                    if not token:
-                        return self.http_status(401, -1, '未提供有效的用户令牌')
+                        return self.http_status(401, -1, 'No valid user token provided')

                    try:
                        user_email = await self.ap.user_service.verify_jwt_token(token)
@@ -76,9 +76,9 @@ class RouterGroup(abc.ABC):
                        # check if this account exists
                        user = await self.ap.user_service.get_user_by_email(user_email)
                        if not user:
-                            return self.http_status(401, -1, '用户不存在')
+                            return self.http_status(401, -1, 'User not found')

-                        # 检查f是否接受user_email参数
+                        # check if f accepts user_email parameter
                        if 'user_email' in f.__code__.co_varnames:
                            kwargs['user_email'] = user_email
                    except Exception as e:
@@ -86,10 +86,11 @@ class RouterGroup(abc.ABC):

                try:
                    return await f(*args, **kwargs)
-                except Exception:  # 自动 500
+
+                except Exception as e:  # 自动 500
                    traceback.print_exc()
                    # return self.http_status(500, -2, str(e))
-                    return self.http_status(500, -2, 'internal server error')
+                    return self.http_status(500, -2, str(e))

            new_f = handler_error
            new_f.__name__ = (self.name + rule).replace('/', '__')
@@ -101,7 +102,7 @@ class RouterGroup(abc.ABC):
        return decorator

    def success(self, data: typing.Any = None) -> quart.Response:
-        """返回一个 200 响应"""
+        """Return a 200 response"""
        return quart.jsonify(
            {
                'code': 0,
@@ -111,7 +112,7 @@ class RouterGroup(abc.ABC):
        )

    def fail(self, code: int, msg: str) -> quart.Response:
-        """返回一个异常响应"""
+        """Return an error response"""

        return quart.jsonify(
            {
@@ -122,4 +123,4 @@ class RouterGroup(abc.ABC):

    def http_status(self, status: int, code: int, msg: str) -> typing.Tuple[quart.Response, int]:
        """返回一个指定状态码的响应"""
-        return (self.fail(code, msg), status)
+        return (self.fail(code, msg), status)
--- a/pkg/api/http/controller/groups/files.py
+++ b/pkg/api/http/controller/groups/files.py
@@ -34,8 +34,9 @@ class FilesRouterGroup(group.RouterGroup):

            file_bytes = await asyncio.to_thread(file.stream.read)
            extension = file.filename.split('.')[-1]
+            file_name = file.filename.split('.')[0]

-            file_key = str(uuid.uuid4()) + '.' + extension
+            file_key = file_name + '_' + str(uuid.uuid4())[:8] + '.' + extension
            # save file to storage
            await self.ap.storage_mgr.storage_provider.save(file_key, file_bytes)
            return self.success(
--- a/pkg/api/http/controller/groups/knowledge/base.py
+++ b/pkg/api/http/controller/groups/knowledge/base.py
@@ -20,7 +20,7 @@ class KnowledgeBaseRouterGroup(group.RouterGroup):

        @self.route(
            '/<knowledge_base_uuid>',
-            methods=['GET', 'DELETE'],
+            methods=['GET', 'DELETE', 'PUT'],
        )
        async def handle_specific_knowledge_base(knowledge_base_uuid: str) -> quart.Response:
            if quart.request.method == 'GET':
@@ -34,6 +34,12 @@ class KnowledgeBaseRouterGroup(group.RouterGroup):
                        'base': knowledge_base,
                    }
                )
+
+            elif quart.request.method == 'PUT':
+                json_data = await quart.request.json
+                await self.ap.knowledge_service.update_knowledge_base(knowledge_base_uuid, json_data)
+                return self.success({})
+
            elif quart.request.method == 'DELETE':
                await self.ap.knowledge_service.delete_knowledge_base(knowledge_base_uuid)
                return self.success({})
@@ -72,3 +78,13 @@ class KnowledgeBaseRouterGroup(group.RouterGroup):
        async def delete_specific_file_in_kb(file_id: str, knowledge_base_uuid: str) -> str:
            await self.ap.knowledge_service.delete_file(knowledge_base_uuid, file_id)
            return self.success({})
+
+        @self.route(
+            '/<knowledge_base_uuid>/retrieve',
+            methods=['POST'],
+        )
+        async def retrieve_knowledge_base(knowledge_base_uuid: str) -> str:
+            json_data = await quart.request.json
+            query = json_data.get('query')
+            results = await self.ap.knowledge_service.retrieve_knowledge_base(knowledge_base_uuid, query)
+            return self.success(data={'results': results})
--- a/pkg/api/http/controller/groups/pipelines/pipelines.py
+++ b/pkg/api/http/controller/groups/pipelines/pipelines.py
@@ -11,7 +11,9 @@ class PipelinesRouterGroup(group.RouterGroup):
        @self.route('', methods=['GET', 'POST'])
        async def _() -> str:
            if quart.request.method == 'GET':
-                return self.success(data={'pipelines': await self.ap.pipeline_service.get_pipelines()})
+                sort_by = quart.request.args.get('sort_by', 'created_at')
+                sort_order = quart.request.args.get('sort_order', 'DESC')
+                return self.success(data={'pipelines': await self.ap.pipeline_service.get_pipelines(sort_by, sort_order)})
            elif quart.request.method == 'POST':
                json_data = await quart.request.json

--- a/pkg/api/http/controller/groups/pipelines/webchat.py
+++ b/pkg/api/http/controller/groups/pipelines/webchat.py
@@ -8,7 +8,7 @@ class WebChatDebugRouterGroup(group.RouterGroup):
    async def initialize(self) -> None:
        @self.route('/send', methods=['POST'])
        async def send_message(pipeline_uuid: str) -> str:
-            """发送调试消息到流水线"""
+            """Send a message to the pipeline for debugging"""
            try:
                data = await quart.request.get_json()
                session_type = data.get('session_type', 'person')
@@ -38,7 +38,7 @@ class WebChatDebugRouterGroup(group.RouterGroup):

        @self.route('/messages/<session_type>', methods=['GET'])
        async def get_messages(pipeline_uuid: str, session_type: str) -> str:
-            """获取调试消息历史"""
+            """Get the message history of the pipeline for debugging"""
            try:
                if session_type not in ['person', 'group']:
                    return self.http_status(400, -1, 'session_type must be person or group')
@@ -57,7 +57,7 @@ class WebChatDebugRouterGroup(group.RouterGroup):

        @self.route('/reset/<session_type>', methods=['POST'])
        async def reset_session(session_type: str) -> str:
-            """重置调试会话"""
+            """Reset the debug session"""
            try:
                if session_type not in ['person', 'group']:
                    return self.http_status(400, -1, 'session_type must be person or group')
--- a/pkg/api/http/controller/groups/plugins.py
+++ b/pkg/api/http/controller/groups/plugins.py
@@ -40,7 +40,7 @@ class PluginsRouterGroup(group.RouterGroup):
                self.ap.plugin_mgr.update_plugin(plugin_name, task_context=ctx),
                kind='plugin-operation',
                name=f'plugin-update-{plugin_name}',
-                label=f'更新插件 {plugin_name}',
+                label=f'Updating plugin {plugin_name}',
                context=ctx,
            )
            return self.success(data={'task_id': wrapper.id})
@@ -62,7 +62,7 @@ class PluginsRouterGroup(group.RouterGroup):
                    self.ap.plugin_mgr.uninstall_plugin(plugin_name, task_context=ctx),
                    kind='plugin-operation',
                    name=f'plugin-remove-{plugin_name}',
-                    label=f'删除插件 {plugin_name}',
+                    label=f'Removing plugin {plugin_name}',
                    context=ctx,
                )

@@ -102,7 +102,7 @@ class PluginsRouterGroup(group.RouterGroup):
                self.ap.plugin_mgr.install_plugin(data['source'], task_context=ctx),
                kind='plugin-operation',
                name='plugin-install-github',
-                label=f'安装插件 ...{short_source_str}',
+                label=f'Installing plugin ...{short_source_str}',
                context=ctx,
            )

--- a/pkg/api/http/controller/groups/user.py
+++ b/pkg/api/http/controller/groups/user.py
@@ -14,7 +14,7 @@ class UserRouterGroup(group.RouterGroup):
                return self.success(data={'initialized': await self.ap.user_service.is_initialized()})

            if await self.ap.user_service.is_initialized():
-                return self.fail(1, '系统已初始化')
+                return self.fail(1, 'System already initialized')

            json_data = await quart.request.json

@@ -32,7 +32,7 @@ class UserRouterGroup(group.RouterGroup):
            try:
                token = await self.ap.user_service.authenticate(json_data['user'], json_data['password'])
            except argon2.exceptions.VerifyMismatchError:
-                return self.fail(1, '用户名或密码错误')
+                return self.fail(1, 'Invalid username or password')

            return self.success(data={'token': token})

@@ -54,15 +54,15 @@ class UserRouterGroup(group.RouterGroup):
            await asyncio.sleep(3)

            if not await self.ap.user_service.is_initialized():
-                return self.http_status(400, -1, 'system not initialized')
+                return self.http_status(400, -1, 'System not initialized')

            user_obj = await self.ap.user_service.get_user_by_email(user_email)

            if user_obj is None:
-                return self.http_status(400, -1, 'user not found')
+                return self.http_status(400, -1, 'User not found')

            if recovery_key != self.ap.instance_config.data['system']['recovery_key']:
-                return self.http_status(403, -1, 'invalid recovery key')
+                return self.http_status(403, -1, 'Invalid recovery key')

            await self.ap.user_service.reset_password(user_email, new_password)

--- a/pkg/api/http/controller/main.py
+++ b/pkg/api/http/controller/main.py
@@ -47,7 +47,7 @@ class HTTPController:
                try:
                    await self.quart_app.run_task(*args, **kwargs)
                except Exception as e:
-                    self.ap.logger.error(f'启动 HTTP 服务失败： {e}')
+                    self.ap.logger.error(f'Failed to start HTTP service: {e}')

            self.ap.task_mgr.create_task(
                exception_handler(
--- a/pkg/api/http/service/bot.py
+++ b/pkg/api/http/service/bot.py
@@ -10,7 +10,7 @@ from ....entity.persistence import pipeline as persistence_pipeline


 class BotService:
-    """机器人服务"""
+    """Bot service"""

    ap: app.Application

@@ -18,7 +18,7 @@ class BotService:
        self.ap = ap

    async def get_bots(self) -> list[dict]:
-        """获取所有机器人"""
+        """Get all bots"""
        result = await self.ap.persistence_mgr.execute_async(sqlalchemy.select(persistence_bot.Bot))

        bots = result.all()
@@ -26,7 +26,7 @@ class BotService:
        return [self.ap.persistence_mgr.serialize_model(persistence_bot.Bot, bot) for bot in bots]

    async def get_bot(self, bot_uuid: str) -> dict | None:
-        """获取机器人"""
+        """Get bot"""
        result = await self.ap.persistence_mgr.execute_async(
            sqlalchemy.select(persistence_bot.Bot).where(persistence_bot.Bot.uuid == bot_uuid)
        )
@@ -39,7 +39,7 @@ class BotService:
        return self.ap.persistence_mgr.serialize_model(persistence_bot.Bot, bot)

    async def create_bot(self, bot_data: dict) -> str:
-        """创建机器人"""
+        """Create bot"""
        # TODO: 检查配置信息格式
        bot_data['uuid'] = str(uuid.uuid4())

@@ -63,7 +63,7 @@ class BotService:
        return bot_data['uuid']

    async def update_bot(self, bot_uuid: str, bot_data: dict) -> None:
-        """更新机器人"""
+        """Update bot"""
        if 'uuid' in bot_data:
            del bot_data['uuid']

@@ -99,7 +99,7 @@ class BotService:
                session.using_conversation = None

    async def delete_bot(self, bot_uuid: str) -> None:
-        """删除机器人"""
+        """Delete bot"""
        await self.ap.platform_mgr.remove_bot(bot_uuid)
        await self.ap.persistence_mgr.execute_async(
            sqlalchemy.delete(persistence_bot.Bot).where(persistence_bot.Bot.uuid == bot_uuid)
--- a/pkg/api/http/service/knowledge.py
+++ b/pkg/api/http/service/knowledge.py
@@ -47,12 +47,18 @@ class KnowledgeService:

    async def update_knowledge_base(self, kb_uuid: str, kb_data: dict) -> None:
        """更新知识库"""
+        if 'uuid' in kb_data:
+            del kb_data['uuid']
+
+        if 'embedding_model_uuid' in kb_data:
+            del kb_data['embedding_model_uuid']
+
        await self.ap.persistence_mgr.execute_async(
            sqlalchemy.update(persistence_rag.KnowledgeBase)
            .values(kb_data)
            .where(persistence_rag.KnowledgeBase.uuid == kb_uuid)
        )
-        await self.ap.rag_mgr.remove_knowledge_base(kb_uuid)
+        await self.ap.rag_mgr.remove_knowledge_base_from_runtime(kb_uuid)

        kb = await self.get_knowledge_base(kb_uuid)

@@ -67,6 +73,13 @@ class KnowledgeService:
            raise Exception('Knowledge base not found')
        return await runtime_kb.store_file(file_id)

+    async def retrieve_knowledge_base(self, kb_uuid: str, query: str) -> list[dict]:
+        """检索知识库"""
+        runtime_kb = await self.ap.rag_mgr.get_knowledge_base_by_uuid(kb_uuid)
+        if runtime_kb is None:
+            raise Exception('Knowledge base not found')
+        return [result.model_dump() for result in await runtime_kb.retrieve(query)]
+
    async def get_files_by_knowledge_base(self, kb_uuid: str) -> list[dict]:
        """获取知识库文件"""
        result = await self.ap.persistence_mgr.execute_async(
@@ -77,14 +90,29 @@ class KnowledgeService:

    async def delete_file(self, kb_uuid: str, file_id: str) -> None:
        """删除文件"""
-        await self.ap.persistence_mgr.execute_async(
-            sqlalchemy.delete(persistence_rag.File).where(persistence_rag.File.uuid == file_id)
-        )
-        # TODO: remove from memory
+        runtime_kb = await self.ap.rag_mgr.get_knowledge_base_by_uuid(kb_uuid)
+        if runtime_kb is None:
+            raise Exception('Knowledge base not found')
+        await runtime_kb.delete_file(file_id)

    async def delete_knowledge_base(self, kb_uuid: str) -> None:
        """删除知识库"""
+        await self.ap.rag_mgr.delete_knowledge_base(kb_uuid)
+
        await self.ap.persistence_mgr.execute_async(
            sqlalchemy.delete(persistence_rag.KnowledgeBase).where(persistence_rag.KnowledgeBase.uuid == kb_uuid)
        )
-        # TODO: remove from memory
+
+        # delete files
+        files = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.select(persistence_rag.File).where(persistence_rag.File.kb_id == kb_uuid)
+        )
+        for file in files:
+            # delete chunks
+            await self.ap.persistence_mgr.execute_async(
+                sqlalchemy.delete(persistence_rag.Chunk).where(persistence_rag.Chunk.file_id == file.uuid)
+            )
+            # delete file
+            await self.ap.persistence_mgr.execute_async(
+                sqlalchemy.delete(persistence_rag.File).where(persistence_rag.File.uuid == file.uuid)
+            )
--- a/pkg/api/http/service/model.py
+++ b/pkg/api/http/service/model.py
@@ -186,6 +186,6 @@ class EmbeddingModelsService:

        await runtime_embedding_model.requester.invoke_embedding(
            model=runtime_embedding_model,
-            input_text='Hello, world!',
+            input_text=['Hello, world!'],
            extra_args={},
        )
--- a/pkg/api/http/service/pipeline.py
+++ b/pkg/api/http/service/pipeline.py
@@ -38,9 +38,21 @@ class PipelineService:
            self.ap.pipeline_config_meta_output.data,
        ]

-    async def get_pipelines(self) -> list[dict]:
-        result = await self.ap.persistence_mgr.execute_async(sqlalchemy.select(persistence_pipeline.LegacyPipeline))
-
+    async def get_pipelines(self, sort_by: str = 'created_at', sort_order: str = 'DESC') -> list[dict]:
+        query = sqlalchemy.select(persistence_pipeline.LegacyPipeline)
+        
+        if sort_by == 'created_at':
+            if sort_order == 'DESC':
+                query = query.order_by(persistence_pipeline.LegacyPipeline.created_at.desc())
+            else:
+                query = query.order_by(persistence_pipeline.LegacyPipeline.created_at.asc())
+        elif sort_by == 'updated_at':
+            if sort_order == 'DESC':
+                query = query.order_by(persistence_pipeline.LegacyPipeline.updated_at.desc())
+            else:
+                query = query.order_by(persistence_pipeline.LegacyPipeline.updated_at.asc())
+        
+        result = await self.ap.persistence_mgr.execute_async(query)
        pipelines = result.all()
        return [
            self.ap.persistence_mgr.serialize_model(persistence_pipeline.LegacyPipeline, pipeline)
--- a/pkg/config/impls/json.py
+++ b/pkg/config/impls/json.py
@@ -6,7 +6,7 @@ from .. import model as file_model


 class JSONConfigFile(file_model.ConfigFile):
-    """JSON配置文件"""
+    """JSON config file"""

    def __init__(
        self,
@@ -42,7 +42,7 @@ class JSONConfigFile(file_model.ConfigFile):
            try:
                cfg = json.load(f)
            except json.JSONDecodeError as e:
-                raise Exception(f'配置文件 {self.config_file_name} 语法错误: {e}')
+                raise Exception(f'Syntax error in config file {self.config_file_name}: {e}')

        if completion:
            for key in self.template_data:
--- a/pkg/config/impls/pymodule.py
+++ b/pkg/config/impls/pymodule.py
@@ -7,13 +7,13 @@ from .. import model as file_model


 class PythonModuleConfigFile(file_model.ConfigFile):
-    """Python模块配置文件"""
+    """Python module config file"""

    config_file_name: str = None
-    """配置文件名"""
+    """Config file name"""

    template_file_name: str = None
-    """模板文件名"""
+    """Template file name"""

    def __init__(self, config_file_name: str, template_file_name: str) -> None:
        self.config_file_name = config_file_name
@@ -42,7 +42,7 @@ class PythonModuleConfigFile(file_model.ConfigFile):

            cfg[key] = getattr(module, key)

-        # 从模板模块文件中进行补全
+        # complete from template module file
        if completion:
            module_name = os.path.splitext(os.path.basename(self.template_file_name))[0]
            module = importlib.import_module(module_name)
@@ -60,7 +60,7 @@ class PythonModuleConfigFile(file_model.ConfigFile):
        return cfg

    async def save(self, data: dict):
-        logging.warning('Python模块配置文件不支持保存')
+        logging.warning('Python module config file does not support saving')

    def save_sync(self, data: dict):
-        logging.warning('Python模块配置文件不支持保存')
+        logging.warning('Python module config file does not support saving')
--- a/pkg/config/impls/yaml.py
+++ b/pkg/config/impls/yaml.py
@@ -6,7 +6,7 @@ from .. import model as file_model


 class YAMLConfigFile(file_model.ConfigFile):
-    """YAML配置文件"""
+    """YAML config file"""

    def __init__(
        self,
@@ -42,7 +42,7 @@ class YAMLConfigFile(file_model.ConfigFile):
            try:
                cfg = yaml.load(f, Loader=yaml.FullLoader)
            except yaml.YAMLError as e:
-                raise Exception(f'配置文件 {self.config_file_name} 语法错误: {e}')
+                raise Exception(f'Syntax error in config file {self.config_file_name}: {e}')

        if completion:
            for key in self.template_data:
--- a/pkg/config/manager.py
+++ b/pkg/config/manager.py
@@ -5,27 +5,27 @@ from .impls import pymodule, json as json_file, yaml as yaml_file


 class ConfigManager:
-    """配置文件管理器"""
+    """Config file manager"""

    name: str = None
-    """配置管理器名"""
+    """Config manager name"""

    description: str = None
-    """配置管理器描述"""
+    """Config manager description"""

    schema: dict = None
-    """配置文件 schema
-    需要符合 JSON Schema Draft 7 规范
+    """Config file schema
+    Must conform to JSON Schema Draft 7 specification
    """

    file: file_model.ConfigFile = None
-    """配置文件实例"""
+    """Config file instance"""

    data: dict = None
-    """配置数据"""
+    """Config data"""

    doc_link: str = None
-    """配置文件文档链接"""
+    """Config file documentation link"""

    def __init__(self, cfg_file: file_model.ConfigFile) -> None:
        self.file = cfg_file
@@ -42,15 +42,15 @@ class ConfigManager:


 async def load_python_module_config(config_name: str, template_name: str, completion: bool = True) -> ConfigManager:
-    """加载Python模块配置文件
+    """Load Python module config file

    Args:
-        config_name (str): 配置文件名
-        template_name (str): 模板文件名
-        completion (bool): 是否自动补全内存中的配置文件
+        config_name (str): Config file name
+        template_name (str): Template file name
+        completion (bool): Whether to automatically complete the config file in memory

    Returns:
-        ConfigManager: 配置文件管理器
+        ConfigManager: Config file manager
    """
    cfg_inst = pymodule.PythonModuleConfigFile(config_name, template_name)

@@ -66,13 +66,13 @@ async def load_json_config(
    template_data: dict = None,
    completion: bool = True,
 ) -> ConfigManager:
-    """加载JSON配置文件
+    """Load JSON config file

    Args:
-        config_name (str): 配置文件名
-        template_name (str): 模板文件名
-        template_data (dict): 模板数据
-        completion (bool): 是否自动补全内存中的配置文件
+        config_name (str): Config file name
+        template_name (str): Template file name
+        template_data (dict): Template data
+        completion (bool): Whether to automatically complete the config file in memory
    """
    cfg_inst = json_file.JSONConfigFile(config_name, template_name, template_data)

@@ -88,16 +88,16 @@ async def load_yaml_config(
    template_data: dict = None,
    completion: bool = True,
 ) -> ConfigManager:
-    """加载YAML配置文件
+    """Load YAML config file

    Args:
-        config_name (str): 配置文件名
-        template_name (str): 模板文件名
-        template_data (dict): 模板数据
-        completion (bool): 是否自动补全内存中的配置文件
+        config_name (str): Config file name
+        template_name (str): Template file name
+        template_data (dict): Template data
+        completion (bool): Whether to automatically complete the config file in memory

    Returns:
-        ConfigManager: 配置文件管理器
+        ConfigManager: Config file manager
    """
    cfg_inst = yaml_file.YAMLConfigFile(config_name, template_name, template_data)

--- a/pkg/config/model.py
+++ b/pkg/config/model.py
@@ -2,16 +2,16 @@ import abc


 class ConfigFile(metaclass=abc.ABCMeta):
-    """配置文件抽象类"""
+    """Config file abstract class"""

    config_file_name: str = None
-    """配置文件名"""
+    """Config file name"""

    template_file_name: str = None
-    """模板文件名"""
+    """Template file name"""

    template_data: dict = None
-    """模板数据"""
+    """Template data"""

    @abc.abstractmethod
    def exists(self) -> bool:
--- a/pkg/core/app.py
+++ b/pkg/core/app.py
@@ -28,11 +28,12 @@ from ..storage import mgr as storagemgr
 from ..utils import logcache
 from . import taskmgr
 from . import entities as core_entities
-from ..rag.knowledge import mgr as rag_mgr
+from ..rag.knowledge import kbmgr as rag_mgr
+from ..vector import mgr as vectordb_mgr


 class Application:
-    """运行时应用对象和上下文"""
+    """Runtime application object and context"""

    event_loop: asyncio.AbstractEventLoop = None

@@ -51,10 +52,10 @@ class Application:

    rag_mgr: rag_mgr.RAGManager = None

-    # TODO 移动到 pipeline 里
+    # TODO move to pipeline
    tool_mgr: llm_tool_mgr.ToolManager = None

-    # ======= 配置管理器 =======
+    # ======= Config manager =======

    command_cfg: config_mgr.ConfigManager = None  # deprecated

@@ -68,7 +69,7 @@ class Application:

    instance_config: config_mgr.ConfigManager = None

-    # ======= 元数据配置管理器 =======
+    # ======= Metadata config manager =======

    sensitive_meta: config_mgr.ConfigManager = None

@@ -97,6 +98,8 @@ class Application:

    persistence_mgr: persistencemgr.PersistenceManager = None

+    vector_db_mgr: vectordb_mgr.VectorDBManager = None
+
    http_ctrl: http_controller.HTTPController = None

    log_cache: logcache.LogCache = None
@@ -163,11 +166,11 @@ class Application:
        except asyncio.CancelledError:
            pass
        except Exception as e:
-            self.logger.error(f'应用运行致命异常: {e}')
+            self.logger.error(f'Application runtime fatal exception: {e}')
            self.logger.debug(f'Traceback: {traceback.format_exc()}')

    async def print_web_access_info(self):
-        """打印访问 webui 的提示"""
+        """Print access webui tips"""

        if not os.path.exists(os.path.join('.', 'web/out')):
            self.logger.warning('WebUI 文件缺失，请根据文档部署：https://docs.langbot.app/zh')
@@ -199,7 +202,7 @@ class Application:
    ):
        match scope:
            case core_entities.LifecycleControlScope.PLATFORM.value:
-                self.logger.info('执行热重载 scope=' + scope)
+                self.logger.info('Hot reload scope=' + scope)
                await self.platform_mgr.shutdown()

                self.platform_mgr = im_mgr.PlatformManager(self)
@@ -215,7 +218,7 @@ class Application:
                    ],
                )
            case core_entities.LifecycleControlScope.PLUGIN.value:
-                self.logger.info('执行热重载 scope=' + scope)
+                self.logger.info('Hot reload scope=' + scope)
                await self.plugin_mgr.destroy_plugins()

                # 删除 sys.module 中所有的 plugins/* 下的模块
@@ -231,7 +234,7 @@ class Application:
                await self.plugin_mgr.load_plugins()
                await self.plugin_mgr.initialize_plugins()
            case core_entities.LifecycleControlScope.PROVIDER.value:
-                self.logger.info('执行热重载 scope=' + scope)
+                self.logger.info('Hot reload scope=' + scope)

                await self.tool_mgr.shutdown()

--- a/pkg/core/boot.py
+++ b/pkg/core/boot.py
@@ -8,7 +8,7 @@ from . import app
 from . import stage
 from ..utils import constants, importutil

-# 引入启动阶段实现以便注册
+# Import startup stage implementation to register
 from . import stages

 importutil.import_modules_in_pkg(stages)
@@ -25,7 +25,7 @@ stage_order = [


 async def make_app(loop: asyncio.AbstractEventLoop) -> app.Application:
-    # 确定是否为调试模式
+    # Determine if it is debug mode
    if 'DEBUG' in os.environ and os.environ['DEBUG'] in ['true', '1']:
        constants.debug_mode = True

@@ -33,7 +33,7 @@ async def make_app(loop: asyncio.AbstractEventLoop) -> app.Application:

    ap.event_loop = loop

-    # 执行启动阶段
+    # Execute startup stage
    for stage_name in stage_order:
        stage_cls = stage.preregistered_stages[stage_name]
        stage_inst = stage_cls()
@@ -47,11 +47,11 @@ async def make_app(loop: asyncio.AbstractEventLoop) -> app.Application:

 async def main(loop: asyncio.AbstractEventLoop):
    try:
-        # 挂系统信号处理
+        # Hang system signal processing
        import signal

        def signal_handler(sig, frame):
-            print('[Signal] 程序退出.')
+            print('[Signal] Program exit.')
            # ap.shutdown()
            os._exit(0)

--- a/pkg/core/bootutils/deps.py
+++ b/pkg/core/bootutils/deps.py
@@ -2,8 +2,8 @@ import pip
 import os
 from ...utils import pkgmgr

-# 检查依赖，防止用户未安装
-# 左边为引入名称，右边为依赖名称
+# Check dependencies to prevent users from not installing
+# Left is the import name, right is the dependency name
 required_deps = {
    'requests': 'requests',
    'openai': 'openai',
@@ -65,7 +65,7 @@ async def install_deps(deps: list[str]):
 async def precheck_plugin_deps():
    print('[Startup] Prechecking plugin dependencies...')

-    # 只有在plugins目录存在时才执行插件依赖安装
+    # Only execute plugin dependency installation when the plugins directory exists
    if os.path.exists('plugins'):
        for dir in os.listdir('plugins'):
            subdir = os.path.join('plugins', dir)
--- a/pkg/core/bootutils/log.py
+++ b/pkg/core/bootutils/log.py
@@ -17,7 +17,7 @@ log_colors_config = {


 async def init_logging(extra_handlers: list[logging.Handler] = None) -> logging.Logger:
-    # 删除所有现有的logger
+    # Remove all existing loggers
    for handler in logging.root.handlers[:]:
        logging.root.removeHandler(handler)

@@ -54,13 +54,13 @@ async def init_logging(extra_handlers: list[logging.Handler] = None) -> logging.
        handler.setFormatter(color_formatter)
        qcg_logger.addHandler(handler)

-    qcg_logger.debug('日志初始化完成，日志级别：%s' % level)
+    qcg_logger.debug('Logging initialized, log level: %s' % level)
    logging.basicConfig(
-        level=logging.CRITICAL,  # 设置日志输出格式
+        level=logging.CRITICAL,  # Set log output format
        format='[DEPR][%(asctime)s.%(msecs)03d] %(pathname)s (%(lineno)d) - [%(levelname)s] :\n%(message)s',
-        # 日志输出的格式
-        # -8表示占位符，让输出左对齐，输出长度都为8位
-        datefmt='%Y-%m-%d %H:%M:%S',  # 时间输出的格式
+        # Log output format
+        # -8 is a placeholder, left-align the output, and output length is 8
+        datefmt='%Y-%m-%d %H:%M:%S',  # Time output format
        handlers=[logging.NullHandler()],
    )

--- a/pkg/core/migration.py
+++ b/pkg/core/migration.py
@@ -7,11 +7,11 @@ from . import app


 preregistered_migrations: list[typing.Type[Migration]] = []
-"""当前阶段暂不支持扩展"""
+"""Currently not supported for extension"""


 def migration_class(name: str, number: int):
-    """注册一个迁移"""
+    """Register a migration"""

    def decorator(cls: typing.Type[Migration]) -> typing.Type[Migration]:
        cls.name = name
@@ -23,7 +23,7 @@ def migration_class(name: str, number: int):


 class Migration(abc.ABC):
-    """一个版本的迁移"""
+    """A version migration"""

    name: str

@@ -36,10 +36,10 @@ class Migration(abc.ABC):

    @abc.abstractmethod
    async def need_migrate(self) -> bool:
-        """判断当前环境是否需要运行此迁移"""
+        """Determine if the current environment needs to run this migration"""
        pass

    @abc.abstractmethod
    async def run(self):
-        """执行迁移"""
+        """Run migration"""
        pass
--- a/pkg/core/note.py
+++ b/pkg/core/note.py
@@ -9,7 +9,7 @@ preregistered_notes: list[typing.Type[LaunchNote]] = []


 def note_class(name: str, number: int):
-    """注册一个启动信息"""
+    """Register a launch information"""

    def decorator(cls: typing.Type[LaunchNote]) -> typing.Type[LaunchNote]:
        cls.name = name
@@ -21,7 +21,7 @@ def note_class(name: str, number: int):


 class LaunchNote(abc.ABC):
-    """启动信息"""
+    """Launch information"""

    name: str

@@ -34,10 +34,10 @@ class LaunchNote(abc.ABC):

    @abc.abstractmethod
    async def need_show(self) -> bool:
-        """判断当前环境是否需要显示此启动信息"""
+        """Determine if the current environment needs to display this launch information"""
        pass

    @abc.abstractmethod
    async def yield_note(self) -> typing.AsyncGenerator[typing.Tuple[str, int], None]:
-        """生成启动信息"""
+        """Generate launch information"""
        pass
--- a/pkg/core/notes/n001_classic_msgs.py
+++ b/pkg/core/notes/n001_classic_msgs.py
@@ -7,7 +7,7 @@ from .. import note

@note.note_class('ClassicNotes', 1)
 class ClassicNotes(note.LaunchNote):
-    """经典启动信息"""
+    """Classic launch information"""

    async def need_show(self) -> bool:
        return True
--- a/pkg/core/notes/n002_selection_mode_on_windows.py
+++ b/pkg/core/notes/n002_selection_mode_on_windows.py
@@ -9,7 +9,7 @@ from .. import note

@note.note_class('SelectionModeOnWindows', 2)
 class SelectionModeOnWindows(note.LaunchNote):
-    """Windows 上的选择模式提示信息"""
+    """Selection mode prompt information on Windows"""

    async def need_show(self) -> bool:
        return os.name == 'nt'
@@ -19,3 +19,8 @@ class SelectionModeOnWindows(note.LaunchNote):
            """您正在使用 Windows 系统，若窗口左上角显示处于”选择“模式，程序将被暂停运行，此时请右键窗口中空白区域退出选择模式。""",
            logging.INFO,
        )
+
+        yield (
+            """You are using Windows system, if the top left corner of the window displays "Selection" mode, the program will be paused running, please right-click on the blank area in the window to exit the selection mode.""",
+            logging.INFO,
+        )
--- a/pkg/core/stage.py
+++ b/pkg/core/stage.py
@@ -7,9 +7,9 @@ from . import app


 preregistered_stages: dict[str, typing.Type[BootingStage]] = {}
-"""预注册的请求处理阶段。在初始化时，所有请求处理阶段类会被注册到此字典中。
+"""Pre-registered request processing stages. All request processing stage classes are registered in this dictionary during initialization.

-当前阶段暂不支持扩展
+Currently not supported for extension
 """


@@ -22,11 +22,11 @@ def stage_class(name: str):


 class BootingStage(abc.ABC):
-    """启动阶段"""
+    """Booting stage"""

    name: str = None

    @abc.abstractmethod
    async def run(self, ap: app.Application):
-        """启动"""
+        """Run"""
        pass
--- a/pkg/core/stages/build_app.py
+++ b/pkg/core/stages/build_app.py
@@ -9,7 +9,7 @@ from ...command import cmdmgr
 from ...provider.session import sessionmgr as llm_session_mgr
 from ...provider.modelmgr import modelmgr as llm_model_mgr
 from ...provider.tools import toolmgr as llm_tool_mgr
-from ...rag.knowledge import mgr as rag_mgr
+from ...rag.knowledge import kbmgr as rag_mgr
 from ...platform import botmgr as im_mgr
 from ...persistence import mgr as persistencemgr
 from ...api.http.controller import main as http_controller
@@ -21,15 +21,16 @@ from ...api.http.service import knowledge as knowledge_service
 from ...discover import engine as discover_engine
 from ...storage import mgr as storagemgr
 from ...utils import logcache
+from ...vector import mgr as vectordb_mgr
 from .. import taskmgr


@stage.stage_class('BuildAppStage')
 class BuildAppStage(stage.BootingStage):
-    """构建应用阶段"""
+    """Build LangBot application"""

    async def run(self, ap: app.Application):
-        """构建app对象的各个组件对象并初始化"""
+        """Build LangBot application"""
        ap.task_mgr = taskmgr.AsyncTaskManager(ap)

        discover = discover_engine.ComponentDiscoveryEngine(ap)
@@ -44,7 +45,7 @@ class BuildAppStage(stage.BootingStage):
        await ver_mgr.initialize()
        ap.ver_mgr = ver_mgr

-        # 发送公告
+        # Send announcement
        ann_mgr = announce.AnnouncementManager(ap)
        ap.ann_mgr = ann_mgr

@@ -91,9 +92,14 @@ class BuildAppStage(stage.BootingStage):
        ap.pipeline_mgr = pipeline_mgr

        rag_mgr_inst = rag_mgr.RAGManager(ap)
-        await rag_mgr_inst.initialize_rag_system()
+        await rag_mgr_inst.initialize()
        ap.rag_mgr = rag_mgr_inst

+        # 初始化向量数据库管理器
+        vectordb_mgr_inst = vectordb_mgr.VectorDBManager(ap)
+        await vectordb_mgr_inst.initialize()
+        ap.vector_db_mgr = vectordb_mgr_inst
+
        http_ctrl = http_controller.HTTPController(ap)
        await http_ctrl.initialize()
        ap.http_ctrl = http_ctrl
--- a/pkg/core/stages/genkeys.py
+++ b/pkg/core/stages/genkeys.py
@@ -7,10 +7,10 @@ from .. import stage, app

@stage.stage_class('GenKeysStage')
 class GenKeysStage(stage.BootingStage):
-    """生成密钥阶段"""
+    """Generate keys stage"""

    async def run(self, ap: app.Application):
-        """启动"""
+        """Generate keys"""

        if not ap.instance_config.data['system']['jwt']['secret']:
            ap.instance_config.data['system']['jwt']['secret'] = secrets.token_hex(16)
--- a/pkg/core/stages/load_config.py
+++ b/pkg/core/stages/load_config.py
@@ -8,10 +8,10 @@ from ..bootutils import config

@stage.stage_class('LoadConfigStage')
 class LoadConfigStage(stage.BootingStage):
-    """加载配置文件阶段"""
+    """Load config file stage"""

    async def run(self, ap: app.Application):
-        """启动"""
+        """Load config file"""

        # ======= deprecated =======
        if os.path.exists('data/config/command.json'):
--- a/pkg/core/stages/migrate.py
+++ b/pkg/core/stages/migrate.py
@@ -11,10 +11,13 @@ importutil.import_modules_in_pkg(migrations)

@stage.stage_class('MigrationStage')
 class MigrationStage(stage.BootingStage):
-    """迁移阶段"""
+    """Migration stage
+
+    These migrations are legacy, only performed in version 3.x
+    """

    async def run(self, ap: app.Application):
-        """启动"""
+        """Run migration"""

        if any(
            [
@@ -29,7 +32,7 @@ class MigrationStage(stage.BootingStage):

        migrations = migration.preregistered_migrations

-        # 按照迁移号排序
+        # Sort by migration number
        migrations.sort(key=lambda x: x.number)

        for migration_cls in migrations:
@@ -37,4 +40,4 @@ class MigrationStage(stage.BootingStage):

            if await migration_instance.need_migrate():
                await migration_instance.run()
-                print(f'已执行迁移 {migration_instance.name}')
+                print(f'Migration {migration_instance.name} executed')
--- a/pkg/core/stages/setup_logger.py
+++ b/pkg/core/stages/setup_logger.py
@@ -8,7 +8,7 @@ from ..bootutils import log

 class PersistenceHandler(logging.Handler, object):
    """
-    保存日志到数据库
+    Save logs to database
    """

    ap: app.Application
@@ -19,9 +19,9 @@ class PersistenceHandler(logging.Handler, object):

    def emit(self, record):
        """
-        emit函数为自定义handler类时必重写的函数，这里可以根据需要对日志消息做一些处理，比如发送日志到服务器
+        emit function is a required function for custom handler classes, here you can process the log messages as needed, such as sending logs to the server

-        发出记录(Emit a record)
+        Emit a record
        """
        try:
            msg = self.format(record)
@@ -34,10 +34,10 @@ class PersistenceHandler(logging.Handler, object):

@stage.stage_class('SetupLoggerStage')
 class SetupLoggerStage(stage.BootingStage):
-    """设置日志器阶段"""
+    """Setup logger stage"""

    async def run(self, ap: app.Application):
-        """启动"""
+        """Setup logger"""
        persistence_handler = PersistenceHandler('LoggerHandler', ap)

        extra_handlers = []
--- a/pkg/core/stages/show_notes.py
+++ b/pkg/core/stages/show_notes.py
@@ -12,10 +12,10 @@ importutil.import_modules_in_pkg(notes)

@stage.stage_class('ShowNotesStage')
 class ShowNotesStage(stage.BootingStage):
-    """显示启动信息阶段"""
+    """Show notes stage"""

    async def run(self, ap: app.Application):
-        # 排序
+        # Sort
        note.preregistered_notes.sort(key=lambda x: x.number)

        for note_cls in note.preregistered_notes:
--- a/pkg/core/taskmgr.py
+++ b/pkg/core/taskmgr.py
@@ -9,13 +9,13 @@ from . import entities as core_entities


 class TaskContext:
-    """任务跟踪上下文"""
+    """Task tracking context"""

    current_action: str
-    """当前正在执行的动作"""
+    """Current action being executed"""

    log: str
-    """记录日志"""
+    """Log"""

    def __init__(self):
        self.current_action = 'default'
@@ -58,40 +58,40 @@ placeholder_context: TaskContext | None = None


 class TaskWrapper:
-    """任务包装器"""
+    """Task wrapper"""

    _id_index: int = 0
-    """任务ID索引"""
+    """Task ID index"""

    id: int
-    """任务ID"""
+    """Task ID"""

-    task_type: str = 'system'  # 任务类型: system 或 user
-    """任务类型"""
+    task_type: str = 'system'  # Task type: system or user
+    """Task type"""

-    kind: str = 'system_task'  # 由发起者确定任务种类，通常同质化的任务种类相同
-    """任务种类"""
+    kind: str = 'system_task'  # Task type determined by the initiator, usually the same task type
+    """Task type"""

    name: str = ''
-    """任务唯一名称"""
+    """Task unique name"""

    label: str = ''
-    """任务显示名称"""
+    """Task display name"""

    task_context: TaskContext
-    """任务上下文"""
+    """Task context"""

    task: asyncio.Task
-    """任务"""
+    """Task"""

    task_stack: list = None
-    """任务堆栈"""
+    """Task stack"""

    ap: app.Application
-    """应用实例"""
+    """Application instance"""

    scopes: list[core_entities.LifecycleControlScope]
-    """任务所属生命周期控制范围"""
+    """Task scope"""

    def __init__(
        self,
@@ -165,13 +165,13 @@ class TaskWrapper:


 class AsyncTaskManager:
-    """保存app中的所有异步任务
-    包含系统级的和用户级（插件安装、更新等由用户直接发起的）的"""
+    """Save all asynchronous tasks in the app
+    Include system-level and user-level (plugin installation, update, etc. initiated by users directly)"""

    ap: app.Application

    tasks: list[TaskWrapper]
-    """所有任务"""
+    """All tasks"""

    def __init__(self, ap: app.Application):
        self.ap = ap
--- a/pkg/entity/persistence/bot.py
+++ b/pkg/entity/persistence/bot.py
@@ -4,7 +4,7 @@ from .base import Base


 class Bot(Base):
-    """机器人"""
+    """Bot"""

    __tablename__ = 'bots'

--- a/pkg/entity/persistence/metadata.py
+++ b/pkg/entity/persistence/metadata.py
@@ -12,7 +12,7 @@ initial_metadata = [


 class Metadata(Base):
-    """数据库元数据"""
+    """Database metadata"""

    __tablename__ = 'metadata'

--- a/pkg/entity/persistence/model.py
+++ b/pkg/entity/persistence/model.py
@@ -4,7 +4,7 @@ from .base import Base


 class LLMModel(Base):
-    """LLM 模型"""
+    """LLM model"""

    __tablename__ = 'llm_models'

--- a/pkg/entity/persistence/pipeline.py
+++ b/pkg/entity/persistence/pipeline.py
@@ -4,7 +4,7 @@ from .base import Base


 class LegacyPipeline(Base):
-    """旧版流水线"""
+    """Legacy pipeline"""

    __tablename__ = 'legacy_pipelines'

@@ -20,13 +20,12 @@ class LegacyPipeline(Base):
    )
    for_version = sqlalchemy.Column(sqlalchemy.String(255), nullable=False)
    is_default = sqlalchemy.Column(sqlalchemy.Boolean, nullable=False, default=False)
-
    stages = sqlalchemy.Column(sqlalchemy.JSON, nullable=False)
    config = sqlalchemy.Column(sqlalchemy.JSON, nullable=False)


 class PipelineRunRecord(Base):
-    """流水线运行记录"""
+    """Pipeline run record"""

    __tablename__ = 'pipeline_run_records'

@@ -43,3 +42,4 @@ class PipelineRunRecord(Base):
    started_at = sqlalchemy.Column(sqlalchemy.DateTime, nullable=False)
    finished_at = sqlalchemy.Column(sqlalchemy.DateTime, nullable=False)
    result = sqlalchemy.Column(sqlalchemy.JSON, nullable=False)
+    knowledge_base_uuid = sqlalchemy.Column(sqlalchemy.String(255), nullable=True)
--- a/pkg/entity/persistence/plugin.py
+++ b/pkg/entity/persistence/plugin.py
@@ -4,7 +4,7 @@ from .base import Base


 class PluginSetting(Base):
-    """插件配置"""
+    """Plugin setting"""

    __tablename__ = 'plugin_settings'

--- a/pkg/rag/knowledge/utils/crawler.py
+++ b/pkg/rag/knowledge/utils/crawler.py
--- a/pkg/entity/rag/retriever.py
+++ b/pkg/entity/rag/retriever.py
@@ -0,0 +1,13 @@
+from __future__ import annotations
+
+import pydantic
+
+from typing import Any
+
+
+class RetrieveResultEntry(pydantic.BaseModel):
+    id: str
+
+    metadata: dict[str, Any]
+
+    distance: float
--- a/pkg/persistence/database.py
+++ b/pkg/persistence/database.py
@@ -11,7 +11,7 @@ preregistered_managers: list[type[BaseDatabaseManager]] = []


 def manager_class(name: str) -> None:
-    """注册一个数据库管理类"""
+    """Register a database manager class"""

    def decorator(cls: type[BaseDatabaseManager]) -> type[BaseDatabaseManager]:
        cls.name = name
@@ -22,7 +22,7 @@ def manager_class(name: str) -> None:


 class BaseDatabaseManager(abc.ABC):
-    """基础数据库管理类"""
+    """Base database manager class"""

    name: str

--- a/pkg/persistence/databases/sqlite.py
+++ b/pkg/persistence/databases/sqlite.py
@@ -7,7 +7,7 @@ from .. import database

@database.manager_class('sqlite')
 class SQLiteDatabaseManager(database.BaseDatabaseManager):
-    """SQLite 数据库管理类"""
+    """SQLite database manager"""

    async def initialize(self) -> None:
        sqlite_path = 'data/langbot.db'
--- a/pkg/persistence/mgr.py
+++ b/pkg/persistence/mgr.py
@@ -22,12 +22,12 @@ importutil.import_modules_in_pkg(persistence)


 class PersistenceManager:
-    """持久化模块管理器"""
+    """Persistence module manager"""

    ap: app.Application

    db: database.BaseDatabaseManager
-    """数据库管理器"""
+    """Database manager"""

    meta: sqlalchemy.MetaData

@@ -79,7 +79,7 @@ class PersistenceManager:
                'stages': pipeline_service.default_stage_order,
                'is_default': True,
                'name': 'ChatPipeline',
-                'description': '默认提供的流水线，您配置的机器人、第一个模型将自动绑定到此流水线',
+                'description': 'Default pipeline, new bots will be bound to this pipeline | 默认提供的流水线，您配置的机器人将自动绑定到此流水线',
                'config': pipeline_config,
            }

--- a/pkg/persistence/migration.py
+++ b/pkg/persistence/migration.py
@@ -10,7 +10,7 @@ preregistered_db_migrations: list[typing.Type[DBMigration]] = []


 def migration_class(number: int):
-    """迁移类装饰器"""
+    """Migration class decorator"""

    def wrapper(cls: typing.Type[DBMigration]) -> typing.Type[DBMigration]:
        cls.number = number
@@ -21,20 +21,20 @@ def migration_class(number: int):


 class DBMigration(abc.ABC):
-    """数据库迁移"""
+    """Database migration"""

    number: int
-    """迁移号"""
+    """Migration number"""

    def __init__(self, ap: app.Application):
        self.ap = ap

    @abc.abstractmethod
    async def upgrade(self):
-        """升级"""
+        """Upgrade"""
        pass

    @abc.abstractmethod
    async def downgrade(self):
-        """降级"""
+        """Downgrade"""
        pass
--- a/pkg/persistence/migrations/dbm001_migrate_v3_config.py
+++ b/pkg/persistence/migrations/dbm001_migrate_v3_config.py
@@ -15,21 +15,21 @@ from ...entity.persistence import (

@migration.migration_class(1)
 class DBMigrateV3Config(migration.DBMigration):
-    """从 v3 的配置迁移到 v4 的数据库"""
+    """Migrate v3 config to v4 database"""

    async def upgrade(self):
-        """升级"""
+        """Upgrade"""
        """
-        将 data/config 下的所有配置文件进行迁移。
-        迁移后，之前的配置文件都保存到 data/legacy/config 下。
-        迁移后，data/metadata/ 下的所有配置文件都保存到 data/legacy/metadata 下。
+        Migrate all config files under data/config.
+        After migration, all previous config files are saved under data/legacy/config.
+        After migration, all config files under data/metadata/ are saved under data/legacy/metadata.
        """

        if self.ap.provider_cfg is None:
            return

-        # ======= 迁移模型 =======
-        # 只迁移当前选中的模型
+        # ======= Migrate model =======
+        # Only migrate the currently selected model
        model_name = self.ap.provider_cfg.data.get('model', 'gpt-4o')

        model_requester = 'openai-chat-completions'
@@ -91,8 +91,8 @@ class DBMigrateV3Config(migration.DBMigration):
            sqlalchemy.insert(persistence_model.LLMModel).values(**llm_model_data)
        )

-        # ======= 迁移流水线配置 =======
-        # 修改到默认流水线
+        # ======= Migrate pipeline config =======
+        # Modify to default pipeline
        default_pipeline = [
            self.ap.persistence_mgr.serialize_model(persistence_pipeline.LegacyPipeline, pipeline)
            for pipeline in (
@@ -184,8 +184,8 @@ class DBMigrateV3Config(migration.DBMigration):
                .where(persistence_pipeline.LegacyPipeline.uuid == default_pipeline['uuid'])
            )

-        # ======= 迁移机器人 =======
-        # 只迁移启用的机器人
+        # ======= Migrate bot =======
+        # Only migrate enabled bots
        for adapter in self.ap.platform_cfg.data.get('platform-adapters', []):
            if not adapter.get('enable'):
                continue
@@ -207,7 +207,7 @@ class DBMigrateV3Config(migration.DBMigration):

            await self.ap.persistence_mgr.execute_async(sqlalchemy.insert(persistence_bot.Bot).values(**bot_data))

-        # ======= 迁移系统设置 =======
+        # ======= Migrate system settings =======
        self.ap.instance_config.data['admins'] = self.ap.system_cfg.data['admin-sessions']
        self.ap.instance_config.data['api']['port'] = self.ap.system_cfg.data['http-api']['port']
        self.ap.instance_config.data['command'] = {
@@ -223,7 +223,7 @@ class DBMigrateV3Config(migration.DBMigration):
        await self.ap.instance_config.dump_config()

        # ======= move files =======
-        # 迁移 data/config 下的所有配置文件
+        # Migrate all config files under data/config
        all_legacy_dir_name = [
            'config',
            # 'metadata',
@@ -246,4 +246,4 @@ class DBMigrateV3Config(migration.DBMigration):
            move_legacy_files(dir_name)

    async def downgrade(self):
-        """降级"""
+        """Downgrade"""
--- a/pkg/persistence/migrations/dbm002_combine_quote_msg_config.py
+++ b/pkg/persistence/migrations/dbm002_combine_quote_msg_config.py
@@ -7,10 +7,10 @@ from ...entity.persistence import pipeline as persistence_pipeline

@migration.migration_class(2)
 class DBMigrateCombineQuoteMsgConfig(migration.DBMigration):
-    """引用消息合并配置"""
+    """Combine quote message config"""

    async def upgrade(self):
-        """升级"""
+        """Upgrade"""
        # read all pipelines
        pipelines = await self.ap.persistence_mgr.execute_async(sqlalchemy.select(persistence_pipeline.LegacyPipeline))

@@ -37,5 +37,5 @@ class DBMigrateCombineQuoteMsgConfig(migration.DBMigration):
            )

    async def downgrade(self):
-        """降级"""
+        """Downgrade"""
        pass
--- a/pkg/persistence/migrations/dbm003_n8n_config.py
+++ b/pkg/persistence/migrations/dbm003_n8n_config.py
@@ -7,10 +7,10 @@ from ...entity.persistence import pipeline as persistence_pipeline

@migration.migration_class(3)
 class DBMigrateN8nConfig(migration.DBMigration):
-    """N8n配置"""
+    """N8n config"""

    async def upgrade(self):
-        """升级"""
+        """Upgrade"""
        # read all pipelines
        pipelines = await self.ap.persistence_mgr.execute_async(sqlalchemy.select(persistence_pipeline.LegacyPipeline))

@@ -45,5 +45,5 @@ class DBMigrateN8nConfig(migration.DBMigration):
            )

    async def downgrade(self):
-        """降级"""
+        """Downgrade"""
        pass
--- a/pkg/persistence/migrations/dbm004_rag_kb_uuid.py
+++ b/pkg/persistence/migrations/dbm004_rag_kb_uuid.py
@@ -0,0 +1,38 @@
+from .. import migration
+
+import sqlalchemy
+
+from ...entity.persistence import pipeline as persistence_pipeline
+
+
+@migration.migration_class(4)
+class DBMigrateRAGKBUUID(migration.DBMigration):
+    """RAG知识库UUID"""
+
+    async def upgrade(self):
+        """升级"""
+        # read all pipelines
+        pipelines = await self.ap.persistence_mgr.execute_async(sqlalchemy.select(persistence_pipeline.LegacyPipeline))
+
+        for pipeline in pipelines:
+            serialized_pipeline = self.ap.persistence_mgr.serialize_model(persistence_pipeline.LegacyPipeline, pipeline)
+
+            config = serialized_pipeline['config']
+
+            if 'knowledge-base' not in config['ai']['local-agent']:
+                config['ai']['local-agent']['knowledge-base'] = ''
+
+            await self.ap.persistence_mgr.execute_async(
+                sqlalchemy.update(persistence_pipeline.LegacyPipeline)
+                .where(persistence_pipeline.LegacyPipeline.uuid == serialized_pipeline['uuid'])
+                .values(
+                    {
+                        'config': config,
+                        'for_version': self.ap.ver_mgr.get_current_version(),
+                    }
+                )
+            )
+
+    async def downgrade(self):
+        """降级"""
+        pass
--- a/pkg/pipeline/bansess/bansess.py
+++ b/pkg/pipeline/bansess/bansess.py
@@ -6,9 +6,9 @@ from ...core import entities as core_entities

@stage.stage_class('BanSessionCheckStage')
 class BanSessionCheckStage(stage.PipelineStage):
-    """访问控制处理阶段
+    """Access control processing stage

-    仅检查query中群号或个人号是否在访问控制列表中。
+    Only check if the group or personal number in the query is in the access control list.
    """

    async def initialize(self, pipeline_config: dict):
@@ -41,5 +41,7 @@ class BanSessionCheckStage(stage.PipelineStage):
        return entities.StageProcessResult(
            result_type=entities.ResultType.CONTINUE if ctn else entities.ResultType.INTERRUPT,
            new_query=query,
-            console_notice=f'根据访问控制忽略消息: {query.launcher_type.value}_{query.launcher_id}' if not ctn else '',
+            console_notice=f'Ignore message according to access control: {query.launcher_type.value}_{query.launcher_id}'
+            if not ctn
+            else '',
        )
--- a/pkg/pipeline/cntfilter/filter.py
+++ b/pkg/pipeline/cntfilter/filter.py
@@ -13,13 +13,13 @@ preregistered_filters: list[typing.Type[ContentFilter]] = []
 def filter_class(
    name: str,
 ) -> typing.Callable[[typing.Type[ContentFilter]], typing.Type[ContentFilter]]:
-    """内容过滤器类装饰器
+    """Content filter class decorator

    Args:
-        name (str): 过滤器名称
+        name (str): Filter name

    Returns:
-        typing.Callable[[typing.Type[ContentFilter]], typing.Type[ContentFilter]]: 装饰器
+        typing.Callable[[typing.Type[ContentFilter]], typing.Type[ContentFilter]]: Decorator
    """

    def decorator(cls: typing.Type[ContentFilter]) -> typing.Type[ContentFilter]:
@@ -35,7 +35,7 @@ def filter_class(


 class ContentFilter(metaclass=abc.ABCMeta):
-    """内容过滤器抽象类"""
+    """Content filter abstract class"""

    name: str

@@ -46,31 +46,31 @@ class ContentFilter(metaclass=abc.ABCMeta):

    @property
    def enable_stages(self):
-        """启用的阶段
+        """Enabled stages

-        默认为消息请求AI前后的两个阶段。
+        Default is the two stages before and after the message request to AI.

-        entity.EnableStage.PRE: 消息请求AI前，此时需要检查的内容是用户的输入消息。
-        entity.EnableStage.POST: 消息请求AI后，此时需要检查的内容是AI的回复消息。
+        entity.EnableStage.PRE: Before message request to AI, the content to check is the user's input message.
+        entity.EnableStage.POST: After message request to AI, the content to check is the AI's reply message.
        """
        return [entities.EnableStage.PRE, entities.EnableStage.POST]

    async def initialize(self):
-        """初始化过滤器"""
+        """Initialize filter"""
        pass

    @abc.abstractmethod
    async def process(self, query: core_entities.Query, message: str = None, image_url=None) -> entities.FilterResult:
-        """处理消息
+        """Process message

-        分为前后阶段，具体取决于 enable_stages 的值。
-        对于内容过滤器来说，不需要考虑消息所处的阶段，只需要检查消息内容即可。
+        It is divided into two stages, depending on the value of enable_stages.
+        For content filters, you do not need to consider the stage of the message, you only need to check the message content.

        Args:
-            message (str): 需要检查的内容
-            image_url (str): 要检查的图片的 URL
+            message (str): Content to check
+            image_url (str): URL of the image to check

        Returns:
-            entities.FilterResult: 过滤结果，具体内容请查看 entities.FilterResult 类的文档
+            entities.FilterResult: Filter result, please refer to the documentation of entities.FilterResult class
        """
        raise NotImplementedError
--- a/pkg/pipeline/cntfilter/filters/banwords.py
+++ b/pkg/pipeline/cntfilter/filters/banwords.py
@@ -8,7 +8,7 @@ from ....core import entities as core_entities

@filter_model.filter_class('ban-word-filter')
 class BanWordFilter(filter_model.ContentFilter):
-    """根据内容过滤"""
+    """Filter content"""

    async def initialize(self):
        pass
--- a/pkg/pipeline/cntfilter/filters/cntignore.py
+++ b/pkg/pipeline/cntfilter/filters/cntignore.py
@@ -8,7 +8,7 @@ from ....core import entities as core_entities

@filter_model.filter_class('content-ignore')
 class ContentIgnore(filter_model.ContentFilter):
-    """根据内容忽略消息"""
+    """Ignore message according to content"""

    @property
    def enable_stages(self):
@@ -24,7 +24,7 @@ class ContentIgnore(filter_model.ContentFilter):
                        level=entities.ResultLevel.BLOCK,
                        replacement='',
                        user_notice='',
-                        console_notice='根据 ignore_rules 中的 prefix 规则，忽略消息',
+                        console_notice='Ignore message according to prefix rule in ignore_rules',
                    )

        if 'regexp' in query.pipeline_config['trigger']['ignore-rules']:
@@ -34,7 +34,7 @@ class ContentIgnore(filter_model.ContentFilter):
                        level=entities.ResultLevel.BLOCK,
                        replacement='',
                        user_notice='',
-                        console_notice='根据 ignore_rules 中的 regexp 规则，忽略消息',
+                        console_notice='Ignore message according to regexp rule in ignore_rules',
                    )

        return entities.FilterResult(
--- a/pkg/pipeline/longtext/longtext.py
+++ b/pkg/pipeline/longtext/longtext.py
@@ -16,9 +16,9 @@ importutil.import_modules_in_pkg(strategies)

@stage.stage_class('LongTextProcessStage')
 class LongTextProcessStage(stage.PipelineStage):
-    """长消息处理阶段
+    """Long message processing stage

-    改写：
+    Rewrite:
        - resp_message_chain
    """

@@ -36,22 +36,22 @@ class LongTextProcessStage(stage.PipelineStage):
                        use_font = 'C:/Windows/Fonts/msyh.ttc'
                        if not os.path.exists(use_font):
                            self.ap.logger.warn(
-                                '未找到字体文件，且无法使用Windows自带字体，更换为转发消息组件以发送长消息，您可以在配置文件中调整相关设置。'
+                                'Font file not found, and Windows system font cannot be used, switch to forward message component to send long messages, you can adjust the related settings in the configuration file.'
                            )
                            config['blob_message_strategy'] = 'forward'
                        else:
-                            self.ap.logger.info('使用Windows自带字体：' + use_font)
+                            self.ap.logger.info('Using Windows system font: ' + use_font)
                            config['font-path'] = use_font
                    else:
                        self.ap.logger.warn(
-                            '未找到字体文件，且无法使用系统自带字体，更换为转发消息组件以发送长消息，您可以在配置文件中调整相关设置。'
+                            'Font file not found, and system font cannot be used, switch to forward message component to send long messages, you can adjust the related settings in the configuration file.'
                        )

                        pipeline_config['output']['long-text-processing']['strategy'] = 'forward'
            except Exception:
                traceback.print_exc()
                self.ap.logger.error(
-                    '加载字体文件失败({})，更换为转发消息组件以发送长消息，您可以在配置文件中调整相关设置。'.format(
+                    'Failed to load font file ({}), switch to forward message component to send long messages, you can adjust the related settings in the configuration file.'.format(
                        use_font
                    )
                )
@@ -63,12 +63,12 @@ class LongTextProcessStage(stage.PipelineStage):
                self.strategy_impl = strategy_cls(self.ap)
                break
        else:
-            raise ValueError(f'未找到名为 {config["strategy"]} 的长消息处理策略')
+            raise ValueError(f'Long message processing strategy not found: {config["strategy"]}')

        await self.strategy_impl.initialize()

    async def process(self, query: core_entities.Query, stage_inst_name: str) -> entities.StageProcessResult:
-        # 检查是否包含非 Plain 组件
+        # Check if it contains non-Plain components
        contains_non_plain = False

        for msg in query.resp_message_chain[-1]:
@@ -77,7 +77,7 @@ class LongTextProcessStage(stage.PipelineStage):
                break

        if contains_non_plain:
-            self.ap.logger.debug('消息中包含非 Plain 组件，跳过长消息处理。')
+            self.ap.logger.debug('Message contains non-Plain components, skip long message processing.')
        elif (
            len(str(query.resp_message_chain[-1]))
            > query.pipeline_config['output']['long-text-processing']['threshold']
--- a/pkg/pipeline/longtext/strategies/forward.py
+++ b/pkg/pipeline/longtext/strategies/forward.py
@@ -15,17 +15,17 @@ Forward = platform_message.Forward
 class ForwardComponentStrategy(strategy_model.LongTextStrategy):
    async def process(self, message: str, query: core_entities.Query) -> list[platform_message.MessageComponent]:
        display = ForwardMessageDiaplay(
-            title='群聊的聊天记录',
-            brief='[聊天记录]',
-            source='聊天记录',
-            preview=['QQ用户: ' + message],
-            summary='查看1条转发消息',
+            title='Group chat history',
+            brief='[Chat history]',
+            source='Chat history',
+            preview=['User: ' + message],
+            summary='View 1 forwarded message',
        )

        node_list = [
            platform_message.ForwardMessageNode(
                sender_id=query.adapter.bot_account_id,
-                sender_name='QQ用户',
+                sender_name='User',
                message_chain=platform_message.MessageChain([message]),
            )
        ]
--- a/pkg/pipeline/longtext/strategy.py
+++ b/pkg/pipeline/longtext/strategy.py
@@ -14,13 +14,13 @@ preregistered_strategies: list[typing.Type[LongTextStrategy]] = []
 def strategy_class(
    name: str,
 ) -> typing.Callable[[typing.Type[LongTextStrategy]], typing.Type[LongTextStrategy]]:
-    """长文本处理策略类装饰器
+    """Long text processing strategy class decorator

    Args:
-        name (str): 策略名称
+        name (str): Strategy name

    Returns:
-        typing.Callable[[typing.Type[LongTextStrategy]], typing.Type[LongTextStrategy]]: 装饰器
+        typing.Callable[[typing.Type[LongTextStrategy]], typing.Type[LongTextStrategy]]: Decorator
    """

    def decorator(cls: typing.Type[LongTextStrategy]) -> typing.Type[LongTextStrategy]:
@@ -36,7 +36,7 @@ def strategy_class(


 class LongTextStrategy(metaclass=abc.ABCMeta):
-    """长文本处理策略抽象类"""
+    """Long text processing strategy abstract class"""

    name: str

@@ -50,15 +50,15 @@ class LongTextStrategy(metaclass=abc.ABCMeta):

    @abc.abstractmethod
    async def process(self, message: str, query: core_entities.Query) -> list[platform_message.MessageComponent]:
-        """处理长文本
+        """Process long text

-        在 platform.json 中配置 long-text-process 字段，只要 文本长度超过了 threshold 就会调用此方法
+        If the text length exceeds the threshold, this method will be called.

        Args:
-            message (str): 消息
-            query (core_entities.Query): 此次请求的上下文对象
+            message (str): Message
+            query (core_entities.Query): Query object

        Returns:
-            list[platform_message.MessageComponent]: 转换后的 平台 消息组件列表
+            list[platform_message.MessageComponent]: Converted platform message components
        """
        return []
--- a/pkg/pipeline/msgtrun/msgtrun.py
+++ b/pkg/pipeline/msgtrun/msgtrun.py
@@ -12,9 +12,9 @@ importutil.import_modules_in_pkg(truncators)

@stage.stage_class('ConversationMessageTruncator')
 class ConversationMessageTruncator(stage.PipelineStage):
-    """会话消息截断器
+    """Conversation message truncator

-    用于截断会话消息链，以适应平台消息长度限制。
+    Used to truncate the conversation message chain to adapt to the LLM message length limit.
    """

    trun: truncator.Truncator
@@ -27,10 +27,10 @@ class ConversationMessageTruncator(stage.PipelineStage):
                self.trun = trun(self.ap)
                break
        else:
-            raise ValueError(f'未知的截断器: {use_method}')
+            raise ValueError(f'Unknown truncator: {use_method}')

    async def process(self, query: core_entities.Query, stage_inst_name: str) -> entities.StageProcessResult:
-        """处理"""
+        """Process"""
        query = await self.trun.truncate(query)

        return entities.StageProcessResult(result_type=entities.ResultType.CONTINUE, new_query=query)
--- a/pkg/pipeline/msgtrun/truncators/round.py
+++ b/pkg/pipeline/msgtrun/truncators/round.py
@@ -6,17 +6,17 @@ from ....core import entities as core_entities

@truncator.truncator_class('round')
 class RoundTruncator(truncator.Truncator):
-    """前文回合数阶段器"""
+    """Truncate the conversation message chain to adapt to the LLM message length limit."""

    async def truncate(self, query: core_entities.Query) -> core_entities.Query:
-        """截断"""
+        """Truncate"""
        max_round = query.pipeline_config['ai']['local-agent']['max-round']

        temp_messages = []

        current_round = 0

-        # 从后往前遍历
+        # Traverse from back to front
        for msg in query.messages[::-1]:
            if current_round < max_round:
                temp_messages.append(msg)
--- a/pkg/pipeline/pipelinemgr.py
+++ b/pkg/pipeline/pipelinemgr.py
@@ -144,23 +144,27 @@ class RuntimePipeline:
                result = await result

            if isinstance(result, pipeline_entities.StageProcessResult):  # 直接返回结果
-                self.ap.logger.debug(f'Stage {stage_container.inst_name} processed query {query} res {result}')
+                self.ap.logger.debug(
+                    f'Stage {stage_container.inst_name} processed query {query.query_id} res {result.result_type}'
+                )
                await self._check_output(query, result)

                if result.result_type == pipeline_entities.ResultType.INTERRUPT:
-                    self.ap.logger.debug(f'Stage {stage_container.inst_name} interrupted query {query}')
+                    self.ap.logger.debug(f'Stage {stage_container.inst_name} interrupted query {query.query_id}')
                    break
                elif result.result_type == pipeline_entities.ResultType.CONTINUE:
                    query = result.new_query
            elif isinstance(result, typing.AsyncGenerator):  # 生成器
-                self.ap.logger.debug(f'Stage {stage_container.inst_name} processed query {query} gen')
+                self.ap.logger.debug(f'Stage {stage_container.inst_name} processed query {query.query_id} gen')

                async for sub_result in result:
-                    self.ap.logger.debug(f'Stage {stage_container.inst_name} processed query {query} res {sub_result}')
+                    self.ap.logger.debug(
+                        f'Stage {stage_container.inst_name} processed query {query.query_id} res {sub_result.result_type}'
+                    )
                    await self._check_output(query, sub_result)

                    if sub_result.result_type == pipeline_entities.ResultType.INTERRUPT:
-                        self.ap.logger.debug(f'Stage {stage_container.inst_name} interrupted query {query}')
+                        self.ap.logger.debug(f'Stage {stage_container.inst_name} interrupted query {query.query_id}')
                        break
                    elif sub_result.result_type == pipeline_entities.ResultType.CONTINUE:
                        query = sub_result.new_query
@@ -192,7 +196,7 @@ class RuntimePipeline:
            if event_ctx.is_prevented_default():
                return

-            self.ap.logger.debug(f'Processing query {query}')
+            self.ap.logger.debug(f'Processing query {query.query_id}')

            await self._execute_from_stage(0, query)
        except Exception as e:
@@ -200,7 +204,7 @@ class RuntimePipeline:
            self.ap.logger.error(f'处理请求时出错 query_id={query.query_id} stage={inst_name} : {e}')
            self.ap.logger.error(f'Traceback: {traceback.format_exc()}')
        finally:
-            self.ap.logger.debug(f'Query {query} processed')
+            self.ap.logger.debug(f'Query {query.query_id} processed')


 class PipelineManager:
--- a/pkg/pipeline/preproc/preproc.py
+++ b/pkg/pipeline/preproc/preproc.py
@@ -11,11 +11,11 @@ from ...platform.types import message as platform_message

@stage.stage_class('PreProcessor')
 class PreProcessor(stage.PipelineStage):
-    """请求预处理阶段
+    """Request pre-processing stage

-    签出会话、prompt、上文、模型、内容函数。
+    Check out session, prompt, context, model, and content functions.

-    改写：
+    Rewrite:
        - session
        - prompt
        - messages
@@ -29,12 +29,12 @@ class PreProcessor(stage.PipelineStage):
        query: core_entities.Query,
        stage_inst_name: str,
    ) -> entities.StageProcessResult:
-        """处理"""
+        """Process"""
        selected_runner = query.pipeline_config['ai']['runner']['runner']

        session = await self.ap.sess_mgr.get_session(query)

-        # 非 local-agent 时，llm_model 为 None
+        # When not local-agent, llm_model is None
        llm_model = (
            await self.ap.model_mgr.get_model_by_uuid(query.pipeline_config['ai']['local-agent']['model'])
            if selected_runner == 'local-agent'
@@ -51,7 +51,7 @@ class PreProcessor(stage.PipelineStage):

        conversation.use_llm_model = llm_model

-        # 设置query
+        # Set query
        query.session = session
        query.prompt = conversation.prompt.copy()
        query.messages = conversation.messages.copy()
@@ -80,14 +80,15 @@ class PreProcessor(stage.PipelineStage):
                        if me.type == 'image_url':
                            msg.content.remove(me)

-        content_list = []
+        content_list: list[llm_entities.ContentElement] = []

        plain_text = ''
        qoute_msg = query.pipeline_config['trigger'].get('misc', '').get('combine-quote-message')

+        # tidy the content_list
+        # combine all text content into one, and put it in the first position
        for me in query.message_chain:
            if isinstance(me, platform_message.Plain):
-                content_list.append(llm_entities.ContentElement.from_text(me.text))
                plain_text += me.text
            elif isinstance(me, platform_message.Image):
                if selected_runner != 'local-agent' or query.use_llm_model.model_entity.abilities.__contains__(
@@ -106,10 +107,12 @@ class PreProcessor(stage.PipelineStage):
                            if msg.base64 is not None:
                                content_list.append(llm_entities.ContentElement.from_image_base64(msg.base64))

+        content_list.insert(0, llm_entities.ContentElement.from_text(plain_text))
+
        query.variables['user_message_text'] = plain_text

        query.user_message = llm_entities.Message(role='user', content=content_list)
-        # =========== 触发事件 PromptPreProcessing
+        # =========== Trigger event PromptPreProcessing

        event_ctx = await self.ap.plugin_mgr.emit_event(
            event=events.PromptPreProcessing(
--- a/pkg/pipeline/process/handler.py
+++ b/pkg/pipeline/process/handler.py
@@ -25,7 +25,7 @@ class MessageHandler(metaclass=abc.ABCMeta):

    def cut_str(self, s: str) -> str:
        """
-        取字符串第一行，最多20个字符，若有多行，或超过20个字符，则加省略号
+        Take the first line of the string, up to 20 characters, if there are multiple lines, or more than 20 characters, add an ellipsis
        """
        s0 = s.split('\n')[0]
        if len(s0) > 20 or '\n' in s:
--- a/pkg/pipeline/process/handlers/chat.py
+++ b/pkg/pipeline/process/handlers/chat.py
@@ -22,11 +22,11 @@ class ChatMessageHandler(handler.MessageHandler):
        self,
        query: core_entities.Query,
    ) -> typing.AsyncGenerator[entities.StageProcessResult, None]:
-        """处理"""
-        # 调API
-        #   生成器
+        """Process"""
+        # Call API
+        #   generator

-        # 触发插件事件
+        # Trigger plugin event
        event_class = (
            events.PersonNormalMessageReceived
            if query.launcher_type == core_entities.LauncherTypes.PERSON
@@ -54,7 +54,7 @@ class ChatMessageHandler(handler.MessageHandler):
                yield entities.StageProcessResult(result_type=entities.ResultType.INTERRUPT, new_query=query)
        else:
            if event_ctx.event.alter is not None:
-                # if isinstance(event_ctx.event, str):  # 现在暂时不考虑多模态alter
+                # if isinstance(event_ctx.event, str):  # Currently not considering multi-modal alter
                query.user_message.content = event_ctx.event.alter

            text_length = 0
@@ -65,12 +65,12 @@ class ChatMessageHandler(handler.MessageHandler):
                        runner = r(self.ap, query.pipeline_config)
                        break
                else:
-                    raise ValueError(f'未找到请求运行器: {query.pipeline_config["ai"]["runner"]["runner"]}')
+                    raise ValueError(f'Request runner not found: {query.pipeline_config["ai"]["runner"]["runner"]}')

                async for result in runner.run(query):
                    query.resp_messages.append(result)

-                    self.ap.logger.info(f'对话({query.query_id})响应: {self.cut_str(result.readable_str())}')
+                    self.ap.logger.info(f'Response({query.query_id}): {self.cut_str(result.readable_str())}')

                    if result.content is not None:
                        text_length += len(result.content)
@@ -80,7 +80,7 @@ class ChatMessageHandler(handler.MessageHandler):
                query.session.using_conversation.messages.append(query.user_message)
                query.session.using_conversation.messages.extend(query.resp_messages)
            except Exception as e:
-                self.ap.logger.error(f'对话({query.query_id})请求失败: {type(e).__name__} {str(e)}')
+                self.ap.logger.error(f'Request failed({query.query_id}): {type(e).__name__} {str(e)}')

                hide_exception_info = query.pipeline_config['output']['misc']['hide-exception']

--- a/pkg/pipeline/process/handlers/command.py
+++ b/pkg/pipeline/process/handlers/command.py
@@ -15,7 +15,7 @@ class CommandHandler(handler.MessageHandler):
        self,
        query: core_entities.Query,
    ) -> typing.AsyncGenerator[entities.StageProcessResult, None]:
-        """处理"""
+        """Process"""

        command_text = str(query.message_chain).strip()[1:]

@@ -70,7 +70,7 @@ class CommandHandler(handler.MessageHandler):
                        )
                    )

-                    self.ap.logger.info(f'命令({query.query_id})报错: {self.cut_str(str(ret.error))}')
+                    self.ap.logger.info(f'Command({query.query_id}) error: {self.cut_str(str(ret.error))}')

                    yield entities.StageProcessResult(result_type=entities.ResultType.CONTINUE, new_query=query)
                elif ret.text is not None or ret.image_url is not None:
@@ -89,7 +89,7 @@ class CommandHandler(handler.MessageHandler):
                        )
                    )

-                    self.ap.logger.info(f'命令返回: {self.cut_str(str(content[0]))}')
+                    self.ap.logger.info(f'Command returned: {self.cut_str(str(content[0]))}')

                    yield entities.StageProcessResult(result_type=entities.ResultType.CONTINUE, new_query=query)
                else:
--- a/pkg/pipeline/process/process.py
+++ b/pkg/pipeline/process/process.py
@@ -33,11 +33,11 @@ class Processor(stage.PipelineStage):
        query: core_entities.Query,
        stage_inst_name: str,
    ) -> entities.StageProcessResult:
-        """处理"""
+        """Process"""
        message_text = str(query.message_chain).strip()

        self.ap.logger.info(
-            f'处理 {query.launcher_type.value}_{query.launcher_id} 的请求({query.query_id}): {message_text}'
+            f'Processing request from {query.launcher_type.value}_{query.launcher_id} ({query.query_id}): {message_text}'
        )

        async def generator():
--- a/pkg/platform/sources/aiocqhttp.py
+++ b/pkg/platform/sources/aiocqhttp.py
@@ -76,8 +76,7 @@ class AiocqhttpMessageConverter(adapter.MessageConverter):
        return msg_list, msg_id, msg_time

    @staticmethod
-    async def target2yiri(message: str, message_id: int = -1, bot=None):
-        print(message)
+    async def target2yiri(message: str, message_id: int = -1, bot: aiocqhttp.CQHttp = None):
        message = aiocqhttp.Message(message)

        def get_face_name(face_id):
@@ -271,16 +270,16 @@ class AiocqhttpMessageConverter(adapter.MessageConverter):
                )
                yiri_msg_list.append(reply_msg)

-            elif msg.type == 'file':
-                # file_name = msg.data['file']
-                file_id = msg.data['file_id']
-                file_data = await bot.get_file(file_id=file_id)
-                file_name = file_data.get('file_name')
-                file_path = file_data.get('file')
-                _ = file_path
-                file_url = file_data.get('file_url')
-                file_size = file_data.get('file_size')
-                yiri_msg_list.append(platform_message.File(id=file_id, name=file_name, url=file_url, size=file_size))
+            # 这里下载所有文件会导致下载文件过多，暂时不下载
+            # elif msg.type == 'file':
+            #     # file_name = msg.data['file']
+            #     file_id = msg.data['file_id']
+            #     file_data = await bot.get_file(file_id=file_id)
+            #     file_name = file_data.get('file_name')
+            #     file_path = file_data.get('file')
+            #     file_url = file_data.get('file_url')
+            #     file_size = file_data.get('file_size')
+            #     yiri_msg_list.append(platform_message.File(id=file_id, name=file_name,url=file_url,size=file_size))
            elif msg.type == 'face':
                face_id = msg.data['id']
                face_name = msg.data['raw']['faceText']
--- a/pkg/platform/sources/dingtalk.py
+++ b/pkg/platform/sources/dingtalk.py
@@ -116,6 +116,15 @@ class DingTalkAdapter(adapter.MessagePlatformAdapter):

        self.bot_account_id = self.config['robot_name']

+        self.bot = DingTalkClient(
+            client_id=config['client_id'],
+            client_secret=config['client_secret'],
+            robot_name=config['robot_name'],
+            robot_code=config['robot_code'],
+            markdown_card=config['markdown_card'],
+            logger=self.logger,
+        )
+
    async def reply_message(
        self,
        message_source: platform_events.MessageEvent,
@@ -157,15 +166,6 @@ class DingTalkAdapter(adapter.MessagePlatformAdapter):
            self.bot.on_message('GroupMessage')(on_message)

    async def run_async(self):
-        config = self.config
-        self.bot = DingTalkClient(
-            client_id=config['client_id'],
-            client_secret=config['client_secret'],
-            robot_name=config['robot_name'],
-            robot_code=config['robot_code'],
-            markdown_card=config['markdown_card'],
-            logger=self.logger,
-        )
        await self.bot.start()

    async def kill(self) -> bool:
--- a/pkg/platform/sources/discord.py
+++ b/pkg/platform/sources/discord.py
@@ -8,15 +8,592 @@ import base64
 import uuid
 import os
 import datetime
+import io
+import asyncio
+from enum import Enum

 import aiohttp

 from .. import adapter
 from ...core import app
+from ..logger import EventLogger
 from ..types import message as platform_message
 from ..types import events as platform_events
 from ..types import entities as platform_entities
-from ..logger import EventLogger
+
+# 语音功能相关异常定义
+class VoiceConnectionError(Exception):
+    """语音连接基础异常"""
+    def __init__(self, message: str, error_code: str = None, guild_id: int = None):
+        super().__init__(message)
+        self.error_code = error_code
+        self.guild_id = guild_id
+        self.timestamp = datetime.datetime.now()
+
+
+class VoicePermissionError(VoiceConnectionError):
+    """语音权限异常"""
+    def __init__(self, message: str, missing_permissions: list = None, user_id: int = None, channel_id: int = None):
+        super().__init__(message, "PERMISSION_ERROR")
+        self.missing_permissions = missing_permissions or []
+        self.user_id = user_id
+        self.channel_id = channel_id
+
+
+class VoiceNetworkError(VoiceConnectionError):
+    """语音网络异常"""
+    def __init__(self, message: str, retry_count: int = 0):
+        super().__init__(message, "NETWORK_ERROR")
+        self.retry_count = retry_count
+        self.last_attempt = datetime.datetime.now()
+
+
+class VoiceConnectionStatus(Enum):
+    """语音连接状态枚举"""
+    IDLE = "idle"
+    CONNECTING = "connecting"
+    CONNECTED = "connected"
+    PLAYING = "playing"
+    RECONNECTING = "reconnecting"
+    FAILED = "failed"
+
+
+class VoiceConnectionInfo:
+    """
+    语音连接信息类
+    
+    用于存储和管理单个语音连接的详细信息，包括连接状态、时间戳、
+    频道信息等。提供连接信息的标准化数据结构。
+    
+    @author: @ydzat
+    @version: 1.0
+    @since: 2025-07-04
+    """
+    
+    def __init__(self, guild_id: int, channel_id: int, channel_name: str = None):
+        """
+        初始化语音连接信息
+        
+        @author: @ydzat
+        
+        Args:
+            guild_id (int): 服务器ID
+            channel_id (int): 语音频道ID
+            channel_name (str, optional): 语音频道名称
+        """
+        self.guild_id = guild_id
+        self.channel_id = channel_id
+        self.channel_name = channel_name or f"Channel-{channel_id}"
+        self.connected = False
+        self.connection_time: datetime.datetime = None
+        self.last_activity = datetime.datetime.now()
+        self.status = VoiceConnectionStatus.IDLE
+        self.user_count = 0
+        self.latency = 0.0
+        self.connection_health = "unknown"
+        self.voice_client = None
+        
+    def update_status(self, status: VoiceConnectionStatus):
+        """
+        更新连接状态
+        
+        @author: @ydzat
+        
+        Args:
+            status (VoiceConnectionStatus): 新的连接状态
+        """
+        self.status = status
+        self.last_activity = datetime.datetime.now()
+        
+        if status == VoiceConnectionStatus.CONNECTED:
+            self.connected = True
+            if self.connection_time is None:
+                self.connection_time = datetime.datetime.now()
+        elif status in [VoiceConnectionStatus.IDLE, VoiceConnectionStatus.FAILED]:
+            self.connected = False
+            self.connection_time = None
+            self.voice_client = None
+    
+    def to_dict(self) -> dict:
+        """
+        转换为字典格式
+        
+        @author: @ydzat
+        
+        Returns:
+            dict: 连接信息的字典表示
+        """
+        return {
+            "guild_id": self.guild_id,
+            "channel_id": self.channel_id,
+            "channel_name": self.channel_name,
+            "connected": self.connected,
+            "connection_time": self.connection_time.isoformat() if self.connection_time else None,
+            "last_activity": self.last_activity.isoformat(),
+            "status": self.status.value,
+            "user_count": self.user_count,
+            "latency": self.latency,
+            "connection_health": self.connection_health
+        }
+
+
+class VoiceConnectionManager:
+    """
+    语音连接管理器
+    
+    负责管理多个服务器的语音连接，提供连接建立、断开、状态查询等功能。
+    采用单例模式确保全局只有一个连接管理器实例。
+    
+    @author: @ydzat
+    @version: 1.0
+    @since: 2025-07-04
+    """
+    
+    def __init__(self, bot: discord.Client, logger: EventLogger):
+        """
+        初始化语音连接管理器
+        
+        @author: @ydzat
+        
+        Args:
+            bot (discord.Client): Discord 客户端实例
+            logger (EventLogger): 事件日志记录器
+        """
+        self.bot = bot
+        self.logger = logger
+        self.connections: typing.Dict[int, VoiceConnectionInfo] = {}
+        self._connection_lock = asyncio.Lock()
+        self._cleanup_task = None
+        self._monitoring_enabled = True
+        
+    async def join_voice_channel(self, guild_id: int, channel_id: int, 
+                                user_id: int = None) -> discord.VoiceClient:
+        """
+        加入语音频道
+        
+        验证用户权限和频道状态后，建立到指定语音频道的连接。
+        支持连接复用和自动重连机制。
+        
+        @author: @ydzat
+        
+        Args:
+            guild_id (int): 服务器ID
+            channel_id (int): 语音频道ID
+            user_id (int, optional): 请求用户ID，用于权限验证
+            
+        Returns:
+            discord.VoiceClient: 语音客户端实例
+            
+        Raises:
+            VoicePermissionError: 权限不足时抛出
+            VoiceNetworkError: 网络连接失败时抛出
+            VoiceConnectionError: 其他连接错误时抛出
+        """
+        async with self._connection_lock:
+            try:
+                # 获取服务器和频道对象
+                guild = self.bot.get_guild(guild_id)
+                if not guild:
+                    raise VoiceConnectionError(
+                        f"无法找到服务器 {guild_id}",
+                        "GUILD_NOT_FOUND",
+                        guild_id
+                    )
+                
+                channel = guild.get_channel(channel_id)
+                if not channel or not isinstance(channel, discord.VoiceChannel):
+                    raise VoiceConnectionError(
+                        f"无法找到语音频道 {channel_id}",
+                        "CHANNEL_NOT_FOUND",
+                        guild_id
+                    )
+                
+                # 验证用户是否在语音频道中（如果提供了用户ID）
+                if user_id:
+                    await self._validate_user_in_channel(guild, channel, user_id)
+                
+                # 验证机器人权限
+                await self._validate_bot_permissions(channel)
+                
+                # 检查是否已有连接
+                if guild_id in self.connections:
+                    existing_conn = self.connections[guild_id]
+                    if existing_conn.connected and existing_conn.voice_client:
+                        if existing_conn.channel_id == channel_id:
+                            # 已连接到相同频道，返回现有连接
+                            await self.logger.info(f"复用现有语音连接: {guild.name} -> {channel.name}")
+                            return existing_conn.voice_client
+                        else:
+                            # 连接到不同频道，先断开旧连接
+                            await self._disconnect_internal(guild_id)
+                
+                # 建立新连接
+                voice_client = await channel.connect()
+                
+                # 更新连接信息
+                conn_info = VoiceConnectionInfo(guild_id, channel_id, channel.name)
+                conn_info.voice_client = voice_client
+                conn_info.update_status(VoiceConnectionStatus.CONNECTED)
+                conn_info.user_count = len(channel.members)
+                self.connections[guild_id] = conn_info
+                
+                await self.logger.info(f"成功连接到语音频道: {guild.name} -> {channel.name}")
+                return voice_client
+                
+            except discord.ClientException as e:
+                raise VoiceNetworkError(f"Discord 客户端错误: {str(e)}")
+            except discord.opus.OpusNotLoaded as e:
+                raise VoiceConnectionError(f"Opus 编码器未加载: {str(e)}", "OPUS_NOT_LOADED", guild_id)
+            except Exception as e:
+                await self.logger.error(f"连接语音频道时发生未知错误: {str(e)}")
+                raise VoiceConnectionError(f"连接失败: {str(e)}", "UNKNOWN_ERROR", guild_id)
+    
+    async def leave_voice_channel(self, guild_id: int) -> bool:
+        """
+        离开语音频道
+        
+        断开指定服务器的语音连接，清理相关资源和状态信息。
+        确保音频播放停止后再断开连接。
+        
+        @author: @ydzat
+        
+        Args:
+            guild_id (int): 服务器ID
+            
+        Returns:
+            bool: 断开是否成功
+        """
+        async with self._connection_lock:
+            return await self._disconnect_internal(guild_id)
+    
+    async def _disconnect_internal(self, guild_id: int) -> bool:
+        """
+        内部断开连接方法
+        
+        @author: @ydzat
+        
+        Args:
+            guild_id (int): 服务器ID
+            
+        Returns:
+            bool: 断开是否成功
+        """
+        if guild_id not in self.connections:
+            return True
+        
+        conn_info = self.connections[guild_id]
+        
+        try:
+            if conn_info.voice_client and conn_info.voice_client.is_connected():
+                # 停止当前播放
+                if conn_info.voice_client.is_playing():
+                    conn_info.voice_client.stop()
+                
+                # 等待播放完全停止
+                await asyncio.sleep(0.1)
+                
+                # 断开连接
+                await conn_info.voice_client.disconnect()
+                
+            conn_info.update_status(VoiceConnectionStatus.IDLE)
+            del self.connections[guild_id]
+            
+            await self.logger.info(f"已断开语音连接: Guild {guild_id}")
+            return True
+            
+        except Exception as e:
+            await self.logger.error(f"断开语音连接时发生错误: {str(e)}")
+            # 即使出错也要清理连接记录
+            conn_info.update_status(VoiceConnectionStatus.FAILED)
+            if guild_id in self.connections:
+                del self.connections[guild_id]
+            return False
+    
+    async def get_voice_client(self, guild_id: int) -> typing.Optional[discord.VoiceClient]:
+        """
+        获取语音客户端
+        
+        返回指定服务器的语音客户端实例，如果未连接则返回 None。
+        会验证连接的有效性，自动清理无效连接。
+        
+        @author: @ydzat
+        
+        Args:
+            guild_id (int): 服务器ID
+            
+        Returns:
+            Optional[discord.VoiceClient]: 语音客户端实例或 None
+        """
+        if guild_id not in self.connections:
+            return None
+        
+        conn_info = self.connections[guild_id]
+        
+        # 验证连接是否仍然有效
+        if conn_info.voice_client and not conn_info.voice_client.is_connected():
+            # 连接已失效，清理状态
+            await self._disconnect_internal(guild_id)
+            return None
+        
+        return conn_info.voice_client if conn_info.connected else None
+    
+    async def is_connected_to_voice(self, guild_id: int) -> bool:
+        """
+        检查是否连接到语音频道
+        
+        @author: @ydzat
+        
+        Args:
+            guild_id (int): 服务器ID
+            
+        Returns:
+            bool: 是否已连接
+        """
+        if guild_id not in self.connections:
+            return False
+        
+        conn_info = self.connections[guild_id]
+        
+        # 检查实际连接状态
+        if conn_info.voice_client and not conn_info.voice_client.is_connected():
+            # 连接已失效，清理状态
+            await self._disconnect_internal(guild_id)
+            return False
+        
+        return conn_info.connected
+    
+    async def get_connection_status(self, guild_id: int) -> typing.Optional[dict]:
+        """
+        获取连接状态信息
+        
+        @author: @ydzat
+        
+        Args:
+            guild_id (int): 服务器ID
+            
+        Returns:
+            Optional[dict]: 连接状态信息字典或 None
+        """
+        if guild_id not in self.connections:
+            return None
+        
+        conn_info = self.connections[guild_id]
+        
+        # 更新实时信息
+        if conn_info.voice_client and conn_info.voice_client.is_connected():
+            conn_info.latency = conn_info.voice_client.latency * 1000  # 转换为毫秒
+            conn_info.connection_health = "good" if conn_info.latency < 100 else "poor"
+            
+            # 更新频道用户数
+            guild = self.bot.get_guild(guild_id)
+            if guild:
+                channel = guild.get_channel(conn_info.channel_id)
+                if channel and isinstance(channel, discord.VoiceChannel):
+                    conn_info.user_count = len(channel.members)
+        
+        return conn_info.to_dict()
+    
+    async def list_active_connections(self) -> typing.List[dict]:
+        """
+        列出所有活跃连接
+        
+        @author: @ydzat
+        
+        Returns:
+            List[dict]: 活跃连接列表
+        """
+        active_connections = []
+        
+        for guild_id, conn_info in self.connections.items():
+            if conn_info.connected:
+                status = await self.get_connection_status(guild_id)
+                if status:
+                    active_connections.append(status)
+        
+        return active_connections
+    
+    async def get_voice_channel_info(self, guild_id: int, channel_id: int) -> typing.Optional[dict]:
+        """
+        获取语音频道信息
+        
+        @author: @ydzat
+        
+        Args:
+            guild_id (int): 服务器ID
+            channel_id (int): 频道ID
+            
+        Returns:
+            Optional[dict]: 频道信息字典或 None
+        """
+        guild = self.bot.get_guild(guild_id)
+        if not guild:
+            return None
+        
+        channel = guild.get_channel(channel_id)
+        if not channel or not isinstance(channel, discord.VoiceChannel):
+            return None
+        
+        # 获取用户信息
+        users = []
+        for member in channel.members:
+            users.append({
+                "id": member.id,
+                "name": member.display_name,
+                "status": str(member.status),
+                "is_bot": member.bot
+            })
+        
+        # 获取权限信息
+        bot_member = guild.me
+        permissions = channel.permissions_for(bot_member)
+        
+        return {
+            "channel_id": channel_id,
+            "channel_name": channel.name,
+            "guild_id": guild_id,
+            "guild_name": guild.name,
+            "user_limit": channel.user_limit,
+            "current_users": users,
+            "user_count": len(users),
+            "bitrate": channel.bitrate,
+            "permissions": {
+                "connect": permissions.connect,
+                "speak": permissions.speak,
+                "use_voice_activation": permissions.use_voice_activation,
+                "priority_speaker": permissions.priority_speaker
+            }
+        }
+    
+    async def _validate_user_in_channel(self, guild: discord.Guild, 
+                                       channel: discord.VoiceChannel, user_id: int):
+        """
+        验证用户是否在语音频道中
+        
+        @author: @ydzat
+        
+        Args:
+            guild: Discord 服务器对象
+            channel: 语音频道对象
+            user_id: 用户ID
+            
+        Raises:
+            VoicePermissionError: 用户不在频道中时抛出
+        """
+        member = guild.get_member(user_id)
+        if not member:
+            raise VoicePermissionError(
+                f"无法找到用户 {user_id}",
+                ["member_not_found"],
+                user_id,
+                channel.id
+            )
+        
+        if not member.voice or member.voice.channel != channel:
+            raise VoicePermissionError(
+                f"用户 {member.display_name} 不在语音频道 {channel.name} 中",
+                ["user_not_in_channel"],
+                user_id,
+                channel.id
+            )
+    
+    async def _validate_bot_permissions(self, channel: discord.VoiceChannel):
+        """
+        验证机器人权限
+        
+        @author: @ydzat
+        
+        Args:
+            channel: 语音频道对象
+            
+        Raises:
+            VoicePermissionError: 权限不足时抛出
+        """
+        bot_member = channel.guild.me
+        permissions = channel.permissions_for(bot_member)
+        
+        missing_permissions = []
+        
+        if not permissions.connect:
+            missing_permissions.append("connect")
+        if not permissions.speak:
+            missing_permissions.append("speak")
+        
+        if missing_permissions:
+            raise VoicePermissionError(
+                f"机器人在频道 {channel.name} 中缺少权限: {', '.join(missing_permissions)}",
+                missing_permissions,
+                channel_id=channel.id
+            )
+    
+    async def cleanup_inactive_connections(self):
+        """
+        清理无效连接
+        
+        定期检查并清理已断开或无效的语音连接，释放资源。
+        
+        @author: @ydzat
+        """
+        cleanup_guilds = []
+        
+        for guild_id, conn_info in self.connections.items():
+            if not conn_info.voice_client or not conn_info.voice_client.is_connected():
+                cleanup_guilds.append(guild_id)
+        
+        for guild_id in cleanup_guilds:
+            await self._disconnect_internal(guild_id)
+        
+        if cleanup_guilds:
+            await self.logger.info(f"清理了 {len(cleanup_guilds)} 个无效的语音连接")
+    
+    async def start_monitoring(self):
+        """
+        开始连接监控
+        
+        @author: @ydzat
+        """
+        if self._cleanup_task is None and self._monitoring_enabled:
+            self._cleanup_task = asyncio.create_task(self._monitoring_loop())
+    
+    async def stop_monitoring(self):
+        """
+        停止连接监控
+        
+        @author: @ydzat
+        """
+        self._monitoring_enabled = False
+        if self._cleanup_task:
+            self._cleanup_task.cancel()
+            try:
+                await self._cleanup_task
+            except asyncio.CancelledError:
+                pass
+            self._cleanup_task = None
+    
+    async def _monitoring_loop(self):
+        """
+        监控循环
+        
+        @author: @ydzat
+        """
+        try:
+            while self._monitoring_enabled:
+                await asyncio.sleep(60)  # 每分钟检查一次
+                await self.cleanup_inactive_connections()
+        except asyncio.CancelledError:
+            pass
+    
+    async def disconnect_all(self):
+        """
+        断开所有连接
+        
+        @author: @ydzat
+        """
+        async with self._connection_lock:
+            guild_ids = list(self.connections.keys())
+            for guild_id in guild_ids:
+                await self._disconnect_internal(guild_id)
+        
+        await self.stop_monitoring()


 class DiscordMessageConverter(adapter.MessageConverter):
@@ -238,6 +815,9 @@ class DiscordAdapter(adapter.MessagePlatformAdapter):
        self.logger = logger

        self.bot_account_id = self.config['client_id']
+        
+        # 初始化语音连接管理器
+        self.voice_manager: VoiceConnectionManager = None

        adapter_self = self

@@ -258,6 +838,169 @@ class DiscordAdapter(adapter.MessagePlatformAdapter):
            args['proxy'] = os.getenv('http_proxy')

        self.bot = MyClient(intents=intents, **args)
+    
+    # Voice functionality methods
+    async def join_voice_channel(self, guild_id: int, channel_id: int, 
+                                user_id: int = None) -> discord.VoiceClient:
+        """
+        加入语音频道
+        
+        为指定服务器的语音频道建立连接，支持用户权限验证和连接复用。
+        
+        @author: @ydzat
+        @version: 1.0
+        @since: 2025-07-04
+        
+        Args:
+            guild_id (int): Discord 服务器ID
+            channel_id (int): 语音频道ID
+            user_id (int, optional): 请求用户ID，用于权限验证
+            
+        Returns:
+            discord.VoiceClient: 语音客户端实例
+            
+        Raises:
+            VoicePermissionError: 权限不足
+            VoiceNetworkError: 网络连接失败
+            VoiceConnectionError: 其他连接错误
+        """
+        if not self.voice_manager:
+            raise VoiceConnectionError("语音管理器未初始化", "MANAGER_NOT_READY")
+        
+        return await self.voice_manager.join_voice_channel(guild_id, channel_id, user_id)
+    
+    async def leave_voice_channel(self, guild_id: int) -> bool:
+        """
+        离开语音频道
+        
+        断开指定服务器的语音连接，清理相关资源。
+        
+        @author: @ydzat
+        @version: 1.0
+        @since: 2025-07-04
+        
+        Args:
+            guild_id (int): Discord 服务器ID
+            
+        Returns:
+            bool: 是否成功断开连接
+        """
+        if not self.voice_manager:
+            return False
+        
+        return await self.voice_manager.leave_voice_channel(guild_id)
+    
+    async def get_voice_client(self, guild_id: int) -> typing.Optional[discord.VoiceClient]:
+        """
+        获取语音客户端
+        
+        返回指定服务器的语音客户端实例，用于音频播放控制。
+        
+        @author: @ydzat
+        @version: 1.0
+        @since: 2025-07-04
+        
+        Args:
+            guild_id (int): Discord 服务器ID
+            
+        Returns:
+            Optional[discord.VoiceClient]: 语音客户端实例或 None
+        """
+        if not self.voice_manager:
+            return None
+        
+        return await self.voice_manager.get_voice_client(guild_id)
+    
+    async def is_connected_to_voice(self, guild_id: int) -> bool:
+        """
+        检查语音连接状态
+        
+        @author: @ydzat
+        @version: 1.0
+        @since: 2025-07-04
+        
+        Args:
+            guild_id (int): Discord 服务器ID
+            
+        Returns:
+            bool: 是否已连接到语音频道
+        """
+        if not self.voice_manager:
+            return False
+        
+        return await self.voice_manager.is_connected_to_voice(guild_id)
+    
+    async def get_voice_connection_status(self, guild_id: int) -> typing.Optional[dict]:
+        """
+        获取语音连接详细状态
+        
+        返回包含连接时间、延迟、用户数等详细信息的状态字典。
+        
+        @author: @ydzat
+        @version: 1.0
+        @since: 2025-07-04
+        
+        Args:
+            guild_id (int): Discord 服务器ID
+            
+        Returns:
+            Optional[dict]: 连接状态信息或 None
+        """
+        if not self.voice_manager:
+            return None
+        
+        return await self.voice_manager.get_connection_status(guild_id)
+    
+    async def list_active_voice_connections(self) -> typing.List[dict]:
+        """
+        列出所有活跃的语音连接
+        
+        @author: @ydzat
+        @version: 1.0
+        @since: 2025-07-04
+        
+        Returns:
+            List[dict]: 活跃语音连接列表
+        """
+        if not self.voice_manager:
+            return []
+        
+        return await self.voice_manager.list_active_connections()
+    
+    async def get_voice_channel_info(self, guild_id: int, channel_id: int) -> typing.Optional[dict]:
+        """
+        获取语音频道详细信息
+        
+        包括频道名称、用户列表、权限信息等。
+        
+        @author: @ydzat
+        @version: 1.0
+        @since: 2025-07-04
+        
+        Args:
+            guild_id (int): Discord 服务器ID
+            channel_id (int): 语音频道ID
+            
+        Returns:
+            Optional[dict]: 频道信息字典或 None
+        """
+        if not self.voice_manager:
+            return None
+        
+        return await self.voice_manager.get_voice_channel_info(guild_id, channel_id)
+    
+    async def cleanup_voice_connections(self):
+        """
+        清理无效的语音连接
+        
+        手动触发语音连接清理，移除已断开或无效的连接。
+        
+        @author: @ydzat
+        @version: 1.0
+        @since: 2025-07-04
+        """
+        if self.voice_manager:
+            await self.voice_manager.cleanup_inactive_connections()

    async def send_message(self, target_type: str, target_id: str, message: platform_message.MessageChain):
        msg_to_send, image_files = await self.message_converter.yiri2target(message)
@@ -324,9 +1067,32 @@ class DiscordAdapter(adapter.MessagePlatformAdapter):
        self.listeners.pop(event_type)

    async def run_async(self):
+        """
+        启动 Discord 适配器
+        
+        初始化语音管理器并启动 Discord 客户端连接。
+        
+        @author: @ydzat (修改)
+        """
        async with self.bot:
+            # 初始化语音管理器
+            self.voice_manager = VoiceConnectionManager(self.bot, self.logger)
+            await self.voice_manager.start_monitoring()
+            
+            await self.logger.info("Discord 适配器语音功能已启用")
            await self.bot.start(self.config['token'], reconnect=True)

    async def kill(self) -> bool:
+        """
+        关闭 Discord 适配器
+        
+        清理语音连接并关闭 Discord 客户端。
+        
+        @author: @ydzat (修改)
+        """
+        if self.voice_manager:
+            await self.voice_manager.disconnect_all()
+        
        await self.bot.close()
        return True
+
--- a/pkg/platform/sources/wechatpad.py
+++ b/pkg/platform/sources/wechatpad.py
@@ -29,18 +29,21 @@ import logging


 class WeChatPadMessageConverter(adapter.MessageConverter):
-    def __init__(self, config: dict):
+
+    def __init__(self, config: dict, logger: logging.Logger):
        self.config = config
-        self.bot = WeChatPadClient(self.config['wechatpad_url'], self.config['token'])
-        self.logger = logging.getLogger('WeChatPadMessageConverter')
+        self.bot = WeChatPadClient(self.config["wechatpad_url"],self.config["token"])
+        self.logger = logger

    @staticmethod
    async def yiri2target(message_chain: platform_message.MessageChain) -> list[dict]:
        content_list = []

        for component in message_chain:
-            if isinstance(component, platform_message.At):
-                content_list.append({'type': 'at', 'target': component.target})
+            if isinstance(component, platform_message.AtAll):
+                content_list.append({"type": "at", "target": "all"})
+            elif isinstance(component, platform_message.At):
+                content_list.append({"type": "at", "target": component.target})
            elif isinstance(component, platform_message.Plain):
                content_list.append({'type': 'text', 'content': component.text})
            elif isinstance(component, platform_message.Image):
@@ -73,20 +76,34 @@ class WeChatPadMessageConverter(adapter.MessageConverter):

        return content_list

-    async def target2yiri(self, message: dict, bot_account_id: str) -> platform_message.MessageChain:
+    async def target2yiri(
+            self,
+            message: dict,
+            bot_account_id: str,
+    ) -> platform_message.MessageChain:
        """外部消息转平台消息"""
        # 数据预处理
        message_list = []
+        bot_wxid = self.config['wxid']
        ats_bot = False  # 是否被@
        content = message['content']['str']
        content_no_preifx = content  # 群消息则去掉前缀
        is_group_message = self._is_group_message(message)
        if is_group_message:
            ats_bot = self._ats_bot(message, bot_account_id)
-            if '@所有人' in content:
+
+            self.logger.info(f"ats_bot: {ats_bot}; bot_account_id: {bot_account_id}; bot_wxid: {bot_wxid}")
+            if "@所有人" in content:
                message_list.append(platform_message.AtAll())
-            elif ats_bot:
+            if ats_bot:
                message_list.append(platform_message.At(target=bot_account_id))
+            
+            # 解析@信息并生成At组件
+            at_targets = self._extract_at_targets(message)
+            for target_id in at_targets:
+                if target_id != bot_wxid:  # 避免重复添加机器人的At
+                    message_list.append(platform_message.At(target=target_id))
+            
            content_no_preifx, _ = self._extract_content_and_sender(content)

        msg_type = message['msg_type']
@@ -395,6 +412,23 @@ class WeChatPadMessageConverter(adapter.MessageConverter):
        finally:
            return ats_bot

+    # 提取一下at的wxid列表
+    def _extract_at_targets(self, message: dict) -> list[str]:
+        """从消息中提取被@用户的ID列表"""
+        at_targets = []
+        try:
+            # 从msg_source中解析atuserlist
+            msg_source = message.get('msg_source', '') or ''
+            if len(msg_source) > 0:
+                msg_source_data = ET.fromstring(msg_source)
+                at_user_list = msg_source_data.findtext("atuserlist") or ""
+                if at_user_list:
+                    # atuserlist格式通常是逗号分隔的用户ID列表
+                    at_targets = [user_id.strip() for user_id in at_user_list.split(',') if user_id.strip()]
+        except Exception as e:
+            self.logger.error(f"_extract_at_targets got except: {e}")
+        return at_targets
+    
    # 提取一下content前面的sender_id, 和去掉前缀的内容
    def _extract_content_and_sender(self, raw_content: str) -> Tuple[str, Optional[str]]:
        try:
@@ -418,16 +452,22 @@ class WeChatPadMessageConverter(adapter.MessageConverter):


 class WeChatPadEventConverter(adapter.EventConverter):
-    def __init__(self, config: dict):
-        self.config = config
-        self.message_converter = WeChatPadMessageConverter(config)
-        self.logger = logging.getLogger('WeChatPadEventConverter')

+    def __init__(self, config: dict, logger: logging.Logger):
+        self.config = config
+        self.message_converter = WeChatPadMessageConverter(config, logger)
+        self.logger = logger
+        
    @staticmethod
    async def yiri2target(event: platform_events.MessageEvent) -> dict:
        pass

-    async def target2yiri(self, event: dict, bot_account_id: str) -> platform_events.MessageEvent:
+    async def target2yiri(
+            self,
+            event: dict,
+            bot_account_id: str,
+    ) -> platform_events.MessageEvent:
+
        # 排除公众号以及微信团队消息
        if (
            event['from_user_name']['str'].startswith('gh_')
@@ -503,8 +543,8 @@ class WeChatPadAdapter(adapter.MessagePlatformAdapter):
        self.logger = logger
        self.quart_app = quart.Quart(__name__)

-        self.message_converter = WeChatPadMessageConverter(config)
-        self.event_converter = WeChatPadEventConverter(config)
+        self.message_converter = WeChatPadMessageConverter(config, ap.logger)
+        self.event_converter = WeChatPadEventConverter(config, ap.logger)

    async def ws_message(self, data):
        """处理接收到的消息"""
@@ -539,19 +579,26 @@ class WeChatPadAdapter(adapter.MessagePlatformAdapter):
        for msg in content_list:
            # 文本消息处理@
            if msg['type'] == 'text' and at_targets:
-                at_nick_name_list = []
-                for member in member_info:
-                    if member['user_name'] in at_targets:
-                        at_nick_name_list.append(f'@{member["nick_name"]}')
-                msg['content'] = f'{" ".join(at_nick_name_list)} {msg["content"]}'
+                if "all" in at_targets:
+                    msg['content'] = f'@所有人 {msg["content"]}'
+                else:
+                    at_nick_name_list = []
+                    for member in member_info:
+                        if member["user_name"] in at_targets:
+                            at_nick_name_list.append(f'@{member["nick_name"]}')
+                    msg['content'] = f'{" ".join(at_nick_name_list)} {msg["content"]}'

            # 统一消息派发
            handler_map = {
                'text': lambda msg: self.bot.send_text_message(
-                    to_wxid=target_id, message=msg['content'], ats=at_targets
+                    to_wxid=target_id,
+                    message=msg['content'],
+                    ats= ["notify@all"] if "all" in at_targets else at_targets
                ),
                'image': lambda msg: self.bot.send_image_message(
-                    to_wxid=target_id, img_url=msg['image'], ats=at_targets
+                    to_wxid=target_id,
+                    img_url=msg["image"],
+                    ats = ["notify@all"] if "all" in at_targets else at_targets
                ),
                'WeChatEmoji': lambda msg: self.bot.send_emoji_message(
                    to_wxid=target_id, emoji_md5=msg['emoji_md5'], emoji_size=msg['emoji_size']
--- a/pkg/provider/modelmgr/requester.py
+++ b/pkg/provider/modelmgr/requester.py
@@ -101,18 +101,18 @@ class ProviderAPIRequester(metaclass=abc.ABCMeta):
    async def invoke_embedding(
        self,
        model: RuntimeEmbeddingModel,
-        input_text: str,
+        input_text: list[str],
        extra_args: dict[str, typing.Any] = {},
-    ) -> list[float]:
+    ) -> list[list[float]]:
        """调用 Embedding API

        Args:
            query (core_entities.Query): 请求上下文
            model (RuntimeEmbeddingModel): 使用的模型信息
-            input_text (str): 输入文本
+            input_text (list[str]): 输入文本
            extra_args (dict[str, typing.Any], optional): 额外的参数. Defaults to {}.

        Returns:
-            list[float]: 返回的 embedding 向量
+            list[list[float]]: 返回的 embedding 向量
        """
        pass
--- a/pkg/provider/modelmgr/requesters/302aichatcmpl.py
+++ b/pkg/provider/modelmgr/requesters/302aichatcmpl.py
@@ -7,7 +7,7 @@ from . import chatcmpl


 class AI302ChatCompletions(chatcmpl.OpenAIChatCompletions):
-    """302 AI ChatCompletion API 请求器"""
+    """302.AI ChatCompletion API 请求器"""

    client: openai.AsyncClient

--- a/pkg/provider/modelmgr/requesters/chatcmpl.py
+++ b/pkg/provider/modelmgr/requesters/chatcmpl.py
@@ -145,9 +145,9 @@ class OpenAIChatCompletions(requester.ProviderAPIRequester):
    async def invoke_embedding(
        self,
        model: requester.RuntimeEmbeddingModel,
-        input_text: str,
+        input_text: list[str],
        extra_args: dict[str, typing.Any] = {},
-    ) -> list[float]:
+    ) -> list[list[float]]:
        """调用 Embedding API"""
        self.client.api_key = model.token_mgr.get_token()

@@ -163,7 +163,8 @@ class OpenAIChatCompletions(requester.ProviderAPIRequester):

        try:
            resp = await self.client.embeddings.create(**args)
-            return resp.data[0].embedding
+
+            return [d.embedding for d in resp.data]
        except asyncio.TimeoutError:
            raise errors.RequesterError('请求超时')
        except openai.BadRequestError as e:
--- a/pkg/provider/runners/localagent.py
+++ b/pkg/provider/runners/localagent.py
@@ -1,13 +1,28 @@
 from __future__ import annotations

 import json
+import copy
 import typing
-
 from .. import runner
 from ...core import entities as core_entities
 from .. import entities as llm_entities


+rag_combined_prompt_template = """
+The following are relevant context entries retrieved from the knowledge base. 
+Please use them to answer the user's message. 
+Respond in the same language as the user's input.
+
+<context>
+{rag_context}
+</context>
+
+<user_message>
+{user_message}
+</user_message>
+"""
+
+
@runner.runner_class('local-agent')
 class LocalAgentRunner(runner.RequestRunner):
    """本地Agent请求运行器"""
@@ -16,7 +31,54 @@ class LocalAgentRunner(runner.RequestRunner):
        """运行请求"""
        pending_tool_calls = []

-        req_messages = query.prompt.messages.copy() + query.messages.copy() + [query.user_message]
+        kb_uuid = query.pipeline_config['ai']['local-agent']['knowledge-base']
+
+        if kb_uuid == '__none__':
+            kb_uuid = None
+
+        user_message = copy.deepcopy(query.user_message)
+
+        user_message_text = ''
+
+        if isinstance(user_message.content, str):
+            user_message_text = user_message.content
+        elif isinstance(user_message.content, list):
+            for ce in user_message.content:
+                if ce.type == 'text':
+                    user_message_text += ce.text
+                    break
+
+        if kb_uuid and user_message_text:
+            # only support text for now
+            kb = await self.ap.rag_mgr.get_knowledge_base_by_uuid(kb_uuid)
+
+            if not kb:
+                self.ap.logger.warning(f'Knowledge base {kb_uuid} not found')
+                raise ValueError(f'Knowledge base {kb_uuid} not found')
+
+            result = await kb.retrieve(user_message_text)
+
+            final_user_message_text = ''
+
+            if result:
+                rag_context = '\n\n'.join(
+                    f'[{i + 1}] {entry.metadata.get("text", "")}' for i, entry in enumerate(result)
+                )
+                final_user_message_text = rag_combined_prompt_template.format(
+                    rag_context=rag_context, user_message=user_message_text
+                )
+
+            else:
+                final_user_message_text = user_message_text
+
+            self.ap.logger.debug(f'Final user message text: {final_user_message_text}')
+
+            for ce in user_message.content:
+                if ce.type == 'text':
+                    ce.text = final_user_message_text
+                    break
+
+        req_messages = query.prompt.messages.copy() + query.messages.copy() + [user_message]

        # 首次请求
        msg = await query.use_llm_model.requester.invoke_llm(
--- a/pkg/rag/knowledge/kbmgr.py
+++ b/pkg/rag/knowledge/kbmgr.py
@@ -0,0 +1,212 @@
+from __future__ import annotations
+import traceback
+import uuid
+from .services import parser, chunker
+from pkg.core import app
+from pkg.rag.knowledge.services.embedder import Embedder
+from pkg.rag.knowledge.services.retriever import Retriever
+import sqlalchemy
+from ...entity.persistence import rag as persistence_rag
+from pkg.core import taskmgr
+from ...entity.rag import retriever as retriever_entities
+
+
+class RuntimeKnowledgeBase:
+    ap: app.Application
+
+    knowledge_base_entity: persistence_rag.KnowledgeBase
+
+    parser: parser.FileParser
+
+    chunker: chunker.Chunker
+
+    embedder: Embedder
+
+    retriever: Retriever
+
+    def __init__(self, ap: app.Application, knowledge_base_entity: persistence_rag.KnowledgeBase):
+        self.ap = ap
+        self.knowledge_base_entity = knowledge_base_entity
+        self.parser = parser.FileParser(ap=self.ap)
+        self.chunker = chunker.Chunker(ap=self.ap)
+        self.embedder = Embedder(ap=self.ap)
+        self.retriever = Retriever(ap=self.ap)
+        # 传递kb_id给retriever
+        self.retriever.kb_id = knowledge_base_entity.uuid
+
+    async def initialize(self):
+        pass
+
+    async def _store_file_task(self, file: persistence_rag.File, task_context: taskmgr.TaskContext):
+        try:
+            # set file status to processing
+            await self.ap.persistence_mgr.execute_async(
+                sqlalchemy.update(persistence_rag.File)
+                .where(persistence_rag.File.uuid == file.uuid)
+                .values(status='processing')
+            )
+
+            task_context.set_current_action('Parsing file')
+            # parse file
+            text = await self.parser.parse(file.file_name, file.extension)
+            if not text:
+                raise Exception(f'No text extracted from file {file.file_name}')
+
+            task_context.set_current_action('Chunking file')
+            # chunk file
+            chunks_texts = await self.chunker.chunk(text)
+            if not chunks_texts:
+                raise Exception(f'No chunks extracted from file {file.file_name}')
+
+            task_context.set_current_action('Embedding chunks')
+
+            embedding_model = await self.ap.model_mgr.get_embedding_model_by_uuid(
+                self.knowledge_base_entity.embedding_model_uuid
+            )
+            # embed chunks
+            await self.embedder.embed_and_store(
+                kb_id=self.knowledge_base_entity.uuid,
+                file_id=file.uuid,
+                chunks=chunks_texts,
+                embedding_model=embedding_model,
+            )
+
+            # set file status to completed
+            await self.ap.persistence_mgr.execute_async(
+                sqlalchemy.update(persistence_rag.File)
+                .where(persistence_rag.File.uuid == file.uuid)
+                .values(status='completed')
+            )
+
+        except Exception as e:
+            self.ap.logger.error(f'Error storing file {file.uuid}: {e}')
+            traceback.print_exc()
+            # set file status to failed
+            await self.ap.persistence_mgr.execute_async(
+                sqlalchemy.update(persistence_rag.File)
+                .where(persistence_rag.File.uuid == file.uuid)
+                .values(status='failed')
+            )
+
+            raise
+
+    async def store_file(self, file_id: str) -> str:
+        # pre checking
+        if not await self.ap.storage_mgr.storage_provider.exists(file_id):
+            raise Exception(f'File {file_id} not found')
+
+        file_uuid = str(uuid.uuid4())
+        kb_id = self.knowledge_base_entity.uuid
+        file_name = file_id
+        extension = file_name.split('.')[-1]
+
+        file_obj_data = {
+            'uuid': file_uuid,
+            'kb_id': kb_id,
+            'file_name': file_name,
+            'extension': extension,
+            'status': 'pending',
+        }
+
+        file_obj = persistence_rag.File(**file_obj_data)
+
+        await self.ap.persistence_mgr.execute_async(sqlalchemy.insert(persistence_rag.File).values(file_obj_data))
+
+        # run background task asynchronously
+        ctx = taskmgr.TaskContext.new()
+        wrapper = self.ap.task_mgr.create_user_task(
+            self._store_file_task(file_obj, task_context=ctx),
+            kind='knowledge-operation',
+            name=f'knowledge-store-file-{file_id}',
+            label=f'Store file {file_id}',
+            context=ctx,
+        )
+        return wrapper.id
+
+    async def retrieve(self, query: str) -> list[retriever_entities.RetrieveResultEntry]:
+        embedding_model = await self.ap.model_mgr.get_embedding_model_by_uuid(
+            self.knowledge_base_entity.embedding_model_uuid
+        )
+        return await self.retriever.retrieve(self.knowledge_base_entity.uuid, query, embedding_model)
+
+    async def delete_file(self, file_id: str):
+        # delete vector
+        await self.ap.vector_db_mgr.vector_db.delete_by_file_id(self.knowledge_base_entity.uuid, file_id)
+
+        # delete chunk
+        await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.delete(persistence_rag.Chunk).where(persistence_rag.Chunk.file_id == file_id)
+        )
+
+        await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.delete(persistence_rag.File).where(persistence_rag.File.uuid == file_id)
+        )
+
+    async def dispose(self):
+        await self.ap.vector_db_mgr.vector_db.delete_collection(self.knowledge_base_entity.uuid)
+
+
+class RAGManager:
+    ap: app.Application
+
+    knowledge_bases: list[RuntimeKnowledgeBase]
+
+    def __init__(self, ap: app.Application):
+        self.ap = ap
+        self.knowledge_bases = []
+
+    async def initialize(self):
+        await self.load_knowledge_bases_from_db()
+
+    async def load_knowledge_bases_from_db(self):
+        self.ap.logger.info('Loading knowledge bases from db...')
+
+        self.knowledge_bases = []
+
+        result = await self.ap.persistence_mgr.execute_async(sqlalchemy.select(persistence_rag.KnowledgeBase))
+
+        knowledge_bases = result.all()
+
+        for knowledge_base in knowledge_bases:
+            try:
+                await self.load_knowledge_base(knowledge_base)
+            except Exception as e:
+                self.ap.logger.error(
+                    f'Error loading knowledge base {knowledge_base.uuid}: {e}\n{traceback.format_exc()}'
+                )
+
+    async def load_knowledge_base(
+        self,
+        knowledge_base_entity: persistence_rag.KnowledgeBase | sqlalchemy.Row | dict,
+    ) -> RuntimeKnowledgeBase:
+        if isinstance(knowledge_base_entity, sqlalchemy.Row):
+            knowledge_base_entity = persistence_rag.KnowledgeBase(**knowledge_base_entity._mapping)
+        elif isinstance(knowledge_base_entity, dict):
+            knowledge_base_entity = persistence_rag.KnowledgeBase(**knowledge_base_entity)
+
+        runtime_knowledge_base = RuntimeKnowledgeBase(ap=self.ap, knowledge_base_entity=knowledge_base_entity)
+
+        await runtime_knowledge_base.initialize()
+
+        self.knowledge_bases.append(runtime_knowledge_base)
+
+        return runtime_knowledge_base
+
+    async def get_knowledge_base_by_uuid(self, kb_uuid: str) -> RuntimeKnowledgeBase | None:
+        for kb in self.knowledge_bases:
+            if kb.knowledge_base_entity.uuid == kb_uuid:
+                return kb
+        return None
+
+    async def remove_knowledge_base_from_runtime(self, kb_uuid: str):
+        for kb in self.knowledge_bases:
+            if kb.knowledge_base_entity.uuid == kb_uuid:
+                self.knowledge_bases.remove(kb)
+                return
+
+    async def delete_knowledge_base(self, kb_uuid: str):
+        for kb in self.knowledge_bases:
+            if kb.knowledge_base_entity.uuid == kb_uuid:
+                await kb.dispose()
+                self.knowledge_bases.remove(kb)
+                return
--- a/pkg/rag/knowledge/mgr.py
+++ b/pkg/rag/knowledge/mgr.py
@@ -1,408 +0,0 @@
-from __future__ import annotations
-import os
-import asyncio
-import traceback
-import uuid
-from pkg.rag.knowledge.services.parser import FileParser
-from pkg.rag.knowledge.services.chunker import Chunker
-from pkg.rag.knowledge.services.database import (
-    KnowledgeBase,
-    File,
-    Chunk,
-)
-from pkg.core import app
-from pkg.rag.knowledge.services.embedder import Embedder
-from pkg.rag.knowledge.services.retriever import Retriever
-from pkg.rag.knowledge.services.chroma_manager import ChromaIndexManager
-from pkg.core import taskmgr
-from ...entity.persistence import rag as persistence_rag
-import sqlalchemy
-
-
-class RuntimeKnowledgeBase:
-    ap: app.Application
-
-    knowledge_base_entity: persistence_rag.KnowledgeBase
-
-    chroma_manager: ChromaIndexManager
-
-    parser: FileParser
-
-    chunker: Chunker
-
-    embedder: Embedder
-
-    retriever: Retriever
-
-    def __init__(self, ap: app.Application, knowledge_base_entity: persistence_rag.KnowledgeBase):
-        self.ap = ap
-        self.knowledge_base_entity = knowledge_base_entity
-        self.chroma_manager = ChromaIndexManager(ap=self.ap)
-        self.parser = FileParser(ap=self.ap)
-        self.chunker = Chunker(ap=self.ap)
-        self.embedder = Embedder(ap=self.ap, chroma_manager=self.chroma_manager)
-        self.retriever = Retriever(ap=self.ap, chroma_manager=self.chroma_manager)
-
-    async def initialize(self):
-        pass
-
-    async def _store_file_task(self, file: persistence_rag.File, task_context: taskmgr.TaskContext):
-        try:
-            # set file status to processing
-            await self.ap.persistence_mgr.execute_async(
-                sqlalchemy.update(persistence_rag.File)
-                .where(persistence_rag.File.uuid == file.uuid)
-                .values(status='processing')
-            )
-
-            task_context.set_current_action('Parsing file')
-            # parse file
-            text = await self.parser.parse(file.file_name, file.extension)
-            if not text:
-                raise Exception(f'No text extracted from file {file.file_name}')
-
-            task_context.set_current_action('Chunking file')
-            # chunk file
-            chunks_texts = await self.chunker.chunk(text)
-            if not chunks_texts:
-                raise Exception(f'No chunks extracted from file {file.file_name}')
-
-            task_context.set_current_action('Embedding chunks')
-            # embed chunks
-            await self.embedder.embed_and_store(
-                file_id=file.uuid, chunks=chunks_texts, embedding_model=self.knowledge_base_entity.embedding_model_uuid
-            )
-
-            # set file status to completed
-            await self.ap.persistence_mgr.execute_async(
-                sqlalchemy.update(persistence_rag.File)
-                .where(persistence_rag.File.uuid == file.uuid)
-                .values(status='completed')
-            )
-
-        except Exception as e:
-            self.ap.logger.error(f'Error storing file {file.file_id}: {e}')
-            # set file status to failed
-            await self.ap.persistence_mgr.execute_async(
-                sqlalchemy.update(persistence_rag.File)
-                .where(persistence_rag.File.uuid == file.uuid)
-                .values(status='failed')
-            )
-
-            raise
-
-    async def store_file(self, file_id: str) -> int:
-        # pre checking
-        if not await self.ap.storage_mgr.storage_provider.exists(file_id):
-            raise Exception(f'File {file_id} not found')
-
-        file_uuid = str(uuid.uuid4())
-        kb_id = self.knowledge_base_entity.uuid
-        file_name = file_id
-        extension = os.path.splitext(file_id)[1].lstrip('.')
-
-        file = persistence_rag.File(
-            uuid=file_uuid,
-            kb_id=kb_id,
-            file_name=file_name,
-            extension=extension,
-            status='pending',
-        )
-
-        await self.ap.persistence_mgr.execute_async(sqlalchemy.insert(persistence_rag.File).values(**file.to_dict()))
-
-        # run background task asynchronously
-        ctx = taskmgr.TaskContext.new()
-        wrapper = self.ap.task_mgr.create_user_task(
-            self._store_file_task(file, task_context=ctx),
-            kind='knowledge-operation',
-            name=f'knowledge-store-file-{file_id}',
-            label=f'Store file {file_id}',
-            context=ctx,
-        )
-        return wrapper.id
-
-    async def dispose(self):
-        pass
-
-
-class RAGManager:
-    ap: app.Application
-
-    knowledge_bases: list[RuntimeKnowledgeBase]
-
-    def __init__(self, ap: app.Application):
-        self.ap = ap
-        self.knowledge_bases = []
-
-    async def initialize(self):
-        pass
-
-    async def load_knowledge_bases_from_db(self):
-        self.ap.logger.info('Loading knowledge bases from db...')
-
-        self.knowledge_bases = []
-
-        result = await self.ap.persistence_mgr.execute_async(sqlalchemy.select(persistence_rag.KnowledgeBase))
-
-        knowledge_bases = result.all()
-
-        for knowledge_base in knowledge_bases:
-            try:
-                await self.load_knowledge_base(knowledge_base)
-            except Exception as e:
-                self.ap.logger.error(
-                    f'Error loading knowledge base {knowledge_base.uuid}: {e}\n{traceback.format_exc()}'
-                )
-
-    async def load_knowledge_base(
-        self,
-        knowledge_base_entity: persistence_rag.KnowledgeBase | sqlalchemy.Row | dict,
-    ) -> RuntimeKnowledgeBase:
-        if isinstance(knowledge_base_entity, sqlalchemy.Row):
-            knowledge_base_entity = persistence_rag.KnowledgeBase(**knowledge_base_entity._mapping)
-        elif isinstance(knowledge_base_entity, dict):
-            knowledge_base_entity = persistence_rag.KnowledgeBase(**knowledge_base_entity)
-
-        runtime_knowledge_base = RuntimeKnowledgeBase(ap=self.ap, knowledge_base_entity=knowledge_base_entity)
-
-        await runtime_knowledge_base.initialize()
-
-        self.knowledge_bases.append(runtime_knowledge_base)
-
-        return runtime_knowledge_base
-
-    async def get_knowledge_base_by_uuid(self, kb_uuid: str) -> RuntimeKnowledgeBase | None:
-        for kb in self.knowledge_bases:
-            if kb.knowledge_base_entity.uuid == kb_uuid:
-                return kb
-        return None
-
-    async def remove_knowledge_base(self, kb_uuid: str):
-        for kb in self.knowledge_bases:
-            if kb.knowledge_base_entity.uuid == kb_uuid:
-                await kb.dispose()
-                self.knowledge_bases.remove(kb)
-                return
-
-    async def store_data(self, file_path: str, kb_id: str, file_type: str, file_id: str = None):
-        """
-        Parses, chunks, embeds, and stores data from a given file into the RAG system.
-        Associates the file with a knowledge base using kb_id in the File table.
-        """
-        self.ap.logger.info(f'Starting data storage process for file: {file_path}')
-        session = SessionLocal()
-        file_obj = None
-
-        try:
-            kb = session.query(KnowledgeBase).filter_by(id=kb_id).first()
-            if not kb:
-                self.ap.logger.info(f'Knowledge Base "{kb_id}" does not exist. ')
-                return
-            # get embedding model
-            embedding_model = await self.ap.model_mgr.get_embedding_model_by_uuid(kb.embedding_model_uuid)
-            file_name = os.path.basename(file_path)
-            text = await self.parser.parse(file_path)
-            if not text:
-                self.ap.logger.warning(f'No text extracted from file {file_path}. ')
-                return
-
-            chunks_texts = await self.chunker.chunk(text)
-            self.ap.logger.info(f"Chunked file '{file_name}' into {len(chunks_texts)} chunks.")
-            await self.embedder.embed_and_store(file_id=file_id, chunks=chunks_texts, embedding_model=embedding_model)
-            self.ap.logger.info(f'Data storage process completed for file: {file_path}')
-
-        except Exception as e:
-            session.rollback()
-            self.ap.logger.error(f'Error in store_data for file {file_path}: {str(e)}', exc_info=True)
-            raise
-        finally:
-            if file_id:
-                file_obj = session.query(File).filter_by(id=file_id).first()
-            if file_obj:
-                file_obj.status = 1
-            session.close()
-
-    async def retrieve_data(self, query: str):
-        """
-        Retrieves relevant data chunks based on a given query using the configured retriever.
-        """
-        self.ap.logger.info(f"Starting data retrieval process for query: '{query}'")
-        try:
-            retrieved_chunks = await self.retriever.retrieve(query)
-            self.ap.logger.info(f'Successfully retrieved {len(retrieved_chunks)} chunks for query.')
-            return retrieved_chunks
-        except Exception as e:
-            self.ap.logger.error(f"Error in retrieve_data for query '{query}': {str(e)}", exc_info=True)
-            return []
-
-    async def delete_data_by_file_id(self, file_id: str):
-        """
-        Deletes all data associated with a specific file ID, including its chunks and vectors,
-        and the file record itself.
-        """
-        self.ap.logger.info(f'Starting data deletion process for file_id: {file_id}')
-        session = SessionLocal()
-        try:
-            # delete vectors
-            await asyncio.to_thread(self.chroma_manager.delete_by_file_id_sync, file_id)
-            self.ap.logger.info(f'Deleted embeddings from ChromaDB for file_id: {file_id}')
-
-            chunks_to_delete = session.query(Chunk).filter_by(file_id=file_id).all()
-            for chunk in chunks_to_delete:
-                session.delete(chunk)
-            self.ap.logger.info(f'Deleted {len(chunks_to_delete)} chunk records for file_id: {file_id}')
-
-            file_to_delete = session.query(File).filter_by(id=file_id).first()
-            if file_to_delete:
-                session.delete(file_to_delete)
-                try:
-                    await self.ap.storage_mgr.storage_provider.delete(file_id)
-                except Exception as e:
-                    self.ap.logger.error(
-                        f'Error deleting file from storage for file_id {file_id}: {str(e)}',
-                        exc_info=True,
-                    )
-                self.ap.logger.info(f'Deleted file record for file_id: {file_id}')
-            else:
-                self.ap.logger.warning(
-                    f'File with ID {file_id} not found in database. Skipping deletion of file record.'
-                )
-            session.commit()
-            self.ap.logger.info(f'Successfully completed data deletion for file_id: {file_id}')
-        except Exception as e:
-            session.rollback()
-            self.ap.logger.error(f'Error deleting data for file_id {file_id}: {str(e)}', exc_info=True)
-            raise
-        finally:
-            session.close()
-
-    async def delete_kb_by_id(self, kb_id: str):
-        """
-        Deletes a knowledge base and all associated files, chunks, and vectors.
-        This involves querying for associated files and then deleting them.
-        """
-        self.ap.logger.info(f'Starting deletion of knowledge base with ID: {kb_id}')
-        session = SessionLocal()
-
-        try:
-            kb_to_delete = session.query(KnowledgeBase).filter_by(id=kb_id).first()
-            if not kb_to_delete:
-                self.ap.logger.warning(f'Knowledge Base with ID {kb_id} not found.')
-                return
-
-            files_to_delete = session.query(File).filter_by(kb_id=kb_id).all()
-
-            session.close()
-
-            for file_obj in files_to_delete:
-                try:
-                    await self.delete_data_by_file_id(file_obj.id)
-                except Exception as file_del_e:
-                    self.ap.logger.error(f'Failed to delete file ID {file_obj.id} during KB deletion: {file_del_e}')
-
-            session = SessionLocal()
-            try:
-                kb_final_delete = session.query(KnowledgeBase).filter_by(id=kb_id).first()
-                if kb_final_delete:
-                    session.delete(kb_final_delete)
-                    session.commit()
-                    self.ap.logger.info(f'Successfully deleted knowledge base with ID: {kb_id}')
-                else:
-                    self.ap.logger.warning(
-                        f'Knowledge Base with ID {kb_id} not found after file deletion, skipping KB deletion.'
-                    )
-            except Exception as kb_del_e:
-                session.rollback()
-                self.ap.logger.error(
-                    f'Error deleting KnowledgeBase record for ID {kb_id}: {kb_del_e}',
-                    exc_info=True,
-                )
-                raise
-            finally:
-                session.close()
-
-        except Exception as e:
-            # 如果在最初获取 KB 或文件列表时出错
-            if session.is_active:
-                session.rollback()
-            self.ap.logger.error(
-                f'Error during overall knowledge base deletion for ID {kb_id}: {str(e)}',
-                exc_info=True,
-            )
-            raise
-        finally:
-            if session.is_active:
-                session.close()
-
-    async def get_file_content_by_file_id(self, file_id: str) -> str:
-        file_bytes = await self.ap.storage_mgr.storage_provider.load(file_id)
-
-        _, ext = os.path.splitext(file_id.lower())
-        ext = ext.lstrip('.')
-
-        try:
-            text = file_bytes.decode('utf-8')
-        except UnicodeDecodeError:
-            return '[非文本文件或编码无法识别]'
-
-        if ext in ['txt', 'md', 'csv', 'log', 'py', 'html']:
-            return text
-        else:
-            return f'[未知类型: .{ext}]'
-
-    async def relate_file_id_with_kb(self, knowledge_base_uuid: str, file_id: str) -> None:
-        """
-        Associates a file with a knowledge base by updating the kb_id in the File table.
-        """
-        self.ap.logger.info(f'Associating file ID {file_id} with knowledge base UUID {knowledge_base_uuid}')
-        session = SessionLocal()
-        try:
-            # 查询知识库是否存在
-            kb = session.query(KnowledgeBase).filter_by(id=knowledge_base_uuid).first()
-            if not kb:
-                self.ap.logger.error(f'Knowledge Base with UUID {knowledge_base_uuid} not found.')
-                return
-
-            if not await self.ap.storage_mgr.storage_provider.exists(file_id):
-                self.ap.logger.error(f'File with ID {file_id} does not exist.')
-                return
-            self.ap.logger.info(f'File with ID {file_id} exists, proceeding with association.')
-            # add new file record
-            file_to_update = File(
-                id=file_id,
-                kb_id=kb.id,
-                file_name=file_id,
-                path=os.path.join('data', 'storage', file_id),
-                file_type=os.path.splitext(file_id)[1].lstrip('.'),
-                status=0,
-            )
-            session.add(file_to_update)
-            session.commit()
-            self.ap.logger.info(
-                f'Successfully associated file ID {file_id} with knowledge base UUID {knowledge_base_uuid}'
-            )
-        except Exception as e:
-            session.rollback()
-            self.ap.logger.error(
-                f'Error associating file ID {file_id} with knowledge base UUID {knowledge_base_uuid}: {str(e)}',
-                exc_info=True,
-            )
-        finally:
-            # 进行文件解析
-            try:
-                await self.store_data(
-                    file_path=os.path.join('data', 'storage', file_id),
-                    kb_id=knowledge_base_uuid,
-                    file_type=os.path.splitext(file_id)[1].lstrip('.'),
-                    file_id=file_id,
-                )
-            except Exception:
-                # 如果存储数据时出错，更新文件状态为失败
-                file_obj = session.query(File).filter_by(id=file_id).first()
-                if file_obj:
-                    file_obj.status = 2
-                session.commit()
-                self.ap.logger.error(f'Error storing data for file ID {file_id}', exc_info=True)
-
-            session.close()
--- a/pkg/rag/knowledge/services/base_service.py
+++ b/pkg/rag/knowledge/services/base_service.py
@@ -1,26 +1,15 @@
 # 封装异步操作
 import asyncio
-import logging
-from pkg.rag.knowledge.services.database import SessionLocal 
+

 class BaseService:
    def __init__(self):
-        self.logger = logging.getLogger(self.__class__.__name__)
-        self.db_session_factory = SessionLocal
+        pass

    async def _run_sync(self, func, *args, **kwargs):
        """
        在单独的线程中运行同步函数。
        如果第一个参数是 session，则在 to_thread 中获取新的 session。
        """
-        
-        if getattr(func, '__name__', '').startswith('_db_'): 
-            session = await asyncio.to_thread(self.db_session_factory)
-            try:
-                result = await asyncio.to_thread(func, session, *args, **kwargs)
-                return result
-            finally:
-                session.close()
-        else:
-            # 否则，直接运行同步函数
-            return await asyncio.to_thread(func, *args, **kwargs)
+
+        return await asyncio.to_thread(func, *args, **kwargs)
--- a/pkg/rag/knowledge/services/chroma_manager.py
+++ b/pkg/rag/knowledge/services/chroma_manager.py
@@ -1,67 +0,0 @@
-import numpy as np
-import logging
-from chromadb import PersistentClient
-from pkg.core import app
-
-logger = logging.getLogger(__name__)
-
-
-class ChromaIndexManager:
-    def __init__(self, ap: app.Application, collection_name: str = 'default_collection'):
-        self.ap = ap
-        chroma_data_path = './data/chroma'
-        self.client = PersistentClient(path=chroma_data_path)
-        self._collection_name = collection_name
-        self._collection = None
-
-        self.ap.logger.info(f'ChromaIndexManager initialized. Collection name: {self._collection_name}')
-
-    @property
-    def collection(self):
-        if self._collection is None:
-            self._collection = self.client.get_or_create_collection(name=self._collection_name)
-            self.ap.logger.info(f"Chroma collection '{self._collection_name}' accessed/created.")
-        return self._collection
-
-    def add_embeddings_sync(
-        self, file_ids: list[int], chunk_ids: list[int], embeddings: np.ndarray, documents: list[str]
-    ):
-        if (
-            embeddings.shape[0] != len(chunk_ids)
-            or embeddings.shape[0] != len(file_ids)
-            or embeddings.shape[0] != len(documents)
-        ):
-            raise ValueError('Embedding, file_id, chunk_id, and document count mismatch.')
-
-        chroma_ids = [f'{file_id}_{chunk_id}' for file_id, chunk_id in zip(file_ids, chunk_ids)]
-        metadatas = [{'file_id': fid, 'chunk_id': cid} for fid, cid in zip(file_ids, chunk_ids)]
-
-        self.logger.debug(f"Adding {len(embeddings)} embeddings to Chroma collection '{self._collection_name}'.")
-        self.collection.add(embeddings=embeddings.tolist(), ids=chroma_ids, metadatas=metadatas, documents=documents)
-        self.logger.info(f"Added {len(embeddings)} embeddings to Chroma collection '{self._collection_name}'.")
-
-    def search_sync(self, query_embedding: np.ndarray, k: int = 5):
-        """
-        Searches the Chroma collection for the top-k nearest neighbors.
-        Args:
-            query_embedding: A numpy array of the query embedding.
-            k: The number of results to return.
-        Returns:
-            A dictionary containing query results from Chroma.
-        """
-        self.logger.debug(f"Searching Chroma collection '{self._collection_name}' with k={k}.")
-        results = self.collection.query(
-            query_embeddings=query_embedding.tolist(),
-            n_results=k,
-            # REMOVE 'ids' from the include list. It's returned by default.
-            include=['metadatas', 'distances', 'documents'],
-        )
-        self.logger.debug(f'Chroma search returned {len(results.get("ids", [[]])[0])} results.')
-        return results
-
-    def delete_by_file_id_sync(self, file_id: int):
-        self.logger.info(
-            f"Deleting embeddings for file_id: {file_id} from Chroma collection '{self._collection_name}'."
-        )
-        self.collection.delete(where={'file_id': file_id})
-        self.logger.info(f'Deleted embeddings for file_id: {file_id} from Chroma.')
--- a/pkg/rag/knowledge/services/chunker.py
+++ b/pkg/rag/knowledge/services/chunker.py
@@ -1,24 +1,22 @@
-# services/chunker.py
-import logging
+from __future__ import annotations
+
+import json
 from typing import List
-from pkg.rag.knowledge.services.base_service import BaseService  # Assuming BaseService provides _run_sync
+from pkg.rag.knowledge.services import base_service
 from pkg.core import app

-logger = logging.getLogger(__name__)

-
-class Chunker(BaseService):
+class Chunker(base_service.BaseService):
    """
    A class for splitting long texts into smaller, overlapping chunks.
    """

    def __init__(self, ap: app.Application, chunk_size: int = 500, chunk_overlap: int = 50):
-        super().__init__(ap)  # Initialize BaseService
        self.ap = ap
        self.chunk_size = chunk_size
        self.chunk_overlap = chunk_overlap
        if self.chunk_overlap >= self.chunk_size:
-            self.logger.warning(
+            self.ap.logger.warning(
                'Chunk overlap is greater than or equal to chunk size. This may lead to empty or malformed chunks.'
            )

@@ -61,4 +59,5 @@ class Chunker(BaseService):
        # Run the synchronous splitting logic in a separate thread
        chunks = await self._run_sync(self._split_text_sync, text)
        self.ap.logger.info(f'Text chunked into {len(chunks)} pieces.')
+        self.ap.logger.debug(f'Chunks: {json.dumps(chunks, indent=4, ensure_ascii=False)}')
        return chunks
--- a/pkg/rag/knowledge/services/database.py
+++ b/pkg/rag/knowledge/services/database.py
@@ -1,23 +0,0 @@
-# 全部迁移过去
-
-from pkg.entity.persistence.rag import (
-    create_db_and_tables,
-    SessionLocal,
-    Base,
-    engine,
-    KnowledgeBase,
-    File,
-    Chunk,
-    Vector,
-)
-
-__all__ = [
-    "create_db_and_tables",
-    "SessionLocal",
-    "Base",
-    "engine",
-    "KnowledgeBase",
-    "File",
-    "Chunk",
-    "Vector",
-]
--- a/pkg/rag/knowledge/services/embedder.py
+++ b/pkg/rag/knowledge/services/embedder.py
@@ -1,89 +1,47 @@
 from __future__ import annotations
-import asyncio
-import logging
-import numpy as np
+import uuid
 from typing import List
-from sqlalchemy.orm import Session
 from pkg.rag.knowledge.services.base_service import BaseService
-from pkg.rag.knowledge.services.database import Chunk, SessionLocal
-from pkg.rag.knowledge.services.chroma_manager import ChromaIndexManager
+from ....entity.persistence import rag as persistence_rag
 from ....core import app
 from ....provider.modelmgr.requester import RuntimeEmbeddingModel
+import sqlalchemy


 class Embedder(BaseService):
-    def __init__(self, ap: app.Application, chroma_manager: ChromaIndexManager = None) -> None:
+    def __init__(self, ap: app.Application) -> None:
        super().__init__()
-        self.logger = logging.getLogger(self.__class__.__name__)
-        self.chroma_manager = chroma_manager
        self.ap = ap

-    def _db_save_chunks_sync(self, session: Session, file_id: int, chunks_texts: List[str]):
-        """
-        Saves chunks to the relational database and returns the created Chunk objects.
-        This function assumes it's called within a context where the session
-        will be committed/rolled back and closed by the caller.
-        """
-        self.logger.debug(f'Saving {len(chunks_texts)} chunks for file_id {file_id} to DB (sync).')
-        chunk_objects = []
-        for text in chunks_texts:
-            chunk = Chunk(file_id=file_id, text=text)
-            session.add(chunk)
-            chunk_objects.append(chunk)
-        session.flush()  # This populates the .id attribute for each new chunk object
-        self.logger.debug(f'Successfully added {len(chunk_objects)} chunk entries to DB.')
-        return chunk_objects
-
    async def embed_and_store(
-        self, file_id: int, chunks: List[str], embedding_model: RuntimeEmbeddingModel
-    ) -> List[Chunk]:
-        if not embedding_model:
-            raise RuntimeError('Embedding model not loaded. Please check Embedder initialization.')
+        self, kb_id: str, file_id: str, chunks: List[str], embedding_model: RuntimeEmbeddingModel
+    ) -> list[persistence_rag.Chunk]:
+        # save chunk to db
+        chunk_entities: list[persistence_rag.Chunk] = []
+        chunk_ids: list[str] = []

-        session = SessionLocal()  # Start a session that will live for the whole operation
-        chunk_objects = []
-        try:
-            # 1. Save chunks to the relational database first to get their IDs
-            #    We call _db_save_chunks_sync directly without _run_sync's session management
-            #    because we manage the session here across multiple async calls.
-            chunk_objects = await asyncio.to_thread(self._db_save_chunks_sync, session, file_id, chunks)
-            session.commit()  # Commit chunks to make their IDs permanent and accessible
+        for chunk_text in chunks:
+            chunk_uuid = str(uuid.uuid4())
+            chunk_ids.append(chunk_uuid)
+            chunk_entity = persistence_rag.Chunk(uuid=chunk_uuid, file_id=file_id, text=chunk_text)
+            chunk_entities.append(chunk_entity)

-            if not chunk_objects:
-                self.logger.warning(
-                    f'No chunk objects created for file_id {file_id}. Skipping embedding and Chroma storage.'
-                )
-                return []
+        chunk_dicts = [
+            self.ap.persistence_mgr.serialize_model(persistence_rag.Chunk, chunk) for chunk in chunk_entities
+        ]

-            # get the embeddings for the chunks
-            embeddings: list[list[float]] = []
+        await self.ap.persistence_mgr.execute_async(sqlalchemy.insert(persistence_rag.Chunk).values(chunk_dicts))

-            for chunk in chunks:
-                result = await embedding_model.requester.invoke_embedding(
-                    model=embedding_model,
-                    input_text=chunk,
-                )
-                embeddings.append(result)
+        # get embeddings
+        embeddings_list: list[list[float]] = await embedding_model.requester.invoke_embedding(
+            model=embedding_model,
+            input_text=chunks,
+            extra_args={},  # TODO: add extra args
+        )

-            embeddings_np = np.array(embeddings, dtype=np.float32)
+        # save embeddings to vdb
+        await self.ap.vector_db_mgr.vector_db.add_embeddings(kb_id, chunk_ids, embeddings_list, chunk_dicts)

-            self.logger.info('Saving embeddings to Chroma...')
-            chunk_ids = [c.id for c in chunk_objects]
-            file_ids_for_chroma = [file_id] * len(chunk_ids)
+        self.ap.logger.info(f'Successfully saved {len(chunk_entities)} embeddings to Knowledge Base.')

-            await self._run_sync(  # Use _run_sync for the Chroma operation, as it's a sync call
-                self.chroma_manager.add_embeddings_sync,
-                file_ids_for_chroma,
-                chunk_ids,
-                embeddings_np,
-                chunks,  # Pass original chunks texts for documents
-            )
-            self.logger.info(f'Successfully saved {len(chunk_objects)} embeddings to Chroma.')
-            return chunk_objects
-
-        except Exception as e:
-            session.rollback()  # Rollback on any error
-            self.logger.error(f'Failed to process and store data for file_id {file_id}: {e}', exc_info=True)
-            raise  # Re-raise the exception to propagate it
-        finally:
-            session.close()  # Ensure the session is always closed
+        return chunk_entities
--- a/pkg/rag/knowledge/services/parser.py
+++ b/pkg/rag/knowledge/services/parser.py
@@ -1,21 +1,16 @@
+from __future__ import annotations
+
 import PyPDF2
 import io
 from docx import Document
-import pandas as pd
 import chardet
 from typing import Union, Callable, Any
-import logging
 import markdown
 from bs4 import BeautifulSoup
-import ebooklib
-from ebooklib import epub
 import re
 import asyncio  # Import asyncio for async operations
 from pkg.core import app

-# Configure logging
-logger = logging.getLogger(__name__)
-

 class FileParser:
    """
@@ -144,45 +139,45 @@ class FileParser:
        self.ap.logger.warning(f'Direct .doc parsing is not supported for {file_name}. Please convert to .docx first.')
        raise NotImplementedError('Direct .doc parsing not supported. Please convert to .docx first.')

-    async def _parse_xlsx(self, file_name: str) -> str:
-        """Parses an XLSX file, returning text from all sheets."""
-        self.ap.logger.info(f'Parsing XLSX file: {file_name}')
+    # async def _parse_xlsx(self, file_name: str) -> str:
+    #     """Parses an XLSX file, returning text from all sheets."""
+    #     self.ap.logger.info(f'Parsing XLSX file: {file_name}')

-        xlsx_bytes = await self.ap.storage_mgr.storage_provider.load(file_name)
+    #     xlsx_bytes = await self.ap.storage_mgr.storage_provider.load(file_name)

-        def _parse_xlsx_sync():
-            excel_file = pd.ExcelFile(io.BytesIO(xlsx_bytes))
-            all_sheet_content = []
-            for sheet_name in excel_file.sheet_names:
-                df = pd.read_excel(io.BytesIO(xlsx_bytes), sheet_name=sheet_name)
-                sheet_text = f'--- Sheet: {sheet_name} ---\n{df.to_string(index=False)}\n'
-                all_sheet_content.append(sheet_text)
-            return '\n'.join(all_sheet_content)
+    #     def _parse_xlsx_sync():
+    #         excel_file = pd.ExcelFile(io.BytesIO(xlsx_bytes))
+    #         all_sheet_content = []
+    #         for sheet_name in excel_file.sheet_names:
+    #             df = pd.read_excel(io.BytesIO(xlsx_bytes), sheet_name=sheet_name)
+    #             sheet_text = f'--- Sheet: {sheet_name} ---\n{df.to_string(index=False)}\n'
+    #             all_sheet_content.append(sheet_text)
+    #         return '\n'.join(all_sheet_content)

-        return await self._run_sync(_parse_xlsx_sync)
+    #     return await self._run_sync(_parse_xlsx_sync)

-    async def _parse_csv(self, file_name: str) -> str:
-        """Parses a CSV file and returns its content as a string."""
-        self.ap.logger.info(f'Parsing CSV file: {file_name}')
+    # async def _parse_csv(self, file_name: str) -> str:
+    #     """Parses a CSV file and returns its content as a string."""
+    #     self.ap.logger.info(f'Parsing CSV file: {file_name}')

-        csv_bytes = await self.ap.storage_mgr.storage_provider.load(file_name)
+    #     csv_bytes = await self.ap.storage_mgr.storage_provider.load(file_name)

-        def _parse_csv_sync():
-            # pd.read_csv can often detect encoding, but explicit detection is safer
-            # raw_data = self._read_file_content(
-            #     file_name, mode='rb'
-            # )  # Note: this will need to be await outside this sync function
-            # _ = raw_data
-            # For simplicity, we'll let pandas handle encoding internally after a raw read.
-            # A more robust solution might pass encoding directly to pd.read_csv after detection.
-            detected = chardet.detect(io.BytesIO(csv_bytes))
-            encoding = detected['encoding'] or 'utf-8'
-            df = pd.read_csv(io.BytesIO(csv_bytes), encoding=encoding)
-            return df.to_string(index=False)
+    #     def _parse_csv_sync():
+    #         # pd.read_csv can often detect encoding, but explicit detection is safer
+    #         # raw_data = self._read_file_content(
+    #         #     file_name, mode='rb'
+    #         # )  # Note: this will need to be await outside this sync function
+    #         # _ = raw_data
+    #         # For simplicity, we'll let pandas handle encoding internally after a raw read.
+    #         # A more robust solution might pass encoding directly to pd.read_csv after detection.
+    #         detected = chardet.detect(io.BytesIO(csv_bytes))
+    #         encoding = detected['encoding'] or 'utf-8'
+    #         df = pd.read_csv(io.BytesIO(csv_bytes), encoding=encoding)
+    #         return df.to_string(index=False)

-        return await self._run_sync(_parse_csv_sync)
+    #     return await self._run_sync(_parse_csv_sync)

-    async def _parse_markdown(self, file_name: str) -> str:
+    async def _parse_md(self, file_name: str) -> str:
        """Parses a Markdown file, converting it to structured plain text."""
        self.ap.logger.info(f'Parsing Markdown file: {file_name}')

@@ -261,43 +256,6 @@ class FileParser:

        return await self._run_sync(_parse_html_sync)

-    async def _parse_epub(self, file_name: str) -> str:
-        """Parses an EPUB file, extracting metadata and content."""
-        self.ap.logger.info(f'Parsing EPUB file: {file_name}')
-
-        epub_bytes = await self.ap.storage_mgr.storage_provider.load(file_name)
-
-        def _parse_epub_sync():
-            book = epub.read_epub(io.BytesIO(epub_bytes))
-            text_content = []
-            title_meta = book.get_metadata('DC', 'title')
-            if title_meta:
-                text_content.append(f'Title: {title_meta[0][0]}')
-            creator_meta = book.get_metadata('DC', 'creator')
-            if creator_meta:
-                text_content.append(f'Author: {creator_meta[0][0]}')
-            date_meta = book.get_metadata('DC', 'date')
-            if date_meta:
-                text_content.append(f'Publish Date: {date_meta[0][0]}')
-            toc = book.get_toc()
-            if toc:
-                text_content.append('\n--- Table of Contents ---')
-                self._add_toc_items_sync(toc, text_content, level=0)  # Call sync helper
-                text_content.append('--- End of Table of Contents ---\n')
-            for item in book.get_items():
-                if item.get_type() == ebooklib.ITEM_DOCUMENT:
-                    html_content = item.get_content().decode('utf-8', errors='ignore')
-                    soup = BeautifulSoup(html_content, 'html.parser')
-                    for junk in soup(['script', 'style', 'nav', 'header', 'footer']):
-                        junk.decompose()
-                    text = soup.get_text(separator='\n', strip=True)
-                    text = re.sub(r'\n\s*\n', '\n\n', text)
-                    if text:
-                        text_content.append(text)
-            return re.sub(r'\n\s*\n', '\n\n', '\n'.join(text_content)).strip()
-
-        return await self._run_sync(_parse_epub_sync)
-
    def _add_toc_items_sync(self, toc_list: list, text_content: list, level: int):
        """Recursively adds TOC items to text_content (synchronous helper)."""
        indent = '  ' * level
--- a/pkg/rag/knowledge/services/retriever.py
+++ b/pkg/rag/knowledge/services/retriever.py
@@ -1,94 +1,48 @@
 from __future__ import annotations
-import logging
-import numpy as np  # Make sure numpy is imported
-from typing import List, Dict, Any
-from sqlalchemy.orm import Session
-from pkg.rag.knowledge.services.base_service import BaseService
-from pkg.rag.knowledge.services.database import Chunk, SessionLocal
-from pkg.rag.knowledge.services.chroma_manager import ChromaIndexManager
+
+from . import base_service
 from ....core import app
-
-logger = logging.getLogger(__name__)
+from ....provider.modelmgr.requester import RuntimeEmbeddingModel
+from ....entity.rag import retriever as retriever_entities


-class Retriever(BaseService):
-    def __init__(self, ap:app.Application, chroma_manager: ChromaIndexManager):
+class Retriever(base_service.BaseService):
+    def __init__(self, ap: app.Application):
        super().__init__()
-        self.logger = logging.getLogger(self.__class__.__name__)
-        self.chroma_manager = chroma_manager
        self.ap = ap

-    async def retrieve(self, query: str, k: int = 5) -> List[Dict[str, Any]]:
-        if not self.embedding_model:
-            raise RuntimeError('Retriever embedding model not loaded. Please check Retriever initialization.')
+    async def retrieve(
+        self, kb_id: str, query: str, embedding_model: RuntimeEmbeddingModel, k: int = 5
+    ) -> list[retriever_entities.RetrieveResultEntry]:
+        self.ap.logger.info(
+            f"Retrieving for query: '{query[:10]}' with k={k} using {embedding_model.model_entity.uuid}"
+        )

-        self.logger.info(f"Retrieving for query: '{query}' with k={k} using {self.model_name_key}")
+        query_embedding: list[float] = await embedding_model.requester.invoke_embedding(
+            model=embedding_model,
+            input_text=[query],
+            extra_args={},  # TODO: add extra args
+        )

-        query_embedding: List[float] = await self.embedding_model.embed_query(query)
-        query_embedding_np = np.array([query_embedding], dtype=np.float32)
-
-        chroma_results = await self._run_sync(self.chroma_manager.search_sync, query_embedding_np, k)
+        chroma_results = await self.ap.vector_db_mgr.vector_db.search(kb_id, query_embedding[0], k)

        # 'ids' is always returned by ChromaDB, even if not explicitly in 'include'
        matched_chroma_ids = chroma_results.get('ids', [[]])[0]
        distances = chroma_results.get('distances', [[]])[0]
        chroma_metadatas = chroma_results.get('metadatas', [[]])[0]
-        chroma_documents = chroma_results.get('documents', [[]])[0]

        if not matched_chroma_ids:
-            self.logger.info('No relevant chunks found in Chroma.')
+            self.ap.logger.info('No relevant chunks found in Chroma.')
            return []

-        db_chunk_ids = []
-        for metadata in chroma_metadatas:
-            if 'chunk_id' in metadata:
-                db_chunk_ids.append(metadata['chunk_id'])
-            else:
-                self.logger.warning(f"Metadata missing 'chunk_id': {metadata}. Skipping this entry.")
+        result: list[retriever_entities.RetrieveResultEntry] = []

-        if not db_chunk_ids:
-            self.logger.warning('No valid chunk_ids extracted from Chroma results metadata.')
-            return []
-
-        self.logger.info(f'Fetching {len(db_chunk_ids)} chunk details from relational database...')
-        chunks_from_db = await self._run_sync(
-            lambda cids: self._db_get_chunks_sync(
-                SessionLocal(), cids
-            ),  # Ensure SessionLocal is passed correctly for _db_get_chunks_sync
-            db_chunk_ids,
-        )
-
-        chunk_map = {chunk.id: chunk for chunk in chunks_from_db}
-        results_list: List[Dict[str, Any]] = []
-
-        for i, chroma_id in enumerate(matched_chroma_ids):
-            try:
-                # Ensure original_chunk_id is int for DB lookup
-                original_chunk_id = int(chroma_id.split('_')[-1])
-            except (ValueError, IndexError):
-                self.logger.warning(f'Could not parse chunk_id from Chroma ID: {chroma_id}. Skipping.')
-                continue
-
-            chunk_text_from_chroma = chroma_documents[i]
-            distance = float(distances[i])
-            file_id_from_chroma = chroma_metadatas[i].get('file_id')
-
-            chunk_from_db = chunk_map.get(original_chunk_id)
-
-            results_list.append(
-                {
-                    'chunk_id': original_chunk_id,
-                    'text': chunk_from_db.text if chunk_from_db else chunk_text_from_chroma,
-                    'distance': distance,
-                    'file_id': file_id_from_chroma,
-                }
+        for i, id in enumerate(matched_chroma_ids):
+            entry = retriever_entities.RetrieveResultEntry(
+                id=id,
+                metadata=chroma_metadatas[i],
+                distance=distances[i],
            )
+            result.append(entry)

-        self.logger.info(f'Retrieved {len(results_list)} chunks.')
-        return results_list
-
-    def _db_get_chunks_sync(self, session: Session, chunk_ids: List[int]) -> List[Chunk]:
-        self.logger.debug(f'Fetching {len(chunk_ids)} chunk details from database (sync).')
-        chunks = session.query(Chunk).filter(Chunk.id.in_(chunk_ids)).all()
-        session.close()
-        return chunks
+        return result
--- a/pkg/utils/announce.py
+++ b/pkg/utils/announce.py
@@ -46,7 +46,7 @@ class AnnouncementManager:
    async def fetch_all(self) -> list[Announcement]:
        """获取所有公告"""
        resp = requests.get(
-            url='https://api.github.com/repos/RockChinQ/LangBot/contents/res/announcement.json',
+            url='https://api.github.com/repos/langbot-app/LangBot/contents/res/announcement.json',
            proxies=self.ap.proxy_mgr.get_forward_proxies(),
            timeout=5,
        )
--- a/pkg/utils/constants.py
+++ b/pkg/utils/constants.py
@@ -1,6 +1,6 @@
-semantic_version = 'v4.0.8'
+semantic_version = 'v4.1.0'

-required_database_version = 3
+required_database_version = 4
 """Tag the version of the database schema, used to check if the database needs to be migrated"""

 debug_mode = False
--- a/pkg/utils/version.py
+++ b/pkg/utils/version.py
@@ -29,7 +29,7 @@ class VersionManager:
    async def get_release_list(self) -> list:
        """获取发行列表"""
        rls_list_resp = requests.get(
-            url='https://api.github.com/repos/RockChinQ/LangBot/releases',
+            url='https://api.github.com/repos/langbot-app/LangBot/releases',
            proxies=self.ap.proxy_mgr.get_forward_proxies(),
            timeout=5,
        )
--- a/pkg/vector/mgr.py
+++ b/pkg/vector/mgr.py
@@ -1,13 +1,18 @@
 from __future__ import annotations

 from ..core import app
+from .vdb import VectorDatabase
+from .vdbs.chroma import ChromaVectorDatabase


 class VectorDBManager:
    ap: app.Application
+    vector_db: VectorDatabase = None

    def __init__(self, ap: app.Application):
        self.ap = ap

    async def initialize(self):
-        pass
+        # 初始化 Chroma 向量数据库（可扩展为多种实现）
+        if self.vector_db is None:
+            self.vector_db = ChromaVectorDatabase(self.ap)
--- a/pkg/vector/vdb.py
+++ b/pkg/vector/vdb.py
@@ -1,7 +1,37 @@
 from __future__ import annotations
-
 import abc
+from typing import Any, Dict
+import numpy as np


 class VectorDatabase(abc.ABC):
-    pass
+    @abc.abstractmethod
+    async def add_embeddings(
+        self,
+        collection: str,
+        ids: list[str],
+        embeddings_list: list[list[float]],
+        metadatas: list[dict[str, Any]],
+        documents: list[str],
+    ) -> None:
+        """向指定 collection 添加向量数据。"""
+        pass
+
+    @abc.abstractmethod
+    async def search(self, collection: str, query_embedding: np.ndarray, k: int = 5) -> Dict[str, Any]:
+        """在指定 collection 中检索最相似的向量。"""
+        pass
+
+    @abc.abstractmethod
+    async def delete_by_file_id(self, collection: str, file_id: str) -> None:
+        """根据 file_id 删除指定 collection 中的向量。"""
+        pass
+
+    @abc.abstractmethod
+    async def get_or_create_collection(self, collection: str):
+        """获取或创建 collection。"""
+        pass
+
+    @abc.abstractmethod
+    async def delete_collection(self, collection: str):
+        pass
--- a/pkg/vector/vdbs/init.py
+++ b/pkg/vector/vdbs/init.py
--- a/pkg/vector/vdbs/chroma.py
+++ b/pkg/vector/vdbs/chroma.py
@@ -0,0 +1,61 @@
+from __future__ import annotations
+import asyncio
+from typing import Any
+from chromadb import PersistentClient
+from pkg.vector.vdb import VectorDatabase
+from pkg.core import app
+import chromadb
+import chromadb.errors
+
+
+class ChromaVectorDatabase(VectorDatabase):
+    def __init__(self, ap: app.Application, base_path: str = './data/chroma'):
+        self.ap = ap
+        self.client = PersistentClient(path=base_path)
+        self._collections = {}
+
+    async def get_or_create_collection(self, collection: str) -> chromadb.Collection:
+        if collection not in self._collections:
+            self._collections[collection] = await asyncio.to_thread(
+                self.client.get_or_create_collection, name=collection
+            )
+            self.ap.logger.info(f"Chroma collection '{collection}' accessed/created.")
+        return self._collections[collection]
+
+    async def add_embeddings(
+        self,
+        collection: str,
+        ids: list[str],
+        embeddings_list: list[list[float]],
+        metadatas: list[dict[str, Any]],
+    ) -> None:
+        col = await self.get_or_create_collection(collection)
+        await asyncio.to_thread(col.add, embeddings=embeddings_list, ids=ids, metadatas=metadatas)
+        self.ap.logger.info(f"Added {len(ids)} embeddings to Chroma collection '{collection}'.")
+
+    async def search(self, collection: str, query_embedding: list[float], k: int = 5) -> dict[str, Any]:
+        col = await self.get_or_create_collection(collection)
+        results = await asyncio.to_thread(
+            col.query,
+            query_embeddings=query_embedding,
+            n_results=k,
+            include=['metadatas', 'distances', 'documents'],
+        )
+        self.ap.logger.info(f"Chroma search in '{collection}' returned {len(results.get('ids', [[]])[0])} results.")
+        return results
+
+    async def delete_by_file_id(self, collection: str, file_id: str) -> None:
+        col = await self.get_or_create_collection(collection)
+        await asyncio.to_thread(col.delete, where={'file_id': file_id})
+        self.ap.logger.info(f"Deleted embeddings from Chroma collection '{collection}' with file_id: {file_id}")
+
+    async def delete_collection(self, collection: str):
+        if collection in self._collections:
+            del self._collections[collection]
+
+        try:
+            await asyncio.to_thread(self.client.delete_collection, name=collection)
+        except chromadb.errors.NotFoundError:
+            self.ap.logger.warning(f"Chroma collection '{collection}' not found.")
+            return
+        self.ap.logger.info(f"Chroma collection '{collection}' deleted.")
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -1,6 +1,6 @@
 [project]
 name = "langbot"
-version = "4.0.7"
+version = "4.1.0"
 description = "高稳定、支持扩展、多模态 - 大模型原生即时通信机器人平台"
 readme = "README.md"
 requires-python = ">=3.10.1"
@@ -19,6 +19,7 @@ dependencies = [
    "dashscope>=1.23.2",
    "dingtalk-stream>=0.24.0",
    "discord-py>=2.5.2",
+    "pynacl>=1.5.0",  # Required for Discord voice support
    "gewechat-client>=0.1.5",
    "lark-oapi>=1.4.15",
    "mcp>=1.8.1",
@@ -59,7 +60,6 @@ dependencies = [
    "html2text>=2024.2.26",
    "langchain>=0.2.0",
    "chromadb>=0.4.24",
-    "sentence-transformers>=2.6.1",
 ]
 keywords = [
    "bot",
@@ -90,11 +90,13 @@ classifiers = [
 [project.urls]
 Homepage = "https://langbot.app"
 Documentation = "https://docs.langbot.app"
-Repository = "https://github.com/RockChinQ/langbot"
+Repository = "https://github.com/langbot-app/LangBot"

 [dependency-groups]
 dev = [
    "pre-commit>=4.2.0",
+    "pytest>=8.4.1",
+    "pytest-asyncio>=1.0.0",
    "ruff>=0.11.9",
 ]

--- a/templates/default-pipeline-config.json
+++ b/templates/default-pipeline-config.json
@@ -44,7 +44,8 @@
                    "role": "system",
                    "content": "You are a helpful assistant."
                }
-            ]
+            ],
+            "knowledge-base": ""
        },
        "dify-service-api": {
            "base-url": "https://api.dify.ai/v1",
--- a/templates/metadata/pipeline/ai.yaml
+++ b/templates/metadata/pipeline/ai.yaml
@@ -68,6 +68,16 @@ stages:
          zh_Hans: 除非您了解消息结构，否则请只使用 system 单提示词
        type: prompt-editor
        required: true
+      - name: knowledge-base
+        label:
+          en_US: Knowledge Base
+          zh_Hans: 知识库
+        description:
+          en_US: Configure the knowledge base to use for the agent, if not selected, the agent will directly use the LLM to reply
+          zh_Hans: 配置用于提升回复质量的知识库，若不选择，则直接使用大模型回复
+        type: knowledge-base-selector
+        required: false
+        default: ''
  - name: dify-service-api
    label:
      en_US: Dify Service API
@@ -298,3 +308,4 @@ stages:
        type: string
        required: false
        default: 'response'
+  
--- a/web/package-lock.json
+++ b/web/package-lock.json
@@ -13,6 +13,7 @@
        "@hookform/resolvers": "^5.0.1",
        "@radix-ui/react-checkbox": "^1.3.1",
        "@radix-ui/react-dialog": "^1.1.14",
+        "@radix-ui/react-dropdown-menu": "^2.1.15",
        "@radix-ui/react-hover-card": "^1.1.13",
        "@radix-ui/react-label": "^2.1.6",
        "@radix-ui/react-popover": "^1.1.14",
@@ -1152,31 +1153,6 @@
        }
      }
    },
-    "node_modules/@radix-ui/react-dialog/node_modules/@radix-ui/react-focus-scope": {
-      "version": "1.1.7",
-      "resolved": "https://registry.npmjs.org/@radix-ui/react-focus-scope/-/react-focus-scope-1.1.7.tgz",
-      "integrity": "sha512-t2ODlkXBQyn7jkl6TNaw/MtVEVvIGelJDCG41Okq/KwUsJBwQ4XVZsHAVUkK4mBv3ewiAS3PGuUWuY2BoK4ZUw==",
-      "license": "MIT",
-      "dependencies": {
-        "@radix-ui/react-compose-refs": "1.1.2",
-        "@radix-ui/react-primitive": "2.1.3",
-        "@radix-ui/react-use-callback-ref": "1.1.1"
-      },
-      "peerDependencies": {
-        "@types/react": "*",
-        "@types/react-dom": "*",
-        "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc",
-        "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc"
-      },
-      "peerDependenciesMeta": {
-        "@types/react": {
-          "optional": true
-        },
-        "@types/react-dom": {
-          "optional": true
-        }
-      }
-    },
    "node_modules/@radix-ui/react-dialog/node_modules/@radix-ui/react-portal": {
      "version": "1.1.9",
      "resolved": "https://registry.npmjs.org/@radix-ui/react-portal/-/react-portal-1.1.9.tgz",
@@ -1266,6 +1242,58 @@
        }
      }
    },
+    "node_modules/@radix-ui/react-dropdown-menu": {
+      "version": "2.1.15",
+      "resolved": "https://registry.npmjs.org/@radix-ui/react-dropdown-menu/-/react-dropdown-menu-2.1.15.tgz",
+      "integrity": "sha512-mIBnOjgwo9AH3FyKaSWoSu/dYj6VdhJ7frEPiGTeXCdUFHjl9h3mFh2wwhEtINOmYXWhdpf1rY2minFsmaNgVQ==",
+      "license": "MIT",
+      "dependencies": {
+        "@radix-ui/primitive": "1.1.2",
+        "@radix-ui/react-compose-refs": "1.1.2",
+        "@radix-ui/react-context": "1.1.2",
+        "@radix-ui/react-id": "1.1.1",
+        "@radix-ui/react-menu": "2.1.15",
+        "@radix-ui/react-primitive": "2.1.3",
+        "@radix-ui/react-use-controllable-state": "1.2.2"
+      },
+      "peerDependencies": {
+        "@types/react": "*",
+        "@types/react-dom": "*",
+        "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc",
+        "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc"
+      },
+      "peerDependenciesMeta": {
+        "@types/react": {
+          "optional": true
+        },
+        "@types/react-dom": {
+          "optional": true
+        }
+      }
+    },
+    "node_modules/@radix-ui/react-dropdown-menu/node_modules/@radix-ui/react-primitive": {
+      "version": "2.1.3",
+      "resolved": "https://registry.npmjs.org/@radix-ui/react-primitive/-/react-primitive-2.1.3.tgz",
+      "integrity": "sha512-m9gTwRkhy2lvCPe6QJp4d3G1TYEUHn/FzJUtq9MjH46an1wJU+GdoGC5VLof8RX8Ft/DlpshApkhswDLZzHIcQ==",
+      "license": "MIT",
+      "dependencies": {
+        "@radix-ui/react-slot": "1.2.3"
+      },
+      "peerDependencies": {
+        "@types/react": "*",
+        "@types/react-dom": "*",
+        "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc",
+        "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc"
+      },
+      "peerDependenciesMeta": {
+        "@types/react": {
+          "optional": true
+        },
+        "@types/react-dom": {
+          "optional": true
+        }
+      }
+    },
    "node_modules/@radix-ui/react-focus-guards": {
      "version": "1.1.2",
      "resolved": "https://registry.npmjs.org/@radix-ui/react-focus-guards/-/react-focus-guards-1.1.2.tgz",
@@ -1282,13 +1310,13 @@
      }
    },
    "node_modules/@radix-ui/react-focus-scope": {
-      "version": "1.1.6",
-      "resolved": "https://registry.npmjs.org/@radix-ui/react-focus-scope/-/react-focus-scope-1.1.6.tgz",
-      "integrity": "sha512-r9zpYNUQY+2jWHWZGyddQLL9YHkM/XvSFHVcWs7bdVuxMAnCwTAuy6Pf47Z4nw7dYcUou1vg/VgjjrrH03VeBw==",
+      "version": "1.1.7",
+      "resolved": "https://registry.npmjs.org/@radix-ui/react-focus-scope/-/react-focus-scope-1.1.7.tgz",
+      "integrity": "sha512-t2ODlkXBQyn7jkl6TNaw/MtVEVvIGelJDCG41Okq/KwUsJBwQ4XVZsHAVUkK4mBv3ewiAS3PGuUWuY2BoK4ZUw==",
      "license": "MIT",
      "dependencies": {
        "@radix-ui/react-compose-refs": "1.1.2",
-        "@radix-ui/react-primitive": "2.1.2",
+        "@radix-ui/react-primitive": "2.1.3",
        "@radix-ui/react-use-callback-ref": "1.1.1"
      },
      "peerDependencies": {
@@ -1306,6 +1334,29 @@
        }
      }
    },
+    "node_modules/@radix-ui/react-focus-scope/node_modules/@radix-ui/react-primitive": {
+      "version": "2.1.3",
+      "resolved": "https://registry.npmjs.org/@radix-ui/react-primitive/-/react-primitive-2.1.3.tgz",
+      "integrity": "sha512-m9gTwRkhy2lvCPe6QJp4d3G1TYEUHn/FzJUtq9MjH46an1wJU+GdoGC5VLof8RX8Ft/DlpshApkhswDLZzHIcQ==",
+      "license": "MIT",
+      "dependencies": {
+        "@radix-ui/react-slot": "1.2.3"
+      },
+      "peerDependencies": {
+        "@types/react": "*",
+        "@types/react-dom": "*",
+        "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc",
+        "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc"
+      },
+      "peerDependenciesMeta": {
+        "@types/react": {
+          "optional": true
+        },
+        "@types/react-dom": {
+          "optional": true
+        }
+      }
+    },
    "node_modules/@radix-ui/react-hover-card": {
      "version": "1.1.13",
      "resolved": "https://registry.npmjs.org/@radix-ui/react-hover-card/-/react-hover-card-1.1.13.tgz",
@@ -1378,6 +1429,232 @@
        }
      }
    },
+    "node_modules/@radix-ui/react-menu": {
+      "version": "2.1.15",
+      "resolved": "https://registry.npmjs.org/@radix-ui/react-menu/-/react-menu-2.1.15.tgz",
+      "integrity": "sha512-tVlmA3Vb9n8SZSd+YSbuFR66l87Wiy4du+YE+0hzKQEANA+7cWKH1WgqcEX4pXqxUFQKrWQGHdvEfw00TjFiew==",
+      "license": "MIT",
+      "dependencies": {
+        "@radix-ui/primitive": "1.1.2",
+        "@radix-ui/react-collection": "1.1.7",
+        "@radix-ui/react-compose-refs": "1.1.2",
+        "@radix-ui/react-context": "1.1.2",
+        "@radix-ui/react-direction": "1.1.1",
+        "@radix-ui/react-dismissable-layer": "1.1.10",
+        "@radix-ui/react-focus-guards": "1.1.2",
+        "@radix-ui/react-focus-scope": "1.1.7",
+        "@radix-ui/react-id": "1.1.1",
+        "@radix-ui/react-popper": "1.2.7",
+        "@radix-ui/react-portal": "1.1.9",
+        "@radix-ui/react-presence": "1.1.4",
+        "@radix-ui/react-primitive": "2.1.3",
+        "@radix-ui/react-roving-focus": "1.1.10",
+        "@radix-ui/react-slot": "1.2.3",
+        "@radix-ui/react-use-callback-ref": "1.1.1",
+        "aria-hidden": "^1.2.4",
+        "react-remove-scroll": "^2.6.3"
+      },
+      "peerDependencies": {
+        "@types/react": "*",
+        "@types/react-dom": "*",
+        "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc",
+        "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc"
+      },
+      "peerDependenciesMeta": {
+        "@types/react": {
+          "optional": true
+        },
+        "@types/react-dom": {
+          "optional": true
+        }
+      }
+    },
+    "node_modules/@radix-ui/react-menu/node_modules/@radix-ui/react-arrow": {
+      "version": "1.1.7",
+      "resolved": "https://registry.npmjs.org/@radix-ui/react-arrow/-/react-arrow-1.1.7.tgz",
+      "integrity": "sha512-F+M1tLhO+mlQaOWspE8Wstg+z6PwxwRd8oQ8IXceWz92kfAmalTRf0EjrouQeo7QssEPfCn05B4Ihs1K9WQ/7w==",
+      "license": "MIT",
+      "dependencies": {
+        "@radix-ui/react-primitive": "2.1.3"
+      },
+      "peerDependencies": {
+        "@types/react": "*",
+        "@types/react-dom": "*",
+        "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc",
+        "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc"
+      },
+      "peerDependenciesMeta": {
+        "@types/react": {
+          "optional": true
+        },
+        "@types/react-dom": {
+          "optional": true
+        }
+      }
+    },
+    "node_modules/@radix-ui/react-menu/node_modules/@radix-ui/react-collection": {
+      "version": "1.1.7",
+      "resolved": "https://registry.npmjs.org/@radix-ui/react-collection/-/react-collection-1.1.7.tgz",
+      "integrity": "sha512-Fh9rGN0MoI4ZFUNyfFVNU4y9LUz93u9/0K+yLgA2bwRojxM8JU1DyvvMBabnZPBgMWREAJvU2jjVzq+LrFUglw==",
+      "license": "MIT",
+      "dependencies": {
+        "@radix-ui/react-compose-refs": "1.1.2",
+        "@radix-ui/react-context": "1.1.2",
+        "@radix-ui/react-primitive": "2.1.3",
+        "@radix-ui/react-slot": "1.2.3"
+      },
+      "peerDependencies": {
+        "@types/react": "*",
+        "@types/react-dom": "*",
+        "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc",
+        "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc"
+      },
+      "peerDependenciesMeta": {
+        "@types/react": {
+          "optional": true
+        },
+        "@types/react-dom": {
+          "optional": true
+        }
+      }
+    },
+    "node_modules/@radix-ui/react-menu/node_modules/@radix-ui/react-dismissable-layer": {
+      "version": "1.1.10",
+      "resolved": "https://registry.npmjs.org/@radix-ui/react-dismissable-layer/-/react-dismissable-layer-1.1.10.tgz",
+      "integrity": "sha512-IM1zzRV4W3HtVgftdQiiOmA0AdJlCtMLe00FXaHwgt3rAnNsIyDqshvkIW3hj/iu5hu8ERP7KIYki6NkqDxAwQ==",
+      "license": "MIT",
+      "dependencies": {
+        "@radix-ui/primitive": "1.1.2",
+        "@radix-ui/react-compose-refs": "1.1.2",
+        "@radix-ui/react-primitive": "2.1.3",
+        "@radix-ui/react-use-callback-ref": "1.1.1",
+        "@radix-ui/react-use-escape-keydown": "1.1.1"
+      },
+      "peerDependencies": {
+        "@types/react": "*",
+        "@types/react-dom": "*",
+        "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc",
+        "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc"
+      },
+      "peerDependenciesMeta": {
+        "@types/react": {
+          "optional": true
+        },
+        "@types/react-dom": {
+          "optional": true
+        }
+      }
+    },
+    "node_modules/@radix-ui/react-menu/node_modules/@radix-ui/react-popper": {
+      "version": "1.2.7",
+      "resolved": "https://registry.npmjs.org/@radix-ui/react-popper/-/react-popper-1.2.7.tgz",
+      "integrity": "sha512-IUFAccz1JyKcf/RjB552PlWwxjeCJB8/4KxT7EhBHOJM+mN7LdW+B3kacJXILm32xawcMMjb2i0cIZpo+f9kiQ==",
+      "license": "MIT",
+      "dependencies": {
+        "@floating-ui/react-dom": "^2.0.0",
+        "@radix-ui/react-arrow": "1.1.7",
+        "@radix-ui/react-compose-refs": "1.1.2",
+        "@radix-ui/react-context": "1.1.2",
+        "@radix-ui/react-primitive": "2.1.3",
+        "@radix-ui/react-use-callback-ref": "1.1.1",
+        "@radix-ui/react-use-layout-effect": "1.1.1",
+        "@radix-ui/react-use-rect": "1.1.1",
+        "@radix-ui/react-use-size": "1.1.1",
+        "@radix-ui/rect": "1.1.1"
+      },
+      "peerDependencies": {
+        "@types/react": "*",
+        "@types/react-dom": "*",
+        "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc",
+        "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc"
+      },
+      "peerDependenciesMeta": {
+        "@types/react": {
+          "optional": true
+        },
+        "@types/react-dom": {
+          "optional": true
+        }
+      }
+    },
+    "node_modules/@radix-ui/react-menu/node_modules/@radix-ui/react-portal": {
+      "version": "1.1.9",
+      "resolved": "https://registry.npmjs.org/@radix-ui/react-portal/-/react-portal-1.1.9.tgz",
+      "integrity": "sha512-bpIxvq03if6UNwXZ+HTK71JLh4APvnXntDc6XOX8UVq4XQOVl7lwok0AvIl+b8zgCw3fSaVTZMpAPPagXbKmHQ==",
+      "license": "MIT",
+      "dependencies": {
+        "@radix-ui/react-primitive": "2.1.3",
+        "@radix-ui/react-use-layout-effect": "1.1.1"
+      },
+      "peerDependencies": {
+        "@types/react": "*",
+        "@types/react-dom": "*",
+        "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc",
+        "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc"
+      },
+      "peerDependenciesMeta": {
+        "@types/react": {
+          "optional": true
+        },
+        "@types/react-dom": {
+          "optional": true
+        }
+      }
+    },
+    "node_modules/@radix-ui/react-menu/node_modules/@radix-ui/react-primitive": {
+      "version": "2.1.3",
+      "resolved": "https://registry.npmjs.org/@radix-ui/react-primitive/-/react-primitive-2.1.3.tgz",
+      "integrity": "sha512-m9gTwRkhy2lvCPe6QJp4d3G1TYEUHn/FzJUtq9MjH46an1wJU+GdoGC5VLof8RX8Ft/DlpshApkhswDLZzHIcQ==",
+      "license": "MIT",
+      "dependencies": {
+        "@radix-ui/react-slot": "1.2.3"
+      },
+      "peerDependencies": {
+        "@types/react": "*",
+        "@types/react-dom": "*",
+        "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc",
+        "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc"
+      },
+      "peerDependenciesMeta": {
+        "@types/react": {
+          "optional": true
+        },
+        "@types/react-dom": {
+          "optional": true
+        }
+      }
+    },
+    "node_modules/@radix-ui/react-menu/node_modules/@radix-ui/react-roving-focus": {
+      "version": "1.1.10",
+      "resolved": "https://registry.npmjs.org/@radix-ui/react-roving-focus/-/react-roving-focus-1.1.10.tgz",
+      "integrity": "sha512-dT9aOXUen9JSsxnMPv/0VqySQf5eDQ6LCk5Sw28kamz8wSOW2bJdlX2Bg5VUIIcV+6XlHpWTIuTPCf/UNIyq8Q==",
+      "license": "MIT",
+      "dependencies": {
+        "@radix-ui/primitive": "1.1.2",
+        "@radix-ui/react-collection": "1.1.7",
+        "@radix-ui/react-compose-refs": "1.1.2",
+        "@radix-ui/react-context": "1.1.2",
+        "@radix-ui/react-direction": "1.1.1",
+        "@radix-ui/react-id": "1.1.1",
+        "@radix-ui/react-primitive": "2.1.3",
+        "@radix-ui/react-use-callback-ref": "1.1.1",
+        "@radix-ui/react-use-controllable-state": "1.2.2"
+      },
+      "peerDependencies": {
+        "@types/react": "*",
+        "@types/react-dom": "*",
+        "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc",
+        "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc"
+      },
+      "peerDependenciesMeta": {
+        "@types/react": {
+          "optional": true
+        },
+        "@types/react-dom": {
+          "optional": true
+        }
+      }
+    },
    "node_modules/@radix-ui/react-popover": {
      "version": "1.1.14",
      "resolved": "https://registry.npmjs.org/@radix-ui/react-popover/-/react-popover-1.1.14.tgz",
@@ -1465,31 +1742,6 @@
        }
      }
    },
-    "node_modules/@radix-ui/react-popover/node_modules/@radix-ui/react-focus-scope": {
-      "version": "1.1.7",
-      "resolved": "https://registry.npmjs.org/@radix-ui/react-focus-scope/-/react-focus-scope-1.1.7.tgz",
-      "integrity": "sha512-t2ODlkXBQyn7jkl6TNaw/MtVEVvIGelJDCG41Okq/KwUsJBwQ4XVZsHAVUkK4mBv3ewiAS3PGuUWuY2BoK4ZUw==",
-      "license": "MIT",
-      "dependencies": {
-        "@radix-ui/react-compose-refs": "1.1.2",
-        "@radix-ui/react-primitive": "2.1.3",
-        "@radix-ui/react-use-callback-ref": "1.1.1"
-      },
-      "peerDependencies": {
-        "@types/react": "*",
-        "@types/react-dom": "*",
-        "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc",
-        "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc"
-      },
-      "peerDependenciesMeta": {
-        "@types/react": {
-          "optional": true
-        },
-        "@types/react-dom": {
-          "optional": true
-        }
-      }
-    },
    "node_modules/@radix-ui/react-popover/node_modules/@radix-ui/react-popper": {
      "version": "1.2.7",
      "resolved": "https://registry.npmjs.org/@radix-ui/react-popper/-/react-popper-1.2.7.tgz",
--- a/web/package.json
+++ b/web/package.json
@@ -5,6 +5,7 @@
  "scripts": {
    "dev": "next dev --turbopack",
    "dev:local": "NEXT_PUBLIC_API_BASE_URL=http://localhost:5300 next dev --turbopack",
+    "dev:local:win": "set NEXT_PUBLIC_API_BASE_URL=http://localhost:5300&&next dev --turbopack",
    "build": "next build",
    "start": "next start",
    "lint": "next lint",
@@ -16,6 +17,9 @@
      "prettier --write"
    ]
  },
+  "overrides": {
+    "@radix-ui/react-focus-scope": "1.1.7"
+  },
  "dependencies": {
    "@dnd-kit/core": "^6.3.1",
    "@dnd-kit/sortable": "^10.0.0",
--- a/web/src/app/home/bots/BotDetailDialog.tsx
+++ b/web/src/app/home/bots/BotDetailDialog.tsx
@@ -127,7 +127,6 @@ export default function BotDetailDialog({
                <BotForm
                  initBotId={undefined}
                  onFormSubmit={handleFormSubmit}
-                  onFormCancel={handleFormCancel}
                  onBotDeleted={handleBotDeleted}
                  onNewBotCreated={handleNewBotCreated}
                />
@@ -198,7 +197,6 @@ export default function BotDetailDialog({
                  <BotForm
                    initBotId={botId}
                    onFormSubmit={handleFormSubmit}
-                    onFormCancel={handleFormCancel}
                    onBotDeleted={handleBotDeleted}
                    onNewBotCreated={handleNewBotCreated}
                  />
--- a/web/src/app/home/bots/components/bot-form/BotForm.tsx
+++ b/web/src/app/home/bots/components/bot-form/BotForm.tsx
@@ -64,13 +64,11 @@ const getFormSchema = (t: (key: string) => string) =>
 export default function BotForm({
  initBotId,
  onFormSubmit,
-  onFormCancel,
  onBotDeleted,
  onNewBotCreated,
 }: {
  initBotId?: string;
  onFormSubmit: (value: z.infer<ReturnType<typeof getFormSchema>>) => void;
-  onFormCancel: () => void;
  onBotDeleted: () => void;
  onNewBotCreated: (botId: string) => void;
 }) {
--- a/web/src/app/home/components/dynamic-form/DynamicFormComponent.tsx
+++ b/web/src/app/home/components/dynamic-form/DynamicFormComponent.tsx
@@ -50,6 +50,9 @@ export default function DynamicFormComponent({
          case 'llm-model-selector':
            fieldSchema = z.string();
            break;
+          case 'knowledge-base-selector':
+            fieldSchema = z.string();
+            break;
          case 'prompt-editor':
            fieldSchema = z.array(
              z.object({
--- a/Show More
+++ b/Show More