feat: vision model (#489 )

* mongo init * perf: mongo connect * perf: tts perf: whisper and tts peref: tts whisper permission log reabase (#488) * perf: modal * i18n * perf: schema lean * feat: vision model format * perf: tts loading * perf: static data * perf: tts * feat: image * perf: image * perf: upload image and title * perf: image size * doc * perf: color * doc * speaking can not select file * doc
add image input (#486 )
2023-11-18 15:42:35 +08:00 · 2023-11-17 18:22:29 +08:00 · 2023-11-17 17:15:41 +08:00 · 2023-11-17 00:03:05 +08:00 · 2023-11-16 17:10:04 +08:00 · 2023-11-16 16:22:08 +08:00
608 changed files with 19159 additions and 9572 deletions
--- a/.github/ISSUE_TEMPLATE/bugs.md
+++ b/.github/ISSUE_TEMPLATE/bugs.md
@@ -11,7 +11,7 @@ assignees: ''
 [//]: # '方框内填 x 表示打钩'

 - [ ] 我已确认目前没有类似 issue
- [ ] 我已完整查看过项目 README，以及[项目文档](https://doc.fastgpt.run/docs/intro/)
+- [ ] 我已完整查看过项目 README，以及[项目文档](https://doc.fastgpt.in/docs/intro/)
 - [ ] 我使用了自己的 key，并确认我的 key 是可正常使用的
 - [ ] 我理解并愿意跟进此 issue，协助测试和提供反馈
 - [x] 我理解并认可上述内容，并理解项目维护者精力有限，**不遵循规则的 issue 可能会被无视或直接关闭**
--- a/.github/ISSUE_TEMPLATE/config.yml
+++ b/.github/ISSUE_TEMPLATE/config.yml
@@ -1,5 +1,5 @@
 blank_issues_enabled: false
 contact_links:
  - name: 微信交流群
-    url: https://doc.fastgpt.run/wechat-fastgpt.webp
+    url: https://doc.fastgpt.in/wechat-fastgpt.webp
    about: FastGPT 全是问题群
--- a/.github/workflows/fastgpt-image-personal.yml
+++ b/.github/workflows/fastgpt-image-personal.yml
@@ -0,0 +1,52 @@
+name: Build FastGPT images in Personal warehouse
+on:
+  workflow_dispatch:
+  push:
+    paths:
+      - 'projects/app/**'
+      - 'packages/**'
+    branches:
+      - 'main'
+jobs:
+  build-fastgpt-images:
+    runs-on: ubuntu-20.04
+    if: github.repository != 'labring/FastGPT'
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v2
+        with:
+          driver-opts: network=host
+      - name: Cache Docker layers
+        uses: actions/cache@v3
+        with:
+          path: /tmp/.buildx-cache
+          key: ${{ runner.os }}-buildx-${{ github.sha }}
+          restore-keys: |
+            ${{ runner.os }}-buildx-
+      - name: Login to GitHub Container Registry
+        uses: docker/login-action@v2
+        with:
+          registry: ghcr.io
+          username: ${{ github.repository_owner }}
+          password: ${{ secrets.GH_PAT }}
+      - name: Set DOCKER_REPO_TAGGED based on branch or tag
+        run: |
+          echo "DOCKER_REPO_TAGGED=ghcr.io/${{ github.repository_owner }}/fastgpt:latest" >> $GITHUB_ENV
+      - name: Build and publish image for main branch or tag push event
+        env:
+          DOCKER_REPO_TAGGED: ${{ env.DOCKER_REPO_TAGGED }}
+        run: |
+          docker buildx build \
+          --build-arg name=app \
+          --label "org.opencontainers.image.source=https://github.com/${{ github.repository_owner }}/FastGPT" \
+          --label "org.opencontainers.image.description=fastgpt image" \
+          --push \
+          --cache-from=type=local,src=/tmp/.buildx-cache \
+          --cache-to=type=local,dest=/tmp/.buildx-cache \
+          -t ${DOCKER_REPO_TAGGED} \
+          -f Dockerfile \
+          .
--- a/.github/workflows/fastgpt-image.yml
+++ b/.github/workflows/fastgpt-image.yml
@@ -5,8 +5,6 @@ on:
    paths:
      - 'projects/app/**'
      - 'packages/**'
-    branches:
-      - 'main'
    tags:
      - 'v*.*.*'
 jobs:
@@ -53,9 +51,8 @@ jobs:
          docker buildx build \
          --build-arg name=app \
          --platform linux/amd64,linux/arm64 \
-          --label "org.opencontainers.image.source=  https://github.com/  ${{ github.repository_owner }}/FastGPT" \
+          --label "org.opencontainers.image.source=https://github.com/${{ github.repository_owner }}/FastGPT" \
          --label "org.opencontainers.image.description=fastgpt image" \
-          --label "org.opencontainers.image.licenses=Apache" \
          --push \
          --cache-from=type=local,src=/tmp/.buildx-cache \
          --cache-to=type=local,dest=/tmp/.buildx-cache \
--- a/.github/workflows/preview-image.yml
+++ b/.github/workflows/preview-image.yml
@@ -24,7 +24,7 @@ jobs:
        with:
          driver-opts: network=host
      - name: Cache Docker layers
-        uses: actions/cache@v2
+        uses: actions/cache@v3
        with:
          path: /tmp/.buildx-cache
          key: ${{ runner.os }}-buildx-${{ github.sha }}
@@ -48,6 +48,7 @@ jobs:
          --label "org.opencontainers.image.source=  https://github.com/  ${{ github.repository_owner }}/FastGPT" \
          --label "org.opencontainers.image.description=fastgpt-pr image" \
          --label "org.opencontainers.image.licenses=Apache" \
+          --push \
          --cache-from=type=local,src=/tmp/.buildx-cache \
          --cache-to=type=local,dest=/tmp/.buildx-cache \
          -t ${DOCKER_REPO_TAGGED} \
--- a/README.md
+++ b/README.md
@@ -17,10 +17,10 @@ FastGPT 是一个基于 LLM 大语言模型的知识库问答系统，提供开
  <a href="https://fastgpt.run/">
    <img height="21" src="https://img.shields.io/badge/在线使用-d4eaf7?style=flat-square&logo=spoj&logoColor=7d09f1" alt="cloud">
  </a>
-  <a href="https://doc.fastgpt.run/docs/intro">
+  <a href="https://doc.fastgpt.in/docs/intro">
    <img height="21" src="https://img.shields.io/badge/相关文档-7d09f1?style=flat-square" alt="document">
  </a>
-  <a href="https://doc.fastgpt.run/docs/development">
+  <a href="https://doc.fastgpt.in/docs/development">
    <img height="21" src="https://img.shields.io/badge/本地开发-%23d4eaf7?style=flat-square&logo=xcode&logoColor=7d09f1" alt="development">
  </a>
  <a href="/#-%E7%9B%B8%E5%85%B3%E9%A1%B9%E7%9B%AE">
@@ -43,11 +43,15 @@ https://github.com/labring/FastGPT/assets/15308462/7d3a38df-eb0e-4388-9250-2409b
 | ![Demo](./.github/imgs/intro1.png) | ![Demo](./.github/imgs/intro2.png) |
 | ![Demo](./.github/imgs/intro3.png) | ![Demo](./.github/imgs/intro4.png) |

+<a href="#readme">
+    <img src="https://img.shields.io/badge/-返回顶部-7d09f1.svg" alt="#" align="right">
+</a>
+
 ## 💡 功能

 1. 强大的可视化编排，轻松构建 AI 应用
   - [x] 提供简易模式，无需操作编排
-   - [x] 用户对话前引导, 全局字符串变量
+   - [x] 用户对话前引导，全局字符串变量
   - [x] 知识库搜索
   - [x] 多 LLM 模型对话
   - [x] 文本内容提取成结构化数据
@@ -56,12 +60,12 @@ https://github.com/labring/FastGPT/assets/15308462/7d3a38df-eb0e-4388-9250-2409b
   - [x] 对话下一步指引
   - [ ] 对话多路线选择
   - [x] 源文件引用追踪
-   - [ ] 自定义文件阅读器
+   - [x] 模块封装，实现多级复用
 2. 丰富的知识库预处理
   - [x] 多库复用，混用
   - [x] chunk 记录修改和删除
-   - [x] 支持 手动输入, 直接分段, QA 拆分导入
-   - [x] 支持 url 读取、 CSV 批量导入
+   - [x] 支持手动输入，直接分段，QA 拆分导入
+   - [x] 支持 url 读取、CSV 批量导入
   - [x] 支持知识库单独设置向量模型
   - [x] 源文件存储
   - [ ] 文件学习 Agent
@@ -71,16 +75,20 @@ https://github.com/labring/FastGPT/assets/15308462/7d3a38df-eb0e-4388-9250-2409b
   - [x] 完整上下文呈现
   - [x] 完整模块中间值呈现
 4. OpenAPI
-   - [x] completions 接口（对齐 GPT 接口）
+   - [x] completions 接口 (对齐 GPT 接口)
   - [ ] 知识库 CRUD
 5. 运营功能
   - [x] 免登录分享窗口
   - [x] Iframe 一键嵌入
   - [x] 统一查阅对话记录，并对数据进行标注

+<a href="#readme">
+    <img src="https://img.shields.io/badge/-返回顶部-7d09f1.svg" alt="#" align="right">
+</a>
+
 ## 👨‍💻 开发

-项目技术栈: NextJs + TS + ChakraUI + Mongo + Postgres（Vector 插件）
+项目技术栈：NextJs + TS + ChakraUI + Mongo + Postgres (Vector 插件)

 - **⚡ 快速部署**

@@ -90,12 +98,17 @@ https://github.com/labring/FastGPT/assets/15308462/7d3a38df-eb0e-4388-9250-2409b

  由于需要部署数据库，部署完后需要等待 2~4 分钟才能正常访问。默认用了最低配置，首次访问时会有些慢。

-* [快开始本地开发](https://doc.fastgpt.run/docs/development/intro/)
-* [部署 FastGPT](https://doc.fastgpt.run/docs/installation)
-* [系统配置文件说明](https://doc.fastgpt.run/docs/development/configuration/)
-* [多模型配置](https://doc.fastgpt.run/docs/installation/one-api/)
-* [版本更新/升级介绍](https://doc.fastgpt.run/docs/installation/upgrading)
-* [API 文档](https://doc.fastgpt.run/docs/development/openapi/)
+* [快开始本地开发](https://doc.fastgpt.in/docs/development/intro/)
+* [部署 FastGPT](https://doc.fastgpt.in/docs/installation)
+* [系统配置文件说明](https://doc.fastgpt.in/docs/development/configuration/)
+* [多模型配置](https://doc.fastgpt.in/docs/installation/one-api/)
+* [版本更新/升级介绍](https://doc.fastgpt.in/docs/installation/upgrading)
+* [OpenAPI API 文档](https://doc.fastgpt.in/docs/development/openapi/)
+* [知识库结构详解](https://doc.fastgpt.in/docs/use-cases/datasetengine/)
+
+<a href="#readme">
+    <img src="https://img.shields.io/badge/-返回顶部-7d09f1.svg" alt="#" align="right">
+</a>

 ## 🏘️ 社区交流群

@@ -103,12 +116,20 @@ https://github.com/labring/FastGPT/assets/15308462/7d3a38df-eb0e-4388-9250-2409b

 ![](https://otnvvf-imgs.oss.laf.run/wx300.jpg)

+<a href="#readme">
+    <img src="https://img.shields.io/badge/-返回顶部-7d09f1.svg" alt="#" align="right">
+</a>
+
 ## 💪 相关项目

- [Laf: 3 分钟快速接入三方应用](https://github.com/labring/laf)
- [Sealos: 快速部署集群应用](https://github.com/labring/sealos)
- [One API: 多模型管理，支持 Azure、文心一言等](https://github.com/songquanpeng/one-api)
- [TuShan: 5 分钟搭建后台管理系统](https://github.com/msgbyte/tushan)
+- [Laf：3 分钟快速接入三方应用](https://github.com/labring/laf)
+- [Sealos：快速部署集群应用](https://github.com/labring/sealos)
+- [One API：多模型管理，支持 Azure、文心一言等](https://github.com/songquanpeng/one-api)
+- [TuShan：5 分钟搭建后台管理系统](https://github.com/msgbyte/tushan)
+
+<a href="#readme">
+    <img src="https://img.shields.io/badge/-返回顶部-7d09f1.svg" alt="#" align="right">
+</a>

 ## 👀 其他

@@ -116,19 +137,31 @@ https://github.com/labring/FastGPT/assets/15308462/7d3a38df-eb0e-4388-9250-2409b
 - [接入飞书](https://www.bilibili.com/video/BV1Su4y1r7R3/?spm_id_from=333.999.0.0)
 - [接入企微](https://www.bilibili.com/video/BV1Tp4y1n72T/?spm_id_from=333.999.0.0)

+<a href="#readme">
+    <img src="https://img.shields.io/badge/-返回顶部-7d09f1.svg" alt="#" align="right">
+</a>
+
 ## 🤝 第三方生态

- [OnWeChat 个人微信/企微机器人](https://doc.fastgpt.run/docs/use-cases/onwechat/)
+- [OnWeChat 个人微信/企微机器人](https://doc.fastgpt.in/docs/use-cases/onwechat/)
+
+<a href="#readme">
+    <img src="https://img.shields.io/badge/-返回顶部-7d09f1.svg" alt="#" align="right">
+</a>

 ## 🌟 Star History

 [![Star History Chart](https://api.star-history.com/svg?repos=labring/FastGPT&type=Date)](https://star-history.com/#labring/FastGPT&Date)

+<a href="#readme">
+    <img src="https://img.shields.io/badge/-返回顶部-7d09f1.svg" alt="#" align="right">
+</a>
+
 ## 使用协议

 本仓库遵循 [FastGPT Open Source License](./LICENSE) 开源协议。

 1. 允许作为后台服务直接商用，但不允许提供 SaaS 服务。
-2. 需保留相关版权信息。
+2. 未经商业授权，任何形式的商用服务均需保留相关版权信息。
 3. 完整请查看 [FastGPT Open Source License](./LICENSE)
-4. 联系方式：yujinlong@sealos.io, [点击查看定价策略](https://doc.fastgpt.run/docs/commercial)
+4. 联系方式：yujinlong@sealos.io，[点击查看商业版定价策略](https://doc.fastgpt.in/docs/commercial)
--- a/README_en.md
+++ b/README_en.md
@@ -41,6 +41,10 @@ https://github.com/labring/FastGPT/assets/15308462/7d3a38df-eb0e-4388-9250-2409b
 | ![Demo](./.github/imgs/intro1.png) | ![Demo](./.github/imgs/intro2.png) |
 | ![Demo](./.github/imgs/intro3.png) | ![Demo](./.github/imgs/intro4.png) |

+<a href="#readme">
+    <img src="https://img.shields.io/badge/-Back_to_Top-7d09f1.svg" alt="#" align="right">
+</a>
+
 ## 💡 Features

 1. Powerful visual workflows: Effortlessly craft AI applications
@@ -54,9 +58,9 @@ https://github.com/labring/FastGPT/assets/15308462/7d3a38df-eb0e-4388-9250-2409b
   - [x] Extend with HTTP
   - [ ] Embed Laf for on-the-fly HTTP module crafting
   - [x] Directions for the next dialogue steps
-   - [ ] Multiple dialogue paths selection
   - [x] Tracking source file references
   - [ ] Custom file reader
+   - [ ] Modules are packaged into plug-ins to achieve reuse

 2. Extensive knowledge base preprocessing

@@ -86,6 +90,10 @@ https://github.com/labring/FastGPT/assets/15308462/7d3a38df-eb0e-4388-9250-2409b
   - [x] One-click embedding with Iframe
   - [ ] Unified access to dialogue records

+<a href="#readme">
+    <img src="https://img.shields.io/badge/-Back_to_Top-7d09f1.svg" alt="#" align="right">
+</a>
+
 ## 👨‍💻 Development

 Project tech stack: NextJs + TS + ChakraUI + Mongo + Postgres (Vector plugin)
@@ -111,6 +119,10 @@ Project tech stack: NextJs + TS + ChakraUI + Mongo + Postgres (Vector plugin)
 | ------------------------------------------------- | ---------------------------------------------- |
 | ![](https://otnvvf-imgs.oss.laf.run/wxqun300.jpg) | ![](https://otnvvf-imgs.oss.laf.run/wx300.jpg) | -->

+<a href="#readme">
+    <img src="https://img.shields.io/badge/-Back_to_Top-7d09f1.svg" alt="#" align="right">
+</a>
+
 ## 👀 Others

 - [FastGPT FAQ](https://kjqvjse66l.feishu.cn/docx/HtrgdT0pkonP4kxGx8qcu6XDnGh)
@@ -118,6 +130,10 @@ Project tech stack: NextJs + TS + ChakraUI + Mongo + Postgres (Vector plugin)
 - [Official Account Integration Video Tutorial](https://www.bilibili.com/video/BV1xh4y1t7fy/)
 - [FastGPT Knowledge Base Demo](https://www.bilibili.com/video/BV1Wo4y1p7i1/)

+<a href="#readme">
+    <img src="https://img.shields.io/badge/-Back_to_Top-7d09f1.svg" alt="#" align="right">
+</a>
+
 ## 💪 Related Projects

 - [Laf: 3-minute quick access to third-party applications](https://github.com/labring/laf)
@@ -125,10 +141,18 @@ Project tech stack: NextJs + TS + ChakraUI + Mongo + Postgres (Vector plugin)
 - [One API: Multi-model management, supports Azure, Wenxin Yiyuan, etc.](https://github.com/songquanpeng/one-api)
 - [TuShan: Build a backend management system in 5 minutes](https://github.com/msgbyte/tushan)

+<a href="#readme">
+    <img src="https://img.shields.io/badge/-Back_to_Top-7d09f1.svg" alt="#" align="right">
+</a>
+
 ## 🤝 Third-party Ecosystem

 - [luolinAI: Enterprise WeChat bot, ready to use](https://github.com/luolin-ai/FastGPT-Enterprise-WeChatbot)

+<a href="#readme">
+    <img src="https://img.shields.io/badge/-Back_to_Top-7d09f1.svg" alt="#" align="right">
+</a>
+
 ## 🌟 Star History

 [![Star History Chart](https://api.star-history.com/svg?repos=labring/FastGPT&type=Date)](https://star-history.com/#labring/FastGPT&Date)
--- a/docSite/.zhlintignore
+++ b/docSite/.zhlintignore
@@ -0,0 +1 @@
+*.html
--- a/docSite/.zhlintrc
+++ b/docSite/.zhlintrc
@@ -0,0 +1,6 @@
+{
+  "preset": "default",
+  "rules": {
+    "adjustedFullWidthPunctuation": ""
+  }
+}
--- a/docSite/README.md
+++ b/docSite/README.md
@@ -3,7 +3,7 @@
 ## 本地运行

 1. 安装 go 语言环境。
-2. 安装 hugo。 [二进制下载](https://github.com/gohugoio/hugo/releases/tag/v0.117.0)，注意需要安装 extended 版本。
+2. 安装 hugo。[二进制下载](https://github.com/gohugoio/hugo/releases/tag/v0.117.0)，注意需要安装 extended 版本。
 3. cd docSite
 4. hugo serve
 5. 访问 http://localhost:1313
--- a/docSite/assets/imgs/datasetEngine1.png
+++ b/docSite/assets/imgs/datasetEngine1.png
--- a/docSite/assets/imgs/datasetEngine10.png
+++ b/docSite/assets/imgs/datasetEngine10.png
--- a/docSite/assets/imgs/datasetEngine11.png
+++ b/docSite/assets/imgs/datasetEngine11.png
--- a/docSite/assets/imgs/datasetEngine2.png
+++ b/docSite/assets/imgs/datasetEngine2.png
--- a/docSite/assets/imgs/datasetEngine3.png
+++ b/docSite/assets/imgs/datasetEngine3.png
--- a/docSite/assets/imgs/datasetEngine4.png
+++ b/docSite/assets/imgs/datasetEngine4.png
--- a/docSite/assets/imgs/datasetEngine5.png
+++ b/docSite/assets/imgs/datasetEngine5.png
--- a/docSite/assets/imgs/datasetEngine6.png
+++ b/docSite/assets/imgs/datasetEngine6.png
--- a/docSite/assets/imgs/datasetEngine7.png
+++ b/docSite/assets/imgs/datasetEngine7.png
--- a/docSite/assets/imgs/datasetEngine8.png
+++ b/docSite/assets/imgs/datasetEngine8.png
--- a/docSite/assets/imgs/datasetEngine9.png
+++ b/docSite/assets/imgs/datasetEngine9.png
--- a/docSite/assets/imgs/datasetSetting1.png
+++ b/docSite/assets/imgs/datasetSetting1.png
--- a/docSite/assets/imgs/datasetprompt1.png
+++ b/docSite/assets/imgs/datasetprompt1.png
--- a/docSite/assets/imgs/datasetprompt2.png
+++ b/docSite/assets/imgs/datasetprompt2.png
--- a/docSite/assets/imgs/datasetprompt3.png
+++ b/docSite/assets/imgs/datasetprompt3.png
--- a/docSite/assets/imgs/datasetprompt4.png
+++ b/docSite/assets/imgs/datasetprompt4.png
--- a/docSite/assets/imgs/datasetprompt5.png
+++ b/docSite/assets/imgs/datasetprompt5.png
--- a/docSite/assets/imgs/datasetprompt6.png
+++ b/docSite/assets/imgs/datasetprompt6.png
--- a/docSite/assets/imgs/datasetprompt7.png
+++ b/docSite/assets/imgs/datasetprompt7.png
--- a/docSite/assets/imgs/datasetprompt8.png
+++ b/docSite/assets/imgs/datasetprompt8.png
--- a/docSite/assets/imgs/datasetprompt9.png
+++ b/docSite/assets/imgs/datasetprompt9.png
--- a/docSite/assets/imgs/wechat1.png
+++ b/docSite/assets/imgs/wechat1.png
--- a/docSite/assets/imgs/wechat10.png
+++ b/docSite/assets/imgs/wechat10.png
--- a/docSite/assets/imgs/wechat2.png
+++ b/docSite/assets/imgs/wechat2.png
--- a/docSite/assets/imgs/wechat3.png
+++ b/docSite/assets/imgs/wechat3.png
--- a/docSite/assets/imgs/wechat4.png
+++ b/docSite/assets/imgs/wechat4.png
--- a/docSite/assets/imgs/wechat5.png
+++ b/docSite/assets/imgs/wechat5.png
--- a/docSite/assets/imgs/wechat6.png
+++ b/docSite/assets/imgs/wechat6.png
--- a/docSite/assets/imgs/wechat7.png
+++ b/docSite/assets/imgs/wechat7.png
--- a/docSite/assets/imgs/wechat8.png
+++ b/docSite/assets/imgs/wechat8.png
--- a/docSite/assets/imgs/wechat9.png
+++ b/docSite/assets/imgs/wechat9.png
--- a/docSite/content/docs/development/configuration.md
+++ b/docSite/content/docs/development/configuration.md
@@ -21,62 +21,76 @@ weight: 520
 ```json
 {
  "SystemParams": {
+    "pluginBaseUrl": "", // 商业版接口地址
    "vectorMaxProcess": 15, // 向量生成最大进程，结合数据库性能和 key 来设置
    "qaMaxProcess": 15,  // QA 生成最大进程，结合数据库性能和 key 来设置
-    "pgHNSWEfSearch": 40  // pg vector 索引参数，越大精度高但速度慢
+    "pgHNSWEfSearch": 100  // pg vector 索引参数，越大精度高但速度慢
  },
  "ChatModels": [
    {
-      "model": "gpt-3.5-turbo", // 实际调用的模型
-      "name": "GPT35-4k", // 展示的名字
-      "maxToken": 4000, // 最大token，均按 gpt35 计算
-      "quoteMaxToken": 2000, // 引用内容最大 token
-      "maxTemperature": 1.2, // 最大温度
-      "price": 0,
+      "model": "gpt-3.5-turbo-1106",
+      "name": "GPT35-1106",
+      "price": 0, // 除以 100000 后等于1个token的价格
+      "maxContext": 16000, // 最大上下文长度
+      "maxResponse": 4000, // 最大回复长度
+      "quoteMaxToken": 2000, // 最大引用内容长度
+      "maxTemperature": 1.2, // 最大温度值
+      "censor": false, // 是否开启敏感词过滤(商业版)
+      "vision": false, // 支持图片输入
      "defaultSystemChatPrompt": ""
    },
    {
      "model": "gpt-3.5-turbo-16k",
      "name": "GPT35-16k",
-      "maxToken": 16000,
+      "maxContext": 16000,
+      "maxResponse": 16000,
+      "price": 0,
      "quoteMaxToken": 8000,
      "maxTemperature": 1.2,
-      "price": 0,
+      "censor": false,
+      "vision": false,
      "defaultSystemChatPrompt": ""
    },
    {
      "model": "gpt-4",
      "name": "GPT4-8k",
-      "maxToken": 8000,
+      "maxContext": 8000,
+      "maxResponse": 8000,
+      "price": 0,
      "quoteMaxToken": 4000,
      "maxTemperature": 1.2,
+      "censor": false,
+      "vision": false,
+      "defaultSystemChatPrompt": ""
+    },
+    {
+      "model": "gpt-4-vision-preview",
+      "name": "GPT4-Vision",
+      "maxContext": 128000,
+      "maxResponse": 4000,
      "price": 0,
+      "quoteMaxToken": 100000,
+      "maxTemperature": 1.2,
+      "censor": false,
+      "vision": true,
      "defaultSystemChatPrompt": ""
    }
  ],
-  "QAModels": [ // QA 拆分模型
-    { 
+  "QAModels": [
+    {
      "model": "gpt-3.5-turbo-16k",
      "name": "GPT35-16k",
-      "maxToken": 16000,
+      "maxContext": 16000,
+      "maxResponse": 16000,
      "price": 0
    }
  ],
-  "ExtractModels": [ // 内容提取模型
-    { 
-      "model": "gpt-3.5-turbo-16k",
-      "name": "GPT35-16k",
-      "maxToken": 16000, 
-      "price": 0,
-      "functionCall": true, // 是否支持 function call
-      "functionPrompt": "" // 自定义非 function call 提示词
-    }
-  ],
-  "CQModels": [ // Classify Question: 问题分类模型
+  "CQModels": [
    {
-      "model": "gpt-3.5-turbo-16k",
-      "name": "GPT35-16k",
-      "maxToken": 16000,
+      "model": "gpt-3.5-turbo-1106",
+      "name": "GPT35-1106",
+      "maxContext": 16000,
+      "maxResponse": 4000,
      "price": 0,
      "functionCall": true,
      "functionPrompt": ""
@@ -84,17 +98,30 @@ weight: 520
    {
      "model": "gpt-4",
      "name": "GPT4-8k",
-      "maxToken": 8000,
+      "maxContext": 8000,
+      "maxResponse": 8000,
      "price": 0,
      "functionCall": true,
      "functionPrompt": ""
    }
  ],
-  "QGModels": [ // Question Generation: 生成下一步指引模型
-    { 
-      "model": "gpt-3.5-turbo",
-      "name": "GPT35-4k",
-      "maxToken": 4000,
+  "ExtractModels": [
+    {
+      "model": "gpt-3.5-turbo-1106",
+      "name": "GPT35-1106",
+      "maxContext": 16000,
+      "maxResponse": 4000,
+      "price": 0,
+      "functionCall": true,
+      "functionPrompt": ""
+    }
+  ],
+  "QGModels": [
+    {
+      "model": "gpt-3.5-turbo-1106",
+      "name": "GPT35-1106",
+      "maxContext": 1600,
+      "maxResponse": 4000,
      "price": 0
    }
  ],
@@ -102,10 +129,32 @@ weight: 520
    {
      "model": "text-embedding-ada-002",
      "name": "Embedding-2",
-      "price": 0,
-      "defaultToken": 500,
+      "price": 0.2,
+      "defaultToken": 700,
      "maxToken": 3000
    }
-  ]
+  ],
+  "AudioSpeechModels": [
+    {
+      "model": "tts-1",
+      "name": "OpenAI TTS1",
+      "price": 0,
+      "baseUrl": "",
+      "key": "",
+      "voices": [
+        { "label": "Alloy", "value": "alloy", "bufferId": "openai-Alloy" },
+        { "label": "Echo", "value": "echo", "bufferId": "openai-Echo" },
+        { "label": "Fable", "value": "fable", "bufferId": "openai-Fable" },
+        { "label": "Onyx", "value": "onyx", "bufferId": "openai-Onyx" },
+        { "label": "Nova", "value": "nova", "bufferId": "openai-Nova" },
+        { "label": "Shimmer", "value": "shimmer", "bufferId": "openai-Shimmer" }
+      ]
+    }
+  ],
+  "WhisperModel": {
+    "model": "whisper-1",
+    "name": "Whisper1",
+    "price": 0
+  }
 }
 ```
--- a/docSite/content/docs/development/intro.md
+++ b/docSite/content/docs/development/intro.md
@@ -54,7 +54,7 @@ git clone git@github.com:<github_username>/FastGPT.git

 **环境变量**

-复制.env.template 文件，生成一个.env.local 环境变量文件夹，修改.env.local 里内容才是有效的变量。变量说明见 .env.template
+复制.env.template 文件，在同级目录下生成一个.env.local 文件，修改.env.local 里内容才是有效的变量。变量说明见 .env.template

 **config 配置文件**

--- a/docSite/content/docs/development/openApi.md
+++ b/docSite/content/docs/development/openApi.md
@@ -393,7 +393,7 @@ curl --location --request POST 'https://fastgpt.run/api/core/dataset/searchTest'
 **请求示例**

 ```bash
-curl --location --request POST 'https://fastgpt.run/api/common/bill/createTrainingBill' \
+curl --location --request POST 'https://fastgpt.run/api/support/wallet/bill/createTrainingBill' \
 --header 'Authorization: Bearer {{apikey}}' \
 --header 'Content-Type: application/json' \
 --data-raw ''
--- a/docSite/content/docs/installation/one-api.md
+++ b/docSite/content/docs/installation/one-api.md
@@ -99,9 +99,9 @@ CHAT_API_KEY=sk-xxxxxx
    {
      "model": "ERNIE-Bot", // 这里的模型需要对应 One API 的模型
      "name": "文心一言", // 对外展示的名称
-      "maxToken": 4000, // 最大长下文 token，无论什么模型都按 GPT35 的计算。GPT 外的模型需要自行大致计算下这个值。可以调用官方接口去比对 Token 的倍率，然后在这里粗略计算。
+      "maxContext": 8000, // 最大长下文 token，无论什么模型都按 GPT35 的计算。GPT 外的模型需要自行大致计算下这个值。可以调用官方接口去比对 Token 的倍率，然后在这里粗略计算。
+      "maxResponse": 4000, // 最大回复 token
      // 例如：文心一言的中英文 token 基本是 1:1，而 GPT 的中文 Token 是 2:1，如果文心一言官方最大 Token 是 4000，那么这里就可以填 8000，保险点就填 7000.
-      "price": 0, // 1个token 价格 => 1.5 / 100000 * 1000 = 0.015元/1k token
      "quoteMaxToken": 2000, // 引用知识库的最大 Token
      "maxTemperature": 1, // 最大温度
      "defaultSystemChatPrompt": "" // 默认的系统提示词
--- a/docSite/content/docs/installation/upgrading/447.md
+++ b/docSite/content/docs/installation/upgrading/447.md
@@ -1,5 +1,5 @@
 ---
-title: 'V4.4.7'
+title: 'V4.4.7（需执行升级脚本）'
 description: 'FastGPT V4.4.7 更新（需执行升级脚本）'
 icon: 'upgrade'
 draft: false
--- a/docSite/content/docs/installation/upgrading/451.md
+++ b/docSite/content/docs/installation/upgrading/451.md
@@ -4,7 +4,7 @@ description: 'FastGPT V4.5.1 更新'
 icon: 'upgrade'
 draft: false
 toc: true
-weight: 839
+weight: 838
 ---

 ## 执行初始化 API
--- a/docSite/content/docs/installation/upgrading/452.md
+++ b/docSite/content/docs/installation/upgrading/452.md
@@ -0,0 +1,15 @@
+---
+title: 'V4.5.2'
+description: 'FastGPT V4.5.2 更新'
+icon: 'upgrade'
+draft: false
+toc: true
+weight: 837
+---
+
+## 功能介绍
+
+### Fast GPT V4.5.2
+
+1. 新增 - 模块插件，允许自行组装插件进行模块复用。
+2. 优化 - 知识库引用提示。
--- a/docSite/content/docs/installation/upgrading/46.md
+++ b/docSite/content/docs/installation/upgrading/46.md
@@ -0,0 +1,67 @@
+---
+title: 'V4.6(需要初始化)'
+description: 'FastGPT V4.6 更新'
+icon: 'upgrade'
+draft: false
+toc: true
+weight: 836
+---
+
+**V4.6 版本加入了简单的团队功能，可以邀请其他用户进来管理资源。该版本升级后无法执行旧的升级脚本，且无法回退。**
+
+## 1. 更新镜像并变更配置文件
+
+更新镜像至 latest 或者 v4.6 版本。商业版镜像更新至 V0.2.1
+
+最新配置可参考: [V46版本最新 config.json](/docs/development/configuration)，商业镜像配置文件也更新，参考最新的飞书文档。
+
+
+## 2. 执行初始化 API
+
+发起 2 个 HTTP 请求（{{rootkey}} 替换成环境变量里的`rootkey`，{{host}}替换成自己域名）
+
+**该初始化接口可能速度很慢，返回超时不用管，注意看日志即可，需要注意的是，需确保initv46成功后，在执行initv46-2**
+
+1. https://xxxxx/api/admin/initv46
+
+```bash
+curl --location --request POST 'https://{{host}}/api/admin/initv46' \
+--header 'rootkey: {{rootkey}}' \
+--header 'Content-Type: application/json'
+```
+
+2. https://xxxxx/api/admin/initv46-2
+
+```bash
+curl --location --request POST 'https://{{host}}/api/admin/initv46-2' \
+--header 'rootkey: {{rootkey}}' \
+--header 'Content-Type: application/json'
+```
+
+初始化内容：
+1. 创建默认团队
+2. 初始化 Mongo 所有资源的团队字段
+3. 初始化 Pg 的字段
+4. 初始化 Mongo Data
+
+
+## V4.6功能介绍
+
+1. 新增 - 团队空间
+2. 新增 - 多路向量（多个向量映射一组数据）
+3. 新增 - tts语音
+4. 新增 - 支持知识库配置文本预处理模型
+5. 线上环境新增 - ReRank向量召回，提高召回精度
+6. 优化 - 知识库导出，可直接触发流下载，无需等待转圈圈
+
+## 4.6缺陷修复
+
+旧的 4.6 版本由于缺少一个字段，导致文件导入时知识库数据无法显示，可执行下面的脚本：
+
+https://xxxxx/api/admin/initv46-fix
+
+```bash
+curl --location --request POST 'https://{{host}}/api/admin/initv46-fix' \
+--header 'rootkey: {{rootkey}}' \
+--header 'Content-Type: application/json'
+```
--- a/docSite/content/docs/installation/upgrading/461.md
+++ b/docSite/content/docs/installation/upgrading/461.md
@@ -0,0 +1,16 @@
+---
+title: 'V4.6.1'
+description: 'FastGPT V4.6 .1'
+icon: 'upgrade'
+draft: false
+toc: true
+weight: 835
+---
+
+
+## V4.6.1 功能介绍
+
+1. 新增 - GPT4-v 模型支持
+2. 新增 - whisper 语音输入
+3. 优化 - TTS 流传输
+4. 优化 - TTS 缓存
--- a/docSite/content/docs/pricing.md
+++ b/docSite/content/docs/pricing.md
@@ -1,10 +1,10 @@
 ---
-title: '定价'
-description: 'FastGPT 的定价'
+title: '线上版定价'
+description: 'FastGPT 线上版定价'
 icon: 'currency_yen'
 draft: false
 toc: true
-weight: 10
+weight: 11
 ---

 ## Tokens 说明
@@ -15,7 +15,7 @@ weight: 10

 ## FastGPT 线上计费

-目前，FastGPT 线上计费也仅按 Tokens 使用数量为准。以下是详细的计费表（最新定价以线上表格为准，可在点击充值后实时获取）：
+使用: [https://fastgpt.run](https://fastgpt.run) 或  [https://ai.fastgpt.in](https://ai.fastgpt.in) 只需仅按 Tokens 使用数量扣费即可。可在 账号-使用记录 中查看具体使用情况，以下是详细的计费表（最新定价以线上表格为准，可在点击充值后实时获取）：

 {{< table "table-hover table-striped-columns" >}}
 | 计费项                 | 价格: 元/ 1K tokens（包含上下文） |
--- a/docSite/content/docs/use-cases/ai_settings.md
+++ b/docSite/content/docs/use-cases/ai_settings.md
@@ -9,23 +9,23 @@ weight: 310

 在 FastGPT 的 AI 对话模块中，有一个 AI 高级配置，里面包含了 AI 模型的参数配置，本文详细介绍这些配置的含义。

-# 返回AI内容
+## 返回AI内容

 这是一个开关，打开的时候，当 AI 对话模块运行时，会将其输出的内容返回到浏览器（API响应）；如果关闭，AI 输出的内容不会返回到浏览器，但是生成的内容仍可以通过【AI回复】进行输出。你可以将【AI回复】连接到其他模块中。

-# 温度
+## 温度

 可选范围0-10，约大代表生成的内容约自由扩散，越小代表约严谨。调节能力有限，知识库问答场景通常设置为0。

-# 回复上限
+## 回复上限

 控制 AI 回复的最大 Tokens，较小的值可以一定程度上减少 AI 的废话，但也可能导致 AI 回复不完整。

-# 引用模板 & 引用提示词
+## 引用模板 & 引用提示词

 这两个参数与知识库问答场景相关，可以控制知识库相关的提示词。

-## AI 对话消息组成
+### AI 对话消息组成

 想使用明白这两个变量，首先要了解传递传递给 AI 模型的消息格式。它是一个数组，FastGPT 中这个数组的组成形式为：

@@ -39,16 +39,18 @@ weight: 310
 ```

 {{% alert icon="🍅" context="success" %}}
-Tips: 可以通过点击上下文按键查看完整的
+Tips: 可以通过点击上下文按键查看完整的上下文组成，便于调试。
 {{% /alert %}}

-## 引用模板和提示词设计
+### 引用模板和提示词设计

 引用模板和引用提示词通常是成对出现，引用提示词依赖引用模板。

-FastGPT 知识库采用 QA 对(不一定都是问答格式，仅代表两个变量)的格式存储，在转义成字符串时候会根据**引用模板**来进行格式化。知识库包含 3 个变量： q, a, file_id, index, source，可以通过 {{q}} {{a}} {{file_id}} {{index}} {{source}} 按需引入。下面一个模板例子：
+FastGPT 知识库采用 QA 对(不一定都是问答格式，仅代表两个变量)的格式存储，在转义成字符串时候会根据**引用模板**来进行格式化。知识库包含多个可用变量： q, a, sourceId（数据的ID）, index(第n个数据), source(数据的集合名、文件名)，score(距离得分，0-1) 可以通过 {{q}} {{a}} {{sourceId}} {{index}} {{source}} {{score}} 按需引入。下面一个模板例子：

-**引用模板**
+可以通过 [知识库结构讲解](/docs/use-cases/datasetEngine/) 了解详细的知识库的结构。
+
+#### 引用模板

 ```
 {instruction:"{{q}}",output:"{{a}}",source:"{{source}}"}
@@ -62,7 +64,7 @@ FastGPT 知识库采用 QA 对(不一定都是问答格式，仅代表两个变
 {instruction:"电影《铃芽之旅》的编剧是谁？22",output:"新海诚是本片的编剧。",source:"手动输入"}
 ```

-**引用提示词**
+#### 引用提示词

 引用模板需要和引用提示词一起使用，提示词中可以写引用模板的格式说明以及对话的要求等。可以使用 {{quote}} 来使用 **引用模板**，使用 {{question}} 来引入问题。例如：

@@ -91,4 +93,42 @@ FastGPT 知识库采用 QA 对(不一定都是问答格式，仅代表两个变
 2. 使用背景知识回答问题。
 3. 背景知识无法回答问题时，你可以礼貌的的回答用户问题。
 我的问题是:"{{question}}"
-```
+```
+
+#### 总结
+
+引用模板规定了搜索出来的内容如何组成一句话，其由 q,a,index,source 多个变量组成。
+
+引用提示词由`引用模板`和`提示词`组成，提示词通常是对引用模板的一个描述，加上对模型的要求。
+
+### 引用模板和提示词设计 示例
+
+#### 通用模板与问答模板对比
+
+我们通过一组`你是谁`的手动数据，对通用模板与问答模板的效果进行对比。此处特意打了个搞笑的答案，通用模板下 GPT35 就变得不那么听话了，而问答模板下 GPT35 依然能够回答正确。这是由于结构化的提示词，在大语言模型中具有更强的引导作用。
+
+{{% alert icon="🍅" context="success" %}}
+Tips: 建议根据不同的场景，每种知识库仅选择1类数据类型，这样有利于充分发挥提示词的作用。
+{{% /alert %}}
+
+| 通用模板配置及效果 | 问答模板配置及效果 |
+| --- | --- |
+| ![](/imgs/datasetprompt1.png) | ![](/imgs/datasetprompt2.png) |
+| ![](/imgs/datasetprompt3.png) | ![](/imgs/datasetprompt5.png) |
+| ![](/imgs/datasetprompt4.png) | ![](/imgs/datasetprompt6.png) |
+
+#### 严格模板
+
+使用非严格模板，我们随便询问一个不在知识库中的内容，模型通常会根据其自身知识进行回答。
+
+| 非严格模板效果 | 选择严格模板 | 严格模板效果 |
+| --- | --- | --- |
+| ![](/imgs/datasetprompt7.png) | ![](/imgs/datasetprompt8.png) |![](/imgs/datasetprompt9.png) |
+
+#### 提示词设计思路
+
+1. 使用序号进行不同要求描述。
+2. 使用首先、然后、最后等词语进行描述。
+3. 列举不同场景的要求时，尽量完整，不要遗漏。例如：背景知识完全可以回答、背景知识可以回答一部分、背景知识与问题无关，3种场景都说明清楚。
+4. 巧用结构化提示，例如在问答模板中，利用了`instruction`和`output`，清楚的告诉模型，`output`是一个预期的答案。
+5. 标点符号正确且完整。
--- a/docSite/content/docs/use-cases/datasetEngine.md
+++ b/docSite/content/docs/use-cases/datasetEngine.md
@@ -0,0 +1,91 @@
+---
+title: "知识库结构讲解"
+description: "本节会详细介绍 FastGPT 知识库结构设计，理解其 QA 的存储格式和多向量映射，以便更好的构建知识库。这篇介绍主要以使用为主，详细原理不多介绍。"
+icon: "dataset"
+draft: false
+toc: true
+weight: 311
+---
+
+## 理解向量
+
+FastGPT 采用了 RAG 中的 Embedding 方案构建知识库，要使用好 FastGPT 需要简单的理解`Embedding`向量是如何工作的及其特点。
+
+人类的文字、图片、视频等媒介是无法直接被计算机理解的，要想让计算机理解两段文字是否有相似性、相关性，通常需要将它们转成计算机可以理解的语言，向量是其中的一种方式。
+
+向量可以简单理解为一个数字数组，两个向量之间可以通过数学公式得出一个`距离`，距离越小代表两个向量的相似度越大。从而映射到文字、图片、视频等媒介上，可以用来判断两个媒介之间的相似度。向量搜索便是利用了这个原理。
+
+而由于文字是有多种类型，并且拥有成千上万种组合方式，因此在转成向量进行相似度匹配时，很难保障其精确性。在向量方案构建的知识库中，通常使用`topk`召回的方式，也就是查找前`k`个最相似的内容，丢给大模型去做更进一步的`语义判断`、`逻辑推理`和`归纳总结`，从而实现知识库问答。因此，在知识库问答中，向量搜索的环节是最为重要的。
+
+影响向量搜索精度的因素非常多，主要包括：向量模型的质量、数据的质量（长度，完整性，多样性）、检索器的精度（速度与精度之间的取舍）。与数据质量对应的就是检索词的质量。
+
+检索器的精度比较容易解决，向量模型的训练略复杂，因此数据和检索词质量优化成了一个重要的环节。
+
+## FastGPT 中向量的结构设计
+
+FastGPT 采用了 `PostgresSQL` 的 `PG Vector` 插件作为向量检索器，索引为`HNSW`。且`PostgresSQL`仅用于向量检索，`MongoDB`用于其他数据的存取。
+
+在`PostgresSQL`的表中，设置一个 `index` 字段用于存储向量，以及一个`data_id`用于在`MongoDB`中寻找对应的映射值。多个`index`可以对应一组`data_id`，也就是说，一组向量可以对应多组数据。在进行检索时，相同数据会进行合并。
+
+![](/imgs/datasetSetting1.png)
+
+### 多向量的目的和使用方式
+
+在一组向量中，内容的长度和语义的丰富度通常是矛盾的，无法兼得。因此，FastGPT 采用了多向量映射的方式，将一组数据映射到多组向量中，从而保障数据的完整性和语义的丰富度。
+
+你可以为一组较长的文本，添加多组向量，从而在检索时，只要其中一组向量被检索到，该数据也将被召回。
+
+### 提高向量搜索精度的方法
+
+1. 更好分词分段：当一段话的结构和语义是完整的，并且是单一的，精度也会提高。因此，许多系统都会优化分词器，尽可能的保障每组数据的完整性。
+2. 精简`index`的内容，减少向量内容的长度：当`index`的内容更少，更准确时，检索精度自然会提高。但与此同时，会牺牲一定的检索范围，适合答案较为严格的场景。
+3. 丰富`index`的数量，可以为同一个`chunk`内容增加多组`index`。
+4. 优化检索词：在实际使用过程中，用户的问题通常是模糊的或是缺失的，并不一定是完整清晰的问题。因此优化用户的问题（检索词）很大程度上也可以提高精度。
+5. 微调向量模型：由于市面上直接使用的向量模型都是通用型模型，在特定领域的检索精度并不高，因此微调向量模型可以很大程度上提高专业领域的检索效果。
+
+## FastGPT 构建知识库方案
+
+在 FastGPT 中，整个知识库由库、集合和数据 3 部分组成。集合可以简单理解为一个`文件`。一个`库`中可以包含多个`集合`，一个`集合`中可以包含多组`数据`。最小的搜索单位是`库`，也就是说，知识库搜索时，是对整个`库`进行搜索，而集合仅是为了对数据进行分类管理，与搜索效果无关。（起码目前还是）
+
+| 库 | 集合 | 数据 |
+| --- | --- | --- |
+| ![](/imgs/datasetEngine1.png) | ![](/imgs/datasetEngine2.png) | ![](/imgs/datasetEngine3.png) |
+
+### 导入数据方案1 - 直接分段导入
+
+选择文件导入时，可以选择直接分段方案。直接分段会利用`句子分词器`对文本进行一定长度拆分，最终分割中多组的`q`。如果使用了直接分段方案，我们建议在`应用`设置`引用提示词`时，使用`通用模板`即可，无需选择`问答模板`。
+
+| 交互 | 结果 |
+| --- | --- |
+| ![](/imgs/datasetEngine4.png) | ![](/imgs/datasetEngine5.png) |
+
+
+### 导入数据方案2 - QA导入
+
+选择文件导入时，可以选择QA拆分方案。仍然需要使用到`句子分词器`对文本进行拆分，但长度比直接分段大很多。在导入后，会先调用`大模型`对分段进行学习，并给出一些`问题`和`答案`，最终问题和答案会一起被存储到`q`中。注意，新版的 FastGPT 为了提高搜索的范围，不再将问题和答案分别存储到 qa 中。
+
+| 交互 | 结果 |
+| --- | --- |
+| ![](/imgs/datasetEngine6.png) | ![](/imgs/datasetEngine7.png) |
+
+### 导入数据方案3 - 手动录入
+
+在 FastGPT 中，你可以在任何一个`集合`中点击右上角的`插入`手动录入知识点，或者使用`标注`功能手动录入。被搜索的内容为`q`，补充内容(可选)为`a`。
+
+|  |  |  |
+| --- | --- | --- |
+| ![](/imgs/datasetEngine8.png) | ![](/imgs/datasetEngine9.png) | ![](/imgs/datasetEngine10.png) |
+
+### 导入数据方案4 - CSV录入
+
+有些数据较为独特，可能需要单独的进行预处理分割后再导入 FastGPT，此时可以选择 csv 导入，可批量的将处理好的数据导入。
+
+![](/imgs/datasetEngine11.png)
+
+### 导入数据方案5 - API导入
+
+参考[FastGPT OpenAPI使用](/docs/development/openapi/#知识库添加数据)。
+
+## QA的组合与引用提示词构建
+
+参考[引用模板与引用提示词示例](/docs/use-cases/ai_settings/#示例)
--- a/docSite/content/docs/use-cases/kb.md
+++ b/docSite/content/docs/use-cases/kb.md
@@ -73,7 +73,7 @@ weight: 340
 ![手动录入知识库结果](/imgs/9.png)

 导入结果如上图。可以看到，我们均采用的是问答对的格式，而不是粗略的直接导入。目的就是为了模拟用户问题，进一步的提高向量搜索的匹配效果。可以为同一个问题设置多种问法，效果更佳。
-FastGPT 还提供了 openapi 功能，你可以在本地对特殊格式的文件进行处理后，再上传到 FastGPT，具体可以参考：[FastGPT Api Docs](https://doc.fastgpt.run/docs/development/openapi)
+FastGPT 还提供了 openapi 功能，你可以在本地对特殊格式的文件进行处理后，再上传到 FastGPT，具体可以参考：[FastGPT Api Docs](https://doc.fastgpt.in/docs/development/openapi)

 ## 知识库微调和参数调整

--- a/docSite/content/docs/use-cases/openapi.md
+++ b/docSite/content/docs/use-cases/openapi.md
@@ -4,7 +4,7 @@ description: "通过与 OpenAI 兼容的 API 对接第三方应用"
 icon: "model_training"
 draft: false
 toc: true
-weight: 311
+weight: 312
 ---

 ## 获取 API 秘钥
--- a/docSite/content/docs/use-cases/wechat.md
+++ b/docSite/content/docs/use-cases/wechat.md
@@ -0,0 +1,76 @@
+---
+title: " 接入微信和企业微信 "
+description: "FastGPT 接入微信和企业微信 "
+icon: "chat"
+draft: false
+toc: true
+weight: 322
+---
+
+# FastGPT 三分钟接入微信/企业微信
+私人微信和企业微信接入的方式基本一样，不同的地方会刻意指出。   
+[查看视频教程](https://www.bilibili.com/video/BV1cu411F7FN/?spm_id_from=333.1007.top_right_bar_window_history.content.click&vd_source=903c2b09b7412037c2eddc6a8fb9828b)
+## 创建APIKey
+首先找到我们需要接入的应用，然后点击「外部使用」->「API访问」创建一个APIKey并保存。
+
+![](/imgs/wechat1.png)
+
+## 配置微秘书
+
+打开[微秘书](https://wechat.aibotk.com?r=zWLnZK) 注册登陆后找到菜单栏「基础配置」->「智能配置」，按照下图配置。
+
+![](/imgs/wechat2.png)
+
+继续往下看到 `apikey` 和`服务器根地址`，这里`apikey`填写我们在 FastGPT 应用外部访问中创建的 APIkey，服务器根地址填写官方地址或者私有化部署的地址，这里用官方地址示例，注意要添加`/v1`后缀,填写完毕后保存。
+
+![](/imgs/wechat3.png)
+
+## sealos部署服务
+
+[访问sealos](https://cloud.sealos.io/) 登陆进来之后打开「应用管理」-> 「新建应用」。
+- 应用名：称随便填写
+- 镜像名：私人微信填写 aibotk/wechat-assistant 企业微信填写 aibotk/worker-assistant
+- cpu和内存建议 1c1g
+
+![](/imgs/wechat4.png)
+
+往下翻页找到「高级配置」-> 「编辑环境变量」
+
+![](/imgs/wechat5.png)
+
+这里需要填写四个环境变量：   
+AIBOTK_KEY="微秘书 APIKEY"   
+AIBOTK_SECRET="微秘书 APISECRET"   
+WORK_PRO_TOKEN="你申请的企微 token"   （企业微信需要填写，私人微信不需要）
+WECHATY_PUPPET_SERVICE_AUTHORITY=token-service-discovery-test.juzibot.com（企业微信需要填写，私人微信不需要）  
+
+这里最后两个变量只有部署企业微信才需要，私人微信只需要填写前两个即可。
+
+![](/imgs/wechat6.png)
+
+这里环境变量我们介绍下如何填写：
+
+`AIBOTK_KEY` 和 `AIBOTK_SECRET` 我们需要回到[微秘书](https://wechat.aibotk.com?r=zWLnZK)找到「个人中心」,这里的 APIKEY 对应 AIBOTK_KEY ，APISECRET 对应 `AIBOTK_SECRET`。
+
+![](/imgs/wechat7.png)
+
+`WORK_PRO_TOKEN` [点击这里](https://tss.juzibot.com?aff=aibotk)申请 token 然后填入即可。   
+
+`WECHATY_PUPPET_SERVICE_AUTHORITY`的值复制过去就可以。
+
+填写完毕后点右上角「部署」，等待应用状态变为运行中。  
+
+![](/imgs/wechat8.png)
+
+返回[微秘书](https://wechat.aibotk.com?r=zWLnZK) 找到「首页」，扫码登陆需要接入的微信号。
+
+![](/imgs/wechat9.png)
+
+## 测试
+只需要发送信息，或者拉入群聊@登陆的微信就会回复信息啦。
+![](/imgs/wechat10.png)
+
+
+
+
+
--- a/docSite/content/docs/workflow/examples/fixingEvidence.md
+++ b/docSite/content/docs/workflow/examples/fixingEvidence.md
@@ -86,7 +86,7 @@ weight: 142
      {
        "key": "history",
        "label": "聊天记录",
-        "valueType": "chat_history",
+        "valueType": "chatHistory",
        "type": "source",
        "targets": [
          {
@@ -210,14 +210,14 @@ weight: 142
        "type": "target",
        "label": "引用内容",
        "description": "对象数组格式，结构：\n [{q:'问题',a:'回答'}]",
-        "valueType": "kb_quote",
+        "valueType": "datasetQuote",
        "connected": false
      },
      {
        "key": "history",
        "type": "target",
        "label": "聊天记录",
-        "valueType": "chat_history",
+        "valueType": "chatHistory",
        "connected": true
      },
      {
--- a/docSite/content/docs/workflow/examples/google_search.md
+++ b/docSite/content/docs/workflow/examples/google_search.md
@@ -132,7 +132,7 @@ export default async function (ctx: FunctionContext) {
      {
        "key": "history",
        "label": "聊天记录",
-        "valueType": "chat_history",
+        "valueType": "chatHistory",
        "type": "source",
        "targets": [
          {
@@ -179,7 +179,7 @@ export default async function (ctx: FunctionContext) {
        "key": "history",
        "type": "target",
        "label": "聊天记录",
-        "valueType": "chat_history",
+        "valueType": "chatHistory",
        "connected": true
      },
      {
@@ -410,14 +410,14 @@ export default async function (ctx: FunctionContext) {
        "key": "quoteQA",
        "type": "target",
        "label": "引用内容",
-        "valueType": "kb_quote",
+        "valueType": "datasetQuote",
        "connected": false
      },
      {
        "key": "history",
        "type": "target",
        "label": "聊天记录",
-        "valueType": "chat_history",
+        "valueType": "chatHistory",
        "connected": true
      },
      {
--- a/docSite/content/docs/workflow/examples/lab_appointment.md
+++ b/docSite/content/docs/workflow/examples/lab_appointment.md
@@ -131,7 +131,7 @@ HTTP 模块允许你调用任意 POST 类型的 HTTP 接口，从而实验一些
      {
        "key": "history",
        "label": "聊天记录",
-        "valueType": "chat_history",
+        "valueType": "chatHistory",
        "type": "source",
        "targets": [
          {
@@ -174,7 +174,7 @@ HTTP 模块允许你调用任意 POST 类型的 HTTP 接口，从而实验一些
        "key": "history",
        "type": "target",
        "label": "聊天记录",
-        "valueType": "chat_history",
+        "valueType": "chatHistory",
        "connected": true
      },
      {
@@ -413,7 +413,7 @@ HTTP 模块允许你调用任意 POST 类型的 HTTP 接口，从而实验一些
        "key": "history",
        "type": "target",
        "label": "聊天记录",
-        "valueType": "chat_history",
+        "valueType": "chatHistory",
        "connected": true
      },
      {
@@ -630,7 +630,7 @@ HTTP 模块允许你调用任意 POST 类型的 HTTP 接口，从而实验一些
        "label": "引用内容",
        "description": "始终返回数组，如果希望搜索结果为空时执行额外操作，需要用到上面的两个输入以及目标模块的触发器",
        "type": "source",
-        "valueType": "kb_quote",
+        "valueType": "datasetQuote",
        "targets": [
          {
            "moduleId": "bjfklc",
@@ -729,14 +729,14 @@ HTTP 模块允许你调用任意 POST 类型的 HTTP 接口，从而实验一些
        "key": "quoteQA",
        "type": "target",
        "label": "引用内容",
-        "valueType": "kb_quote",
+        "valueType": "datasetQuote",
        "connected": true
      },
      {
        "key": "history",
        "type": "target",
        "label": "聊天记录",
-        "valueType": "chat_history",
+        "valueType": "chatHistory",
        "connected": true
      },
      {
@@ -831,7 +831,7 @@ HTTP 模块允许你调用任意 POST 类型的 HTTP 接口，从而实验一些
      {
        "key": "history",
        "label": "聊天记录",
-        "valueType": "chat_history",
+        "valueType": "chatHistory",
        "type": "source",
        "targets": [
          {
@@ -874,7 +874,7 @@ HTTP 模块允许你调用任意 POST 类型的 HTTP 接口，从而实验一些
        "key": "history",
        "type": "target",
        "label": "聊天记录",
-        "valueType": "chat_history",
+        "valueType": "chatHistory",
        "connected": true
      },
      {
@@ -1006,7 +1006,7 @@ HTTP 模块允许你调用任意 POST 类型的 HTTP 接口，从而实验一些
      {
        "key": "history",
        "label": "聊天记录",
-        "valueType": "chat_history",
+        "valueType": "chatHistory",
        "type": "source",
        "targets": [
          {
--- a/docSite/content/docs/workflow/examples/op_question.md
+++ b/docSite/content/docs/workflow/examples/op_question.md
@@ -83,7 +83,7 @@ weight: 144
      {
        "key": "history",
        "label": "聊天记录",
-        "valueType": "chat_history",
+        "valueType": "chatHistory",
        "type": "source",
        "targets": [
          {
@@ -189,7 +189,7 @@ weight: 144
        "label": "引用内容",
        "description": "始终返回数组，如果希望搜索结果为空时执行额外操作，需要用到上面的两个输入以及目标模块的触发器",
        "type": "source",
-        "valueType": "kb_quote",
+        "valueType": "datasetQuote",
        "targets": [
          {
            "moduleId": "ol82hp",
@@ -291,14 +291,14 @@ weight: 144
        "type": "target",
        "label": "引用内容",
        "description": "对象数组格式，结构：\n [{q:'问题',a:'回答'}]",
-        "valueType": "kb_quote",
+        "valueType": "datasetQuote",
        "connected": true
      },
      {
        "key": "history",
        "type": "target",
        "label": "聊天记录",
-        "valueType": "chat_history",
+        "valueType": "chatHistory",
        "connected": true
      },
      {
@@ -389,7 +389,7 @@ weight: 144
      {
        "key": "history",
        "label": "聊天记录",
-        "valueType": "chat_history",
+        "valueType": "chatHistory",
        "type": "source",
        "targets": [
          {
@@ -432,7 +432,7 @@ weight: 144
        "key": "history",
        "type": "target",
        "label": "聊天记录",
-        "valueType": "chat_history",
+        "valueType": "chatHistory",
        "connected": true
      },
      {
--- a/docSite/content/docs/workflow/examples/versatile_assistant.md
+++ b/docSite/content/docs/workflow/examples/versatile_assistant.md
@@ -245,7 +245,7 @@ PS2：配置中的问题分类还包含着“联网搜索”，这个是另一
      {
        "key": "history",
        "label": "聊天记录",
-        "valueType": "chat_history",
+        "valueType": "chatHistory",
        "type": "source",
        "targets": [
          {
@@ -300,7 +300,7 @@ PS2：配置中的问题分类还包含着“联网搜索”，这个是另一
        "key": "history",
        "type": "target",
        "label": "聊天记录",
-        "valueType": "chat_history",
+        "valueType": "chatHistory",
        "connected": true
      },
      {
@@ -427,7 +427,7 @@ PS2：配置中的问题分类还包含着“联网搜索”，这个是另一
        "key": "history",
        "type": "target",
        "label": "聊天记录",
-        "valueType": "chat_history",
+        "valueType": "chatHistory",
        "connected": true
      },
      {
@@ -713,14 +713,14 @@ PS2：配置中的问题分类还包含着“联网搜索”，这个是另一
        "type": "custom",
        "label": "引用内容",
        "description": "对象数组格式，结构：\n [{q:'问题',a:'回答'}]",
-        "valueType": "kb_quote",
+        "valueType": "datasetQuote",
        "connected": false
      },
      {
        "key": "history",
        "type": "target",
        "label": "聊天记录",
-        "valueType": "chat_history",
+        "valueType": "chatHistory",
        "connected": true
      },
      {
@@ -871,14 +871,14 @@ PS2：配置中的问题分类还包含着“联网搜索”，这个是另一
        "type": "custom",
        "label": "引用内容",
        "description": "对象数组格式，结构：\n [{q:'问题',a:'回答'}]",
-        "valueType": "kb_quote",
+        "valueType": "datasetQuote",
        "connected": false
      },
      {
        "key": "history",
        "type": "target",
        "label": "聊天记录",
-        "valueType": "chat_history",
+        "valueType": "chatHistory",
        "connected": true
      },
      {
@@ -1085,14 +1085,14 @@ PS2：配置中的问题分类还包含着“联网搜索”，这个是另一
        "type": "custom",
        "label": "引用内容",
        "description": "对象数组格式，结构：\n [{q:'问题',a:'回答'}]",
-        "valueType": "kb_quote",
+        "valueType": "datasetQuote",
        "connected": false
      },
      {
        "key": "history",
        "type": "target",
        "label": "聊天记录",
-        "valueType": "chat_history",
+        "valueType": "chatHistory",
        "connected": true
      },
      {
@@ -1162,7 +1162,7 @@ PS2：配置中的问题分类还包含着“联网搜索”，这个是另一
      {
        "key": "history",
        "label": "聊天记录",
-        "valueType": "chat_history",
+        "valueType": "chatHistory",
        "type": "source",
        "targets": [
          {
@@ -1205,7 +1205,7 @@ PS2：配置中的问题分类还包含着“联网搜索”，这个是另一
        "key": "history",
        "type": "target",
        "label": "聊天记录",
-        "valueType": "chat_history",
+        "valueType": "chatHistory",
        "connected": true
      },
      {
@@ -1452,14 +1452,14 @@ PS2：配置中的问题分类还包含着“联网搜索”，这个是另一
        "type": "custom",
        "label": "引用内容",
        "description": "对象数组格式，结构：\n [{q:'问题',a:'回答'}]",
-        "valueType": "kb_quote",
+        "valueType": "datasetQuote",
        "connected": false
      },
      {
        "key": "history",
        "type": "target",
        "label": "聊天记录",
-        "valueType": "chat_history",
+        "valueType": "chatHistory",
        "connected": true
      },
      {
--- a/package.json
+++ b/package.json
@@ -4,20 +4,28 @@
  "private": true,
  "scripts": {
    "prepare": "husky install",
-    "format": "prettier --config \"./.prettierrc.js\" --write \"./**/src/**/*.{ts,tsx,scss}\""
+    "format-code": "prettier --config \"./.prettierrc.js\" --write \"./**/src/**/*.{ts,tsx,scss}\"",
+    "format-doc": "zhlint --dir ./docSite *.md --fix"
  },
  "devDependencies": {
+    "@types/multer": "^1.4.10",
    "husky": "^8.0.3",
+    "i18next": "^22.5.1",
    "lint-staged": "^13.2.1",
+    "next-i18next": "^13.3.0",
    "prettier": "^3.0.3",
-    "i18next": "^23.2.11",
-    "react-i18next": "^13.0.2",
-    "next-i18next": "^14.0.0"
+    "react-i18next": "^12.3.1",
+    "zhlint": "^0.7.1"
  },
  "lint-staged": {
-    "./**/**/*.{ts,tsx,scss}": "npm run format"
+    "./**/**/*.{ts,tsx,scss}": "npm run format-code",
+    "./**/**/*.md": "npm run format-doc"
  },
  "engines": {
    "node": ">=18.0.0"
+  },
+  "dependencies": {
+    "multer": "1.4.5-lts.1",
+    "openai": "4.16.1"
  }
 }
--- a/packages/global/common/bill/constants.ts
+++ b/packages/global/common/bill/constants.ts
@@ -1 +0,0 @@
-export const PRICE_SCALE = 100000;
--- a/packages/global/common/bill/types/billReq.d.ts
+++ b/packages/global/common/bill/types/billReq.d.ts
@@ -1,3 +0,0 @@
-export type CreateTrainingBillType = {
-  name: string;
-};
--- a/packages/global/common/error/code/app.ts
+++ b/packages/global/common/error/code/app.ts
@@ -0,0 +1,28 @@
+import { ErrType } from '../errorCode';
+
+/* dataset: 502000 */
+export enum AppErrEnum {
+  unExist = 'unExist',
+  unAuthApp = 'unAuthApp'
+}
+const appErrList = [
+  {
+    statusText: AppErrEnum.unExist,
+    message: '应用不存在'
+  },
+  {
+    statusText: AppErrEnum.unAuthApp,
+    message: '无权操作该应用'
+  }
+];
+export default appErrList.reduce((acc, cur, index) => {
+  return {
+    ...acc,
+    [cur.statusText]: {
+      code: 502000 + index,
+      statusText: cur.statusText,
+      message: cur.message,
+      data: null
+    }
+  };
+}, {} as ErrType<`${AppErrEnum}`>);
--- a/packages/global/common/error/code/chat.ts
+++ b/packages/global/common/error/code/chat.ts
@@ -0,0 +1,23 @@
+import { ErrType } from '../errorCode';
+
+/* dataset: 504000 */
+export enum ChatErrEnum {
+  unAuthChat = 'unAuthChat'
+}
+const errList = [
+  {
+    statusText: ChatErrEnum.unAuthChat,
+    message: '无权操作该对话记录'
+  }
+];
+export default errList.reduce((acc, cur, index) => {
+  return {
+    ...acc,
+    [cur.statusText]: {
+      code: 504000 + index,
+      statusText: cur.statusText,
+      message: cur.message,
+      data: null
+    }
+  };
+}, {} as ErrType<`${ChatErrEnum}`>);
--- a/packages/global/common/error/code/dataset.ts
+++ b/packages/global/common/error/code/dataset.ts
@@ -0,0 +1,43 @@
+import { ErrType } from '../errorCode';
+
+/* dataset: 501000 */
+export enum DatasetErrEnum {
+  unAuthDataset = 'unAuthDataset',
+  unCreateCollection = 'unCreateCollection',
+  unAuthDatasetCollection = 'unAuthDatasetCollection',
+  unAuthDatasetData = 'unAuthDatasetData',
+  unAuthDatasetFile = 'unAuthDatasetFile'
+}
+const datasetErr = [
+  {
+    statusText: DatasetErrEnum.unAuthDataset,
+    message: '无权操作该知识库'
+  },
+  {
+    statusText: DatasetErrEnum.unAuthDatasetCollection,
+    message: '无权操作该数据集'
+  },
+  {
+    statusText: DatasetErrEnum.unAuthDatasetData,
+    message: '无权操作该数据'
+  },
+  {
+    statusText: DatasetErrEnum.unAuthDatasetFile,
+    message: '无权操作该文件'
+  },
+  {
+    statusText: DatasetErrEnum.unCreateCollection,
+    message: '无权创建数据集'
+  }
+];
+export default datasetErr.reduce((acc, cur, index) => {
+  return {
+    ...acc,
+    [cur.statusText]: {
+      code: 501000 + index,
+      statusText: cur.statusText,
+      message: cur.message,
+      data: null
+    }
+  };
+}, {} as ErrType<`${DatasetErrEnum}`>);
--- a/packages/global/common/error/code/openapi.ts
+++ b/packages/global/common/error/code/openapi.ts
@@ -0,0 +1,28 @@
+import { ErrType } from '../errorCode';
+
+/* dataset: 506000 */
+export enum OpenApiErrEnum {
+  unExist = 'unExist',
+  unAuth = 'unAuth'
+}
+const errList = [
+  {
+    statusText: OpenApiErrEnum.unExist,
+    message: 'Api Key 不存在'
+  },
+  {
+    statusText: OpenApiErrEnum.unAuth,
+    message: '无权操作该 Api Key'
+  }
+];
+export default errList.reduce((acc, cur, index) => {
+  return {
+    ...acc,
+    [cur.statusText]: {
+      code: 506000 + index,
+      statusText: cur.statusText,
+      message: cur.message,
+      data: null
+    }
+  };
+}, {} as ErrType<`${OpenApiErrEnum}`>);
--- a/packages/global/common/error/code/outLink.ts
+++ b/packages/global/common/error/code/outLink.ts
@@ -0,0 +1,34 @@
+import { ErrType } from '../errorCode';
+
+/* dataset: 505000 */
+export enum OutLinkErrEnum {
+  unExist = 'unExist',
+  unAuthLink = 'unAuthLink',
+  linkUnInvalid = 'linkUnInvalid'
+}
+const errList = [
+  {
+    statusText: OutLinkErrEnum.unExist,
+    message: '分享链接不存在'
+  },
+  {
+    statusText: OutLinkErrEnum.unAuthLink,
+    message: '分享链接无效'
+  },
+  {
+    code: 501,
+    statusText: OutLinkErrEnum.linkUnInvalid,
+    message: '分享链接无效'
+  }
+];
+export default errList.reduce((acc, cur, index) => {
+  return {
+    ...acc,
+    [cur.statusText]: {
+      code: cur?.code || 505000 + index,
+      statusText: cur.statusText,
+      message: cur.message,
+      data: null
+    }
+  };
+}, {} as ErrType<`${OutLinkErrEnum}`>);
--- a/packages/global/common/error/code/plugin.ts
+++ b/packages/global/common/error/code/plugin.ts
@@ -0,0 +1,28 @@
+import { ErrType } from '../errorCode';
+
+/* dataset: 507000 */
+export enum PluginErrEnum {
+  unExist = 'unExist',
+  unAuth = 'unAuth'
+}
+const errList = [
+  {
+    statusText: PluginErrEnum.unExist,
+    message: '插件不存在'
+  },
+  {
+    statusText: PluginErrEnum.unAuth,
+    message: '无权操作该插件'
+  }
+];
+export default errList.reduce((acc, cur, index) => {
+  return {
+    ...acc,
+    [cur.statusText]: {
+      code: 507000 + index,
+      statusText: cur.statusText,
+      message: cur.message,
+      data: null
+    }
+  };
+}, {} as ErrType<`${PluginErrEnum}`>);
--- a/packages/global/common/error/code/team.ts
+++ b/packages/global/common/error/code/team.ts
@@ -0,0 +1,22 @@
+import { ErrType } from '../errorCode';
+
+/* team: 500000 */
+export enum TeamErrEnum {
+  teamOverSize = 'teamOverSize',
+  unAuthTeam = 'unAuthTeam'
+}
+const teamErr = [
+  { statusText: TeamErrEnum.teamOverSize, message: 'error.team.overSize' },
+  { statusText: TeamErrEnum.unAuthTeam, message: '无权操作该团队' }
+];
+export default teamErr.reduce((acc, cur, index) => {
+  return {
+    ...acc,
+    [cur.statusText]: {
+      code: 500000 + index,
+      statusText: cur.statusText,
+      message: cur.message,
+      data: null
+    }
+  };
+}, {} as ErrType<`${TeamErrEnum}`>);
--- a/packages/global/common/error/code/user.ts
+++ b/packages/global/common/error/code/user.ts
@@ -0,0 +1,26 @@
+import { ErrType } from '../errorCode';
+
+/* team: 503000 */
+export enum UserErrEnum {
+  unAuthUser = 'unAuthUser',
+  unAuthRole = 'unAuthRole',
+  binVisitor = 'binVisitor',
+  balanceNotEnough = 'balanceNotEnough'
+}
+const errList = [
+  { statusText: UserErrEnum.unAuthUser, message: '找不到该用户' },
+  { statusText: UserErrEnum.binVisitor, message: '您的身份校验未通过' },
+  { statusText: UserErrEnum.binVisitor, message: '您当前身份为游客，无权操作' },
+  { statusText: UserErrEnum.balanceNotEnough, message: '账号余额不足~' }
+];
+export default errList.reduce((acc, cur, index) => {
+  return {
+    ...acc,
+    [cur.statusText]: {
+      code: 503000 + index,
+      statusText: cur.statusText,
+      message: cur.message,
+      data: null
+    }
+  };
+}, {} as ErrType<`${UserErrEnum}`>);
--- a/packages/global/common/error/errorCode.ts
+++ b/packages/global/common/error/errorCode.ts
@@ -1,3 +1,12 @@
+import appErr from './code/app';
+import chatErr from './code/chat';
+import datasetErr from './code/dataset';
+import openapiErr from './code/openapi';
+import pluginErr from './code/plugin';
+import outLinkErr from './code/outLink';
+import teamErr from './code/team';
+import userErr from './code/user';
+
 export const ERROR_CODE: { [key: number]: string } = {
  400: '请求失败',
  401: '无权访问',
@@ -27,10 +36,19 @@ export enum ERROR_ENUM {
  insufficientQuota = 'insufficientQuota',
  unAuthModel = 'unAuthModel',
  unAuthApiKey = 'unAuthApiKey',
-  unAuthDataset = 'unAuthDataset',
-  unAuthDatasetCollection = 'unAuthDatasetCollection',
  unAuthFile = 'unAuthFile'
 }
+
+export type ErrType<T> = Record<
+  string,
+  {
+    code: number;
+    statusText: T;
+    message: string;
+    data: null;
+  }
+>;
+
 export const ERROR_RESPONSE: Record<
  any,
  {
@@ -55,15 +73,10 @@ export const ERROR_RESPONSE: Record<
  [ERROR_ENUM.unAuthModel]: {
    code: 511,
    statusText: ERROR_ENUM.unAuthModel,
-    message: '无权使用该模型',
-    data: null
-  },
-  [ERROR_ENUM.unAuthDataset]: {
-    code: 512,
-    statusText: ERROR_ENUM.unAuthDataset,
-    message: '无权使用该知识库',
+    message: '无权操作该模型',
    data: null
  },
+
  [ERROR_ENUM.unAuthFile]: {
    code: 513,
    statusText: ERROR_ENUM.unAuthFile,
@@ -76,10 +89,12 @@ export const ERROR_RESPONSE: Record<
    message: 'Api Key 不合法',
    data: null
  },
-  [ERROR_ENUM.unAuthDatasetCollection]: {
-    code: 515,
-    statusText: ERROR_ENUM.unAuthDatasetCollection,
-    message: '无权使用该知识库文件',
-    data: null
-  }
+  ...appErr,
+  ...chatErr,
+  ...datasetErr,
+  ...openapiErr,
+  ...outLinkErr,
+  ...teamErr,
+  ...userErr,
+  ...pluginErr
 };
--- a/packages/global/common/file/constants.ts
+++ b/packages/global/common/file/constants.ts
@@ -0,0 +1,5 @@
+export enum BucketNameEnum {
+  dataset = 'dataset'
+}
+
+export const FileBaseUrl = '/api/common/file/read';
--- a/packages/global/common/file/icon.ts
+++ b/packages/global/common/file/icon.ts
@@ -1,16 +1,12 @@
-import { strIsLink } from '../string/tools';
-
 export const fileImgs = [
  { suffix: 'pdf', src: '/imgs/files/pdf.svg' },
  { suffix: 'csv', src: '/imgs/files/csv.svg' },
  { suffix: '(doc|docs)', src: '/imgs/files/doc.svg' },
  { suffix: 'txt', src: '/imgs/files/txt.svg' },
-  { suffix: 'md', src: '/imgs/files/markdown.svg' },
-  { suffix: '.', src: '/imgs/files/file.svg' }
+  { suffix: 'md', src: '/imgs/files/markdown.svg' }
+  // { suffix: '.', src: '/imgs/files/file.svg' }
 ];

-export function getFileIcon(name = '') {
-  return (
-    fileImgs.find((item) => new RegExp(item.suffix, 'gi').test(name))?.src || '/imgs/files/file.svg'
-  );
+export function getFileIcon(name = '', defaultImg = '/imgs/files/file.svg') {
+  return fileImgs.find((item) => new RegExp(item.suffix, 'gi').test(name))?.src || defaultImg;
 }
--- a/packages/global/common/file/type.d.ts
+++ b/packages/global/common/file/type.d.ts
@@ -0,0 +1,8 @@
+import { BucketNameEnum } from './constants';
+
+export type FileTokenQuery = {
+  bucketName: `${BucketNameEnum}`;
+  teamId: string;
+  tmbId: string;
+  fileId: string;
+};
--- a/packages/global/common/string/textSplitter.ts
+++ b/packages/global/common/string/textSplitter.ts
@@ -0,0 +1,131 @@
+import { getErrText } from '../error/utils';
+import { countPromptTokens } from './tiktoken';
+
+/**
+ * text split into chunks
+ * maxLen - one chunk len. max: 3500
+ * overlapLen - The size of the before and after Text
+ * maxLen > overlapLen
+ * markdown
+ */
+export const splitText2Chunks = (props: { text: string; maxLen: number; overlapLen?: number }) => {
+  const { text = '', maxLen, overlapLen = Math.floor(maxLen * 0.2) } = props;
+  const tempMarker = 'SPLIT_HERE_SPLIT_HERE';
+
+  const stepReg: Record<number, RegExp> = {
+    0: /^(#\s[^\n]+)\n/gm,
+    1: /^(##\s[^\n]+)\n/gm,
+    2: /^(###\s[^\n]+)\n/gm,
+    3: /^(####\s[^\n]+)\n/gm,
+
+    4: /(\n\n)/g,
+    5: /([\n])/g,
+    6: /[。]|(?!<[^a-zA-Z])\.\s/g,
+    7: /([！？]|!\s|\?\s)/g,
+    8: /([；]|;\s)/g,
+    9: /([，]|,\s)/g
+  };
+
+  const splitTextRecursively = ({
+    text = '',
+    step,
+    lastChunk,
+    overlayChunk
+  }: {
+    text: string;
+    step: number;
+    lastChunk: string;
+    overlayChunk: string;
+  }) => {
+    if (text.length <= maxLen) {
+      return [text];
+    }
+    const reg = stepReg[step];
+    const isMarkdownSplit = step < 4;
+
+    if (!reg) {
+      // use slice-maxLen to split text
+      const chunks: string[] = [];
+      let chunk = '';
+      for (let i = 0; i < text.length; i += maxLen - overlapLen) {
+        chunk = text.slice(i, i + maxLen);
+        chunks.push(chunk);
+      }
+      return chunks;
+    }
+
+    // split text by special char
+    const splitTexts = text
+      .replace(reg, isMarkdownSplit ? `${tempMarker}$1` : `$1${tempMarker}`)
+      .split(`${tempMarker}`)
+      .filter((part) => part);
+
+    let chunks: string[] = [];
+    for (let i = 0; i < splitTexts.length; i++) {
+      let text = splitTexts[i];
+      let chunkToken = lastChunk.length;
+      const textToken = text.length;
+
+      // next chunk is too large / new chunk is too large(The current chunk must be smaller than maxLen)
+      if (textToken >= maxLen || chunkToken + textToken > maxLen * 1.4) {
+        // last chunk is too large, push it to chunks, not add to next chunk
+        if (chunkToken > maxLen * 0.7) {
+          chunks.push(lastChunk);
+          lastChunk = '';
+          overlayChunk = '';
+        }
+        // chunk is small, insert to next chunks
+        const innerChunks = splitTextRecursively({
+          text,
+          step: step + 1,
+          lastChunk,
+          overlayChunk
+        });
+        if (innerChunks.length === 0) continue;
+        chunks = chunks.concat(innerChunks);
+        lastChunk = '';
+        overlayChunk = '';
+        continue;
+      }
+
+      // size less than maxLen, push text to last chunk
+      lastChunk += text;
+      chunkToken += textToken; // Definitely less than 1.4 * maxLen
+
+      // size over lapLen, push it to next chunk
+      if (
+        overlapLen !== 0 &&
+        !isMarkdownSplit &&
+        chunkToken >= maxLen - overlapLen &&
+        textToken < overlapLen
+      ) {
+        overlayChunk += text;
+      }
+      if (chunkToken >= maxLen) {
+        chunks.push(lastChunk);
+        lastChunk = overlayChunk;
+        overlayChunk = '';
+      }
+    }
+
+    /* If the last chunk is independent, it needs to be push chunks. */
+    if (lastChunk && chunks[chunks.length - 1] && !chunks[chunks.length - 1].endsWith(lastChunk)) {
+      chunks.push(lastChunk);
+    }
+
+    return chunks;
+  };
+
+  try {
+    const chunks = splitTextRecursively({ text, step: 0, lastChunk: '', overlayChunk: '' });
+
+    const tokens = chunks.reduce((sum, chunk) => sum + countPromptTokens(chunk, 'system'), 0);
+
+    return {
+      chunks,
+      tokens
+    };
+  } catch (err) {
+    throw new Error(getErrText(err));
+  }
+};
--- a/projects/app/src/global/common/tiktoken/cl100k_base.json
+++ b/projects/app/src/global/common/tiktoken/cl100k_base.json
--- a/projects/app/src/global/common/tiktoken/index.ts
+++ b/projects/app/src/global/common/tiktoken/index.ts
@@ -1,8 +1,8 @@
 /* Only the token of gpt-3.5-turbo is used */
-import { ChatItemType } from '@/types/chat';
+import type { ChatItemType } from '../../../core/chat/type';
 import { Tiktoken } from 'js-tiktoken/lite';
-import { adaptChat2GptMessages } from '@/utils/common/adapt/message';
-import { ChatCompletionRequestMessageRoleEnum } from '@fastgpt/global/core/ai/constant';
+import { adaptChat2GptMessages } from '../../../core/chat/adapt';
+import { ChatCompletionRequestMessageRoleEnum } from '../../../core/ai/constant';
 import encodingJson from './cl100k_base.json';

 /* init tikToken obj */
@@ -55,17 +55,6 @@ export function countMessagesTokens({ messages }: { messages: ChatItemType[] })
  return totalTokens;
 }

-export function sliceTextByTokens({ text, length }: { text: string; length: number }) {
-  const enc = getTikTokenEnc();
-
-  try {
-    const encodeText = enc.encode(text);
-    return enc.decode(encodeText.slice(0, length));
-  } catch (error) {
-    return text.slice(0, length);
-  }
-}
-
 /* slice messages from top to bottom by maxTokens */
 export function sliceMessagesTB({
  messages,
--- a/packages/global/common/string/tiktoken/type.d.ts
+++ b/packages/global/common/string/tiktoken/type.d.ts
@@ -0,0 +1,5 @@
+import type { Tiktoken } from 'js-tiktoken';
+
+declare global {
+  var TikToken: Tiktoken;
+}
--- a/packages/global/common/string/tools.ts
+++ b/packages/global/common/string/tools.ts
@@ -1,13 +1,15 @@
 import crypto from 'crypto';

+/* check string is a web link */
 export function strIsLink(str?: string) {
  if (!str) return false;
  if (/^((http|https)?:\/\/|www\.|\/)[^\s/$.?#].[^\s]*$/i.test(str)) return true;
  return false;
 }

-export const hashStr = (psw: string) => {
-  return crypto.createHash('sha256').update(psw).digest('hex');
+/* hash string */
+export const hashStr = (str: string) => {
+  return crypto.createHash('sha256').update(str).digest('hex');
 };

 /* simple text, remove chinese space and extra \n */
@@ -20,3 +22,16 @@ export const simpleText = (text: string) => {

  return text;
 };
+
+/* 
+  replace {{variable}} to value
+*/
+export function replaceVariable(text: string, obj: Record<string, string | number>) {
+  for (const key in obj) {
+    const val = obj[key];
+    if (!['string', 'number'].includes(typeof val)) continue;
+
+    text = text.replace(new RegExp(`{{(${key})}}`, 'g'), String(val));
+  }
+  return text || '';
+}
--- a/packages/global/common/system/types/index.d.ts
+++ b/packages/global/common/system/types/index.d.ts
@@ -23,6 +23,7 @@ export type FeConfigsType = {
    exportLimitMinutes?: number;
  };
  scripts?: { [key: string]: string }[];
+  favicon?: string;
 };

 export type SystemEnvType = {
--- a/packages/global/core/ai/api.d.ts
+++ b/packages/global/core/ai/api.d.ts
@@ -0,0 +1,5 @@
+export type PostReRankProps = {
+  query: string;
+  inputs: { id: string; text: string }[];
+};
+export type PostReRankResponse = { id: string; score: number }[];
--- a/packages/global/core/ai/constant.ts
+++ b/packages/global/core/ai/constant.ts
@@ -2,5 +2,6 @@ export enum ChatCompletionRequestMessageRoleEnum {
  'System' = 'system',
  'User' = 'user',
  'Assistant' = 'assistant',
-  'Function' = 'function'
+  'Function' = 'function',
+  'Tool' = 'tool'
 }
--- a/packages/global/core/ai/index.ts
+++ b/packages/global/core/ai/index.ts
@@ -0,0 +1,2 @@
+import OpenAI from 'openai';
+export default OpenAI;
--- a/packages/global/core/ai/model.d.ts
+++ b/packages/global/core/ai/model.d.ts
@@ -1,15 +1,15 @@
-import { LLMModelUsageEnum } from '@/constants/model';
-
 export type LLMModelItemType = {
  model: string;
  name: string;
-  maxToken: number;
+  maxContext: number;
+  maxResponse: number;
  price: number;
 };
 export type ChatModelItemType = LLMModelItemType & {
  quoteMaxToken: number;
  maxTemperature: number;
  censor?: boolean;
+  vision?: boolean;
  defaultSystemChatPrompt?: string;
 };

@@ -25,3 +25,18 @@ export type VectorModelItemType = {
  price: number;
  maxToken: number;
 };
+
+export type AudioSpeechModelType = {
+  model: string;
+  name: string;
+  price: number;
+  baseUrl?: string;
+  key?: string;
+  voices: { label: string; value: string; bufferId: string }[];
+};
+
+export type WhisperModelType = {
+  model: string;
+  name: string;
+  price: number;
+};
--- a/packages/global/core/ai/model.ts
+++ b/packages/global/core/ai/model.ts
@@ -0,0 +1,140 @@
+import type {
+  LLMModelItemType,
+  ChatModelItemType,
+  FunctionModelItemType,
+  VectorModelItemType,
+  AudioSpeechModelType,
+  WhisperModelType
+} from './model.d';
+
+export const defaultChatModels: ChatModelItemType[] = [
+  {
+    model: 'gpt-3.5-turbo-1106',
+    name: 'GPT35-1106',
+    price: 0,
+    maxContext: 16000,
+    maxResponse: 4000,
+    quoteMaxToken: 2000,
+    maxTemperature: 1.2,
+    censor: false,
+    vision: false,
+    defaultSystemChatPrompt: ''
+  },
+  {
+    model: 'gpt-3.5-turbo-16k',
+    name: 'GPT35-16k',
+    maxContext: 16000,
+    maxResponse: 16000,
+    price: 0,
+    quoteMaxToken: 8000,
+    maxTemperature: 1.2,
+    censor: false,
+    vision: false,
+    defaultSystemChatPrompt: ''
+  },
+  {
+    model: 'gpt-4',
+    name: 'GPT4-8k',
+    maxContext: 8000,
+    maxResponse: 8000,
+    price: 0,
+    quoteMaxToken: 4000,
+    maxTemperature: 1.2,
+    censor: false,
+    vision: false,
+    defaultSystemChatPrompt: ''
+  },
+  {
+    model: 'gpt-4-vision-preview',
+    name: 'GPT4-Vision',
+    maxContext: 128000,
+    maxResponse: 4000,
+    price: 0,
+    quoteMaxToken: 100000,
+    maxTemperature: 1.2,
+    censor: false,
+    vision: true,
+    defaultSystemChatPrompt: ''
+  }
+];
+export const defaultQAModels: LLMModelItemType[] = [
+  {
+    model: 'gpt-3.5-turbo-16k',
+    name: 'GPT35-16k',
+    maxContext: 16000,
+    maxResponse: 16000,
+    price: 0
+  }
+];
+export const defaultCQModels: FunctionModelItemType[] = [
+  {
+    model: 'gpt-3.5-turbo-1106',
+    name: 'GPT35-1106',
+    maxContext: 16000,
+    maxResponse: 4000,
+    price: 0,
+    functionCall: true,
+    functionPrompt: ''
+  },
+  {
+    model: 'gpt-4',
+    name: 'GPT4-8k',
+    maxContext: 8000,
+    maxResponse: 8000,
+    price: 0,
+    functionCall: true,
+    functionPrompt: ''
+  }
+];
+export const defaultExtractModels: FunctionModelItemType[] = [
+  {
+    model: 'gpt-3.5-turbo-1106',
+    name: 'GPT35-1106',
+    maxContext: 16000,
+    maxResponse: 4000,
+    price: 0,
+    functionCall: true,
+    functionPrompt: ''
+  }
+];
+export const defaultQGModels: LLMModelItemType[] = [
+  {
+    model: 'gpt-3.5-turbo-1106',
+    name: 'GPT35-1106',
+    maxContext: 1600,
+    maxResponse: 4000,
+    price: 0
+  }
+];
+
+export const defaultVectorModels: VectorModelItemType[] = [
+  {
+    model: 'text-embedding-ada-002',
+    name: 'Embedding-2',
+    price: 0,
+    defaultToken: 500,
+    maxToken: 3000
+  }
+];
+
+export const defaultAudioSpeechModels: AudioSpeechModelType[] = [
+  {
+    model: 'tts-1',
+    name: 'OpenAI TTS1',
+    price: 0,
+    voices: [
+      { label: 'Alloy', value: 'Alloy', bufferId: 'openai-Alloy' },
+      { label: 'Echo', value: 'Echo', bufferId: 'openai-Echo' },
+      { label: 'Fable', value: 'Fable', bufferId: 'openai-Fable' },
+      { label: 'Onyx', value: 'Onyx', bufferId: 'openai-Onyx' },
+      { label: 'Nova', value: 'Nova', bufferId: 'openai-Nova' },
+      { label: 'Shimmer', value: 'Shimmer', bufferId: 'openai-Shimmer' }
+    ]
+  }
+];
+
+export const defaultWhisperModel: WhisperModelType = {
+  model: 'whisper-1',
+  name: 'Whisper1',
+  price: 0
+};
--- a/packages/global/core/ai/type.d.ts
+++ b/packages/global/core/ai/type.d.ts
@@ -1,9 +1,21 @@
-import OpenAI from 'openai';
-export type ChatCompletionRequestMessage = OpenAI.Chat.CreateChatCompletionRequestMessage;
-export type ChatCompletion = OpenAI.Chat.ChatCompletion;
-export type CreateChatCompletionRequest = OpenAI.Chat.ChatCompletionCreateParams;
+import type {
+  ChatCompletion,
+  ChatCompletionCreateParams,
+  ChatCompletionChunk,
+  ChatCompletionMessageParam,
+  ChatCompletionContentPart
+} from 'openai/resources';

-export type StreamChatType = Stream<OpenAI.Chat.ChatCompletionChunk>;
+export type ChatCompletionContentPart = ChatCompletionContentPart;
+export type ChatCompletionCreateParams = ChatCompletionCreateParams;
+export type ChatMessageItemType = Omit<ChatCompletionMessageParam, 'name'> & {
+  name?: any;
+  dataId?: string;
+  content: any;
+} & any;
+
+export type ChatCompletion = ChatCompletion;
+export type StreamChatType = Stream<ChatCompletionChunk>;

 export type PromptTemplateItem = {
  title: string;
--- a/packages/global/core/app/api.d.ts
+++ b/packages/global/core/app/api.d.ts
@@ -0,0 +1,18 @@
+import { AppTypeEnum } from './constants';
+import { AppSchema } from './type';
+
+export type CreateAppParams = {
+  name?: string;
+  avatar?: string;
+  type?: `${AppTypeEnum}`;
+  modules: AppSchema['modules'];
+};
+
+export interface AppUpdateParams {
+  name?: string;
+  type?: `${AppTypeEnum}`;
+  avatar?: string;
+  intro?: string;
+  modules?: AppSchema['modules'];
+  permission?: AppSchema['permission'];
+}
--- a/packages/global/core/app/constants.ts
+++ b/packages/global/core/app/constants.ts
@@ -0,0 +1,4 @@
+export enum AppTypeEnum {
+  basic = 'basic',
+  advanced = 'advanced'
+}
--- a/packages/global/core/app/type.d.ts
+++ b/packages/global/core/app/type.d.ts
@@ -0,0 +1,31 @@
+import { ModuleItemType } from '../module/type';
+import { AppTypeEnum } from './constants';
+import { PermissionTypeEnum } from '../../support/permission/constant';
+
+export interface AppSchema {
+  _id: string;
+  userId: string;
+  teamId: string;
+  tmbId: string;
+  name: string;
+  type: `${AppTypeEnum}`;
+  avatar: string;
+  intro: string;
+  updateTime: number;
+  modules: ModuleItemType[];
+  permission: `${PermissionTypeEnum}`;
+}
+
+export type AppListItemType = {
+  _id: string;
+  name: string;
+  avatar: string;
+  intro: string;
+  isOwner: boolean;
+  permission: `${PermissionTypeEnum}`;
+};
+
+export type AppDetailType = AppSchema & {
+  isOwner: boolean;
+  canWrite: boolean;
+};
--- a/projects/app/src/utils/common/adapt/message.ts
+++ b/projects/app/src/utils/common/adapt/message.ts
@@ -1,18 +1,21 @@
-import type { ChatItemType } from '@/types/chat';
-import { ChatRoleEnum } from '@/constants/chat';
-import { ChatCompletionRequestMessageRoleEnum } from '@fastgpt/global/core/ai/constant';
-import type { MessageItemType } from '@/types/core/chat/type';
+import type { ChatItemType } from '../../core/chat/type.d';
+import { ChatRoleEnum } from '../../core/chat/constants';
+import { ChatCompletionRequestMessageRoleEnum } from '../../core/ai/constant';
+import type { ChatMessageItemType } from '../../core/ai/type.d';

 const chat2Message = {
  [ChatRoleEnum.AI]: ChatCompletionRequestMessageRoleEnum.Assistant,
  [ChatRoleEnum.Human]: ChatCompletionRequestMessageRoleEnum.User,
-  [ChatRoleEnum.System]: ChatCompletionRequestMessageRoleEnum.System
+  [ChatRoleEnum.System]: ChatCompletionRequestMessageRoleEnum.System,
+  [ChatRoleEnum.Function]: ChatCompletionRequestMessageRoleEnum.Function,
+  [ChatRoleEnum.Tool]: ChatCompletionRequestMessageRoleEnum.Tool
 };
 const message2Chat = {
  [ChatCompletionRequestMessageRoleEnum.System]: ChatRoleEnum.System,
  [ChatCompletionRequestMessageRoleEnum.User]: ChatRoleEnum.Human,
  [ChatCompletionRequestMessageRoleEnum.Assistant]: ChatRoleEnum.AI,
-  [ChatCompletionRequestMessageRoleEnum.Function]: 'function'
+  [ChatCompletionRequestMessageRoleEnum.Function]: ChatRoleEnum.Function,
+  [ChatCompletionRequestMessageRoleEnum.Tool]: ChatRoleEnum.Tool
 };

 export function adaptRole_Chat2Message(role: `${ChatRoleEnum}`) {
@@ -28,10 +31,10 @@ export const adaptChat2GptMessages = ({
 }: {
  messages: ChatItemType[];
  reserveId: boolean;
-}): MessageItemType[] => {
+}): ChatMessageItemType[] => {
  return messages.map((item) => ({
    ...(reserveId && { dataId: item.dataId }),
-    role: chat2Message[item.obj] || ChatCompletionRequestMessageRoleEnum.System,
+    role: chat2Message[item.obj],
    content: item.value || ''
  }));
 };
--- a/packages/global/core/chat/api.d.ts
+++ b/packages/global/core/chat/api.d.ts
@@ -0,0 +1,34 @@
+import { ModuleItemType } from '../module/type';
+import { AdminFbkType, ChatItemType, moduleDispatchResType } from './type';
+
+export type UpdateHistoryProps = {
+  chatId: string;
+  customTitle?: string;
+  top?: boolean;
+};
+
+export type AdminUpdateFeedbackParams = AdminFbkType & {
+  chatItemId: string;
+};
+
+export type InitChatResponse = {
+  chatId: string;
+  appId: string;
+  app: {
+    userGuideModule?: ModuleItemType;
+    chatModels?: string[];
+    name: string;
+    avatar: string;
+    intro: string;
+    canUse?: boolean;
+  };
+  title: string;
+  variables: Record<string, any>;
+  history: ChatItemType[];
+};
+
+export type ChatHistoryItemResType = moduleDispatchResType & {
+  moduleType: `${FlowNodeTypeEnum}`;
+  moduleName: string;
+  moduleLogo?: string;
+};
--- a/packages/global/core/chat/constants.ts
+++ b/packages/global/core/chat/constants.ts
@@ -1,16 +1,9 @@
-import dayjs from 'dayjs';
-
-export enum sseResponseEventEnum {
-  error = 'error',
-  answer = 'answer',
-  moduleStatus = 'moduleStatus',
-  appStreamResponse = 'appStreamResponse' // sse response request
-}
-
 export enum ChatRoleEnum {
  System = 'System',
  Human = 'Human',
-  AI = 'AI'
+  AI = 'AI',
+  Function = 'Function',
+  Tool = 'Tool'
 }

 export enum TaskResponseKeyEnum {
@@ -28,6 +21,12 @@ export const ChatRoleMap = {
  },
  [ChatRoleEnum.AI]: {
    name: 'AI'
+  },
+  [ChatRoleEnum.Function]: {
+    name: 'Function'
+  },
+  [ChatRoleEnum.Tool]: {
+    name: 'Tool'
  }
 };

@@ -55,3 +54,6 @@ export const ChatSourceMap = {

 export const HUMAN_ICON = `/icon/human.svg`;
 export const LOGO_ICON = `/icon/logo.svg`;
+
+export const IMG_BLOCK_KEY = 'img-block';
+export const FILE_BLOCK_KEY = 'file-block';
--- a/packages/global/core/chat/type.d.ts
+++ b/packages/global/core/chat/type.d.ts
@@ -0,0 +1,110 @@
+import { ClassifyQuestionAgentItemType } from '../module/type';
+import { SearchDataResponseItemType } from '../dataset/type';
+import { ChatRoleEnum, ChatSourceEnum, TaskResponseKeyEnum } from './constants';
+import { FlowNodeTypeEnum } from '../module/node/constant';
+import { AppSchema } from 'core/app/type';
+
+export type ChatSchema = {
+  _id: string;
+  chatId: string;
+  userId: string;
+  teamId: string;
+  tmbId: string;
+  appId: string;
+  updateTime: Date;
+  title: string;
+  customTitle: string;
+  top: boolean;
+  variables: Record<string, any>;
+  source: `${ChatSourceEnum}`;
+  shareId?: string;
+  isInit: boolean;
+  content: ChatItemType[];
+};
+
+export type ChatWithAppSchema = Omit<ChatSchema, 'appId'> & {
+  appId: AppSchema;
+};
+
+export type ChatItemSchema = {
+  dataId: string;
+  chatId: string;
+  userId: string;
+  teamId: string;
+  tmbId: string;
+  appId: string;
+  time: Date;
+  obj: `${ChatRoleEnum}`;
+  value: string;
+  userFeedback?: string;
+  adminFeedback?: AdminFbkType;
+  [TaskResponseKeyEnum.responseData]?: ChatHistoryItemResType[];
+};
+
+export type AdminFbkType = {
+  dataId: string;
+  datasetId: string;
+  collectionId: string;
+  q: string;
+  a?: string;
+};
+
+export type ChatItemType = {
+  dataId?: string;
+  obj: ChatItemSchema['obj'];
+  value: any;
+  userFeedback?: string;
+  adminFeedback?: ChatItemSchema['feedback'];
+  [TaskResponseKeyEnum.responseData]?: ChatItemSchema[TaskResponseKeyEnum.responseData];
+};
+
+export type ChatSiteItemType = {
+  status: 'loading' | 'running' | 'finish';
+  moduleName?: string;
+  ttsBuffer?: Uint8Array;
+} & ChatItemType;
+
+export type HistoryItemType = {
+  chatId: string;
+  updateTime: Date;
+  customTitle?: string;
+  title: string;
+};
+export type ChatHistoryItemType = HistoryItemType & {
+  appId: string;
+  top: boolean;
+};
+
+// response data
+export type moduleDispatchResType = {
+  price: number;
+  runningTime?: number;
+  tokens?: number;
+  model?: string;
+
+  // chat
+  question?: string;
+  temperature?: number;
+  maxToken?: number;
+  quoteList?: SearchDataResponseItemType[];
+  historyPreview?: ChatItemType[]; // completion context array. history will slice
+
+  // dataset search
+  similarity?: number;
+  limit?: number;
+
+  // cq
+  cqList?: ClassifyQuestionAgentItemType[];
+  cqResult?: string;
+
+  // content extract
+  extractDescription?: string;
+  extractResult?: Record<string, any>;
+
+  // http
+  body?: Record<string, any>;
+  httpResult?: Record<string, any>;
+
+  // plugin output
+  pluginOutput?: Record<string, any>;
+};
--- a/packages/global/core/chat/utils.ts
+++ b/packages/global/core/chat/utils.ts
@@ -0,0 +1,6 @@
+import { IMG_BLOCK_KEY, FILE_BLOCK_KEY } from './constants';
+
+export function chatContentReplaceBlock(content: string = '') {
+  const regex = new RegExp(`\`\`\`(${IMG_BLOCK_KEY})\\n([\\s\\S]*?)\`\`\``, 'g');
+  return content.replace(regex, '').trim();
+}
--- a/packages/global/core/dataset/api.d.ts
+++ b/packages/global/core/dataset/api.d.ts
@@ -0,0 +1,20 @@
+import { DatasetDataIndexItemType } from './type';
+
+/* ================= dataset ===================== */
+
+/* ================= collection ===================== */
+
+/* ================= data ===================== */
+export type PgSearchRawType = {
+  id: string;
+  team_id: string;
+  tmb_id: string;
+  collection_id: string;
+  data_id: string;
+  score: number;
+};
+export type PushDatasetDataChunkProps = {
+  q: string; // embedding content
+  a?: string; // bonus content
+  indexes?: Omit<DatasetDataIndexItemType, 'dataId'>[];
+};
--- a/packages/global/core/dataset/constant.ts
+++ b/packages/global/core/dataset/constant.ts
@@ -1,3 +1,5 @@
+export const PgDatasetTableName = 'modeldata';
+
 export enum DatasetTypeEnum {
  folder = 'folder',
  dataset = 'dataset'
@@ -34,29 +36,54 @@ export const DatasetCollectionTypeMap = {
  }
 };

-export enum TrainingModeEnum {
-  'qa' = 'qa',
-  'index' = 'index'
+export enum DatasetDataIndexTypeEnum {
+  chunk = 'chunk',
+  qa = 'qa',
+  summary = 'summary',
+  hypothetical = 'hypothetical',
+  custom = 'custom'
 }
-export const TrainingTypeMap = {
-  [TrainingModeEnum.qa]: 'qa',
-  [TrainingModeEnum.index]: 'index'
-};
-
-export enum DatasetSpecialIdEnum {
-  manual = 'manual',
-  mark = 'mark'
-}
-export const datasetSpecialIdMap = {
-  [DatasetSpecialIdEnum.manual]: {
-    name: 'kb.Manual Data',
-    sourceName: 'kb.Manual Input'
+export const DatasetDataIndexTypeMap = {
+  [DatasetDataIndexTypeEnum.chunk]: {
+    name: 'dataset.data.indexes.chunk'
  },
-  [DatasetSpecialIdEnum.mark]: {
-    name: 'kb.Mark Data',
-    sourceName: 'kb.Manual Mark'
+  [DatasetDataIndexTypeEnum.summary]: {
+    name: 'dataset.data.indexes.summary'
+  },
+  [DatasetDataIndexTypeEnum.hypothetical]: {
+    name: 'dataset.data.indexes.hypothetical'
+  },
+  [DatasetDataIndexTypeEnum.qa]: {
+    name: 'dataset.data.indexes.qa'
+  },
+  [DatasetDataIndexTypeEnum.custom]: {
+    name: 'dataset.data.indexes.custom'
  }
 };
-export const datasetSpecialIds: string[] = [DatasetSpecialIdEnum.manual, DatasetSpecialIdEnum.mark];
+
+export enum TrainingModeEnum {
+  'chunk' = 'chunk',
+  'qa' = 'qa'
+  // 'hypothetical' = 'hypothetical',
+  // 'summary' = 'summary',
+  // 'multipleIndex' = 'multipleIndex'
+}
+export const TrainingTypeMap = {
+  [TrainingModeEnum.chunk]: {
+    name: 'chunk'
+  },
+  [TrainingModeEnum.qa]: {
+    name: 'qa'
+  }
+  // [TrainingModeEnum.hypothetical]: {
+  //   name: 'hypothetical'
+  // },
+  // [TrainingModeEnum.summary]: {
+  //   name: 'summary'
+  // },
+  // [TrainingModeEnum.multipleIndex]: {
+  //   name: 'multipleIndex'
+  // }
+};

 export const FolderAvatarSrc = '/imgs/files/folder.svg';
--- a/packages/global/core/dataset/controller.d.ts
+++ b/packages/global/core/dataset/controller.d.ts
@@ -0,0 +1,27 @@
+import type { DatasetDataIndexItemType, DatasetDataSchemaType } from './type';
+
+export type CreateDatasetDataProps = {
+  teamId: string;
+  tmbId: string;
+  datasetId: string;
+  collectionId: string;
+  q: string;
+  a?: string;
+  indexes?: Omit<DatasetDataIndexItemType, 'dataId'>[];
+};
+
+export type UpdateDatasetDataProps = {
+  dataId: string;
+  q?: string;
+  a?: string;
+  indexes?: (Omit<DatasetDataIndexItemType, 'dataId'> & {
+    dataId?: string; // pg data id
+  })[];
+};
+
+export type PatchIndexesProps = {
+  type: 'create' | 'update' | 'delete';
+  index: Omit<DatasetDataIndexItemType, 'dataId'> & {
+    dataId?: string;
+  };
+};
--- a/packages/global/core/dataset/type.d.ts
+++ b/packages/global/core/dataset/type.d.ts
@@ -1,20 +1,35 @@
-import { DatasetCollectionTypeEnum, DatasetTypeEnum, TrainingModeEnum } from './constant';
+import type { LLMModelItemType, VectorModelItemType } from '../../core/ai/model.d';
+import { PermissionTypeEnum } from '../../support/permission/constant';
+import { PushDatasetDataChunkProps } from './api';
+import {
+  DatasetCollectionTypeEnum,
+  DatasetDataIndexTypeEnum,
+  DatasetTypeEnum,
+  TrainingModeEnum
+} from './constant';

+/* schema */
 export type DatasetSchemaType = {
  _id: string;
-  userId: string;
  parentId: string;
+  userId: string;
+  teamId: string;
+  tmbId: string;
  updateTime: Date;
  avatar: string;
  name: string;
  vectorModel: string;
+  agentModel: string;
  tags: string[];
  type: `${DatasetTypeEnum}`;
+  permission: `${PermissionTypeEnum}`;
 };

 export type DatasetCollectionSchemaType = {
  _id: string;
  userId: string;
+  teamId: string;
+  tmbId: string;
  datasetId: string;
  parentId?: string;
  name: string;
@@ -27,11 +42,33 @@ export type DatasetCollectionSchemaType = {
  };
 };

+export type DatasetDataIndexItemType = {
+  defaultIndex: boolean;
+  dataId: string; // pg data id
+  type: `${DatasetDataIndexTypeEnum}`;
+  text: string;
+};
+export type DatasetDataSchemaType = {
+  _id: string;
+  userId: string;
+  teamId: string;
+  tmbId: string;
+  datasetId: string;
+  collectionId: string;
+  datasetId: string;
+  collectionId: string;
+  q: string; // large chunks or question
+  a: string; // answer or custom content
+  indexes: DatasetDataIndexItemType[];
+};
+
 export type DatasetTrainingSchemaType = {
  _id: string;
  userId: string;
+  teamId: string;
+  tmbId: string;
  datasetId: string;
-  datasetCollectionId: string;
+  collectionId: string;
  billId: string;
  expireAt: Date;
  lockTime: Date;
@@ -40,36 +77,59 @@ export type DatasetTrainingSchemaType = {
  prompt: string;
  q: string;
  a: string;
+  indexes: Omit<DatasetDataIndexItemType, 'dataId'>[];
+};
+
+export type CollectionWithDatasetType = Omit<DatasetCollectionSchemaType, 'datasetId'> & {
+  datasetId: DatasetSchemaType;
 };

 /* ================= dataset ===================== */
+export type DatasetItemType = Omit<DatasetSchemaType, 'vectorModel' | 'agentModel'> & {
+  vectorModel: VectorModelItemType;
+  agentModel: LLMModelItemType;
+  isOwner: boolean;
+  canWrite: boolean;
+};

 /* ================= collection ===================== */
+export type DatasetCollectionItemType = CollectionWithDatasetType & {
+  canWrite: boolean;
+  sourceName: string;
+  sourceId?: string;
+};

 /* ================= data ===================== */
-export type PgDataItemType = {
-  id: string;
-  q: string;
-  a: string;
-  dataset_id: string;
-  collection_id: string;
-};
-export type DatasetChunkItemType = {
-  q: string;
-  a: string;
-};
-export type DatasetDataItemType = DatasetChunkItemType & {
+export type DatasetDataItemType = {
  id: string;
  datasetId: string;
  collectionId: string;
  sourceName: string;
  sourceId?: string;
+  q: string;
+  a: string;
+  indexes: DatasetDataIndexItemType[];
+  isOwner: boolean;
+  canWrite: boolean;
+};
+
+/* --------------- file ---------------------- */
+export type DatasetFileSchema = {
+  _id: string;
+  length: number;
+  chunkSize: number;
+  uploadDate: Date;
+  filename: string;
+  contentType: string;
+  metadata: {
+    contentType: string;
+    datasetId: string;
+    teamId: string;
+    tmbId: string;
+  };
 };

 /* ============= search =============== */
-export type SearchDataResultItemType = PgDataItemType & {
-  score: number;
-};
 export type SearchDataResponseItemType = DatasetDataItemType & {
  score: number;
 };
--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
Archer	c5664c7e90	feat: vision model (#489 ) * mongo init * perf: mongo connect * perf: tts perf: whisper and tts peref: tts whisper permission log reabase (#488) * perf: modal * i18n * perf: schema lean * feat: vision model format * perf: tts loading * perf: static data * perf: tts * feat: image * perf: image * perf: upload image and title * perf: image size * doc * perf: color * doc * speaking can not select file * doc	2023-11-18 15:42:35 +08:00
heheer	70f3373246	add image input (#486 ) * add image input * use json	2023-11-17 18:22:29 +08:00
左风	af16817a4a	add wechat (#482 )	2023-11-17 17:15:41 +08:00
Archer	4358b6de4d	Add whisper and tts ui (#484 ) Co-authored-by: heheer <71265218+newfish-cmyk@users.noreply.github.com>	2023-11-17 00:03:05 +08:00
Archer	f6aea484ce	fix: 46 tmbId empty (#480 ) * mongo init * perf: mongo connect * perf: favicon * fix: member id * 46fix sh * doc	2023-11-16 17:10:04 +08:00
Archer	fbe1d8cfed	Fixed the duplicate data check problem, history filter and add tts stream (#477 )	2023-11-16 16:22:08 +08:00
Archer	16103029f5	doc and config rerank (#475 )	2023-11-16 10:46:47 +08:00
Archer	cd3acb44ab	v4.6-4 (#473 )	2023-11-15 21:35:50 +08:00
Archer	bfd8be5df0	v4.6-3 (#471 )	2023-11-15 11:36:25 +08:00
Carson Yang	592e1a93a2	README: add "back top top" button (#441 ) Signed-off-by: Carson Yang <yangchuansheng33@gmail.com>	2023-11-15 11:30:21 +08:00
heheer	2b8ff7d32c	change default title (#468 )	2023-11-13 22:44:11 +08:00
heheer	4593eef2ff	add “favicon” feconfig (#467 ) * add favicon config * add default	2023-11-13 16:05:05 +08:00
Archer	d91551e6be	v4.6-3 (#463 )	2023-11-10 11:14:08 +08:00
Archer	0a0fe31d3c	V4.6-2 (#460 )	2023-11-09 12:56:16 +08:00
不做了睡大觉	9f889d8806	Create Python API (#457 ) * 更新镜像 * 更新镜像信息 * 更新镜像信息 * Create openai_api.py * Create requirements.txt * Create README.md * 添加python接口 * Delete python directory * Create README.md * Create Python API * 文件结构化 * 文件结构化	2023-11-09 11:52:53 +08:00
Archer	8bb5588305	v4.6 -1 (#459 )	2023-11-09 09:46:57 +08:00
Archer	661ee79943	fix: CQ module output (#445 )	2023-10-30 16:45:36 +08:00
Archer	60ee160131	v4.5.2 (#439 )	2023-10-30 13:26:42 +08:00
Archer	008d0af010	Quote Modal UI and fix doc (#432 )	2023-10-25 20:13:32 +08:00
lizhuang	f2fb0aedfd	Update README.md 文档改为 https://doc.fastgpt.in网站访问 (#424 ) 文档改为https://doc.fastgpt.in网站访问	2023-10-24 18:07:30 +08:00