V4.8.15 feature (#3331)

* feat: add customize toolkit (#3205)

* chaoyang

* fix-auth

* add toolkit

* add order

* plugin usage

* fix

* delete console:

* Fix: Fix fullscreen preview top positioning and improve Markdown rendering logic (#3247)

* 完成任务：修复全屏预览顶部固定问题，优化 Markdown 渲染逻辑

* 有问题修改

* 问题再修改

* 修正问题

* fix: plugin standalone display issue (#3254)

* 4.8.15 test (#3246)

* o1 config

* perf: system plugin code

* 调整系统插件代码。增加html 渲染安全配置。 (#3258)

* perf: base64 picker

* perf: list app or dataset

* perf: plugin config code

* 小窗适配等问题 (#3257)

* 小窗适配等问题

* git问题

* 小窗剩余问题

* feat: system plugin auth and lock version (#3265)

* feat: system plugin auth and lock version

* update comment

* 4.8.15 test (#3267)

* tmp log

* perf: login direct

* perf: iframe html code

* remove log

* fix: plugin standalone display (#3277)

* refactor: 页面拆分&i18n拆分 (#3281)

* refactor: account组件拆成独立页面

* script: 新增i18n json文件创建脚本

* refactor: 页面i18n拆分

* i18n: add en&hant

* 4.8.15 test (#3285)

* tmp log

* remove log

* fix: watch avatar refresh

* perf: i18n code

* fix(plugin): use intro instead of userguide (#3290)

* Universal SSO (#3292)

* tmp log

* remove log

* feat: common oauth

* readme

* perf: sso provider

* remove sso code

* perf: refresh plugins

* feat: add api dataset (#3272)

* add api-dataset

* fix api-dataset

* fix api dataset

* fix ts

* perf: create collection code (#3301)

* tmp log

* remove log

* perf: i18n change

* update version doc

* feat: question guide from chatId

* perf: create collection code

* fix: request api

* fix: request api

* fix: tts auth and response type (#3303)

* perf: md splitter

* fix: tts auth and response type

* fix: api file dataset (#3307)

* perf: api dataset init (#3310)

* perf: collection schema

* perf: api dataset init

* refactor: 团队管理独立页面 (#3302)

* ui: 团队管理独立页面

* 代码优化

* fix

* perf: sync collection and ui check (#3314)

* perf: sync collection

* remove script

* perf: update api server

* perf: api dataset parent

* perf: team ui

* perf: team 18n

* update team ui

* perf: ui check

* perf: i18n

* fix: debug variables & cronjob & system plugin callback load (#3315)

* fix: debug variables & cronjob & system plugin callback load

* fix type

* fix

* fix

* fix: plugin dataset quote;perf: system variables init (#3316)

* fix: plugin dataset quote

* perf: system variables init

* perf: node templates ui;fix: dataset import ui (#3318)

* fix: dataset import ui

* perf: node templates ui

* perf: ui refresh

* feat:套餐改名和套餐跳转配置 (#3309)

* fixing:except Sidebar

* 去除了多余的代码

* 修正了套餐说明的代码

* 修正了误删除的show_git代码

* 修正了名字部分等代码

* 修正了问题,遗留了其他和ui讨论不一致的部分

* 4.8.15 test (#3319)

* remove log

* pref: bill ui

* pref: bill ui

* perf: log

* html渲染文档 (#3270)

* html渲染文档

* 文档有点小问题

* feat: doc (#3322)

* 集合重训练 (#3282)

* rebaser

* 一点补充

* 小问题

* 其他问题修正，删除集合保留文件的参数还没找到...

* reTraining

* delete uesless

* 删除了一行错误代码

* 集合重训练部分

* fixing

* 删除console代码

* feat: navbar item config (#3326)

* perf: custom navbar code;perf: retraining code;feat: api dataset and dataset api doc (#3329)

* feat: api dataset and dataset api doc

* perf: retraining code

* perf: custom navbar code

* fix: ts (#3330)

* fix: ts

* fix: ts

* retraining ui

* perf: api collection filter

* perf: retrining button

---------

Co-authored-by: heheer <heheer@sealos.io>
Co-authored-by: Jiangween <145003935+Jiangween@users.noreply.github.com>
Co-authored-by: papapatrick <109422393+Patrickill@users.noreply.github.com>

.github/ISSUE_TEMPLATE/bugs.md

@@ -21,7 +21,7 @@ assignees: ''
 - [ ] 公有云版本
 - [ ] 私有部署版本, 具体版本号: 
 
-**问题描述, 日志截图**
+**问题描述, 日志截图，配置文件等**
 
 **复现步骤**
 

.vscode/settings.json

@@ -16,8 +16,8 @@
     "i18n-ally.keystyle": "flat",
     "i18n-ally.sortKeys": true,
     "i18n-ally.keepFulfilled": false,
-    "i18n-ally.sourceLanguage": "zh", // 根据此语言文件翻译其他语言文件的变量和内容
-    "i18n-ally.displayLanguage": "zh", // 显示语言
+    "i18n-ally.sourceLanguage": "zh-CN", // 根据此语言文件翻译其他语言文件的变量和内容
+    "i18n-ally.displayLanguage": "zh-CN", // 显示语言
     "i18n-ally.namespace": true,
     "i18n-ally.pathMatcher": "{locale}/{namespaces}.json",
     "i18n-ally.extract.targetPickingStrategy": "most-similar-by-key",

README.md

@@ -105,12 +105,12 @@ https://github.com/labring/FastGPT/assets/15308462/7d3a38df-eb0e-4388-9250-2409b
   [点击查看 Sealos 一键部署 FastGPT 教程](https://doc.tryfastgpt.ai/docs/development/sealos/)
 
 * [快速开始本地开发](https://doc.tryfastgpt.ai/docs/development/intro/)
-* [部署 FastGPT](https://doc.tryfastgpt.ai/docs/development/sealos)
+* [部署 FastGPT](https://doc.tryfastgpt.ai/docs/development/sealos/)
 * [系统配置文件说明](https://doc.tryfastgpt.ai/docs/development/configuration/)
 * [多模型配置](https://doc.tryfastgpt.ai/docs/development/one-api/)
-* [版本更新/升级介绍](https://doc.tryfastgpt.ai/docs/development/upgrading)
+* [版本更新/升级介绍](https://doc.tryfastgpt.ai/docs/development/upgrading/)
 * [OpenAPI API 文档](https://doc.tryfastgpt.ai/docs/development/openapi/)
-* [知识库结构详解](https://doc.tryfastgpt.ai/docs/course/dataset_engine/)
+* [知识库结构详解](https://doc.tryfastgpt.ai/docs/guide/knowledge_base/rag/)
 
 <a href="#readme">
     <img src="https://img.shields.io/badge/-返回顶部-7d09f1.svg" alt="#" align="right">
@@ -118,7 +118,7 @@ https://github.com/labring/FastGPT/assets/15308462/7d3a38df-eb0e-4388-9250-2409b
 
 ## 🏘️ 社区交流群
 
-扫码加入飞书话题群 (新开，逐渐弃用微信群)：
+扫码加入飞书话题群：
 
 ![](https://oss.laf.run/otnvvf-imgs/fastgpt-feishu1.png)
 
@@ -126,6 +126,11 @@ https://github.com/labring/FastGPT/assets/15308462/7d3a38df-eb0e-4388-9250-2409b
     <img src="https://img.shields.io/badge/-返回顶部-7d09f1.svg" alt="#" align="right">
 </a>
 
+## 🏘️ 加入我们
+
+我们正在寻找志同道合的小伙伴，加速 FastGPT 的发展。你可以通过 [FastGPT 2025 招聘](https://fael3z0zfze.feishu.cn/wiki/P7FOwEmPziVcaYkvVaacnVX1nvg)了解 FastGPT 的招聘信息。
+
+
 ## 💪 相关项目
 
 - [Laf：3 分钟快速接入三方应用](https://github.com/labring/laf)
@@ -149,7 +154,7 @@ https://github.com/labring/FastGPT/assets/15308462/7d3a38df-eb0e-4388-9250-2409b
 
 ## 🌿 第三方生态
 
-- [OnWeChat 个人微信/企微机器人](https://doc.tryfastgpt.ai/docs/use-cases/onwechat/)
+- [COW 个人微信/企微机器人](https://doc.tryfastgpt.ai/docs/use-cases/external-integration/onwechat/)
 
 <a href="#readme">
     <img src="https://img.shields.io/badge/-返回顶部-7d09f1.svg" alt="#" align="right">
@@ -171,7 +176,7 @@ https://github.com/labring/FastGPT/assets/15308462/7d3a38df-eb0e-4388-9250-2409b
         <picture>
           <source media="(prefers-color-scheme: dark)" srcset="https://next.ossinsight.io/widgets/official/compose-org-active-contributors/thumbnail.png?activity=active&period=past_28_days&owner_id=102226726&repo_ids=605673387&image_size=2x3&color_scheme=dark">
           <img alt="Active participants of labring - past 28 days" src="https://next.ossinsight.io/widgets/official/compose-org-active-contributors/thumbnail.png?activity=active&period=past_28_days&owner_id=102226726&repo_ids=605673387&image_size=2x3&color_scheme=light">
-        </picture>
+        </picture>****
       </td>
       <td rowspan="2">
         <picture>

docSite/content/zh-cn/docs/development/configuration.md

@@ -23,6 +23,7 @@ weight: 708
   "systemEnv": {
     "vectorMaxProcess": 15,
     "qaMaxProcess": 15,
+    "tokenWorkers": 50, // Token 计算线程保持数，会持续占用内存，不能设置太大。
     "pgHNSWEfSearch": 100 // 向量搜索参数。越大，搜索越精确，但是速度越慢。设置为100，有99%+精度。
   },
   "llmModels": [
@@ -42,7 +43,7 @@ weight: 708
       "usedInExtractFields": true, // 是否用于内容提取（务必保证至少有一个为true）
       "usedInToolCall": true, // 是否用于工具调用（务必保证至少有一个为true）
       "usedInQueryExtension": true, // 是否用于问题优化（务必保证至少有一个为true）
-      "toolChoice": true, // 是否支持工具选择（分类，内容提取，工具调用会用到。目前只有gpt支持）
+      "toolChoice": true, // 是否支持工具选择（分类，内容提取，工具调用会用到。）
       "functionCall": false, // 是否支持函数调用（分类，内容提取，工具调用会用到。会优先使用 toolChoice，如果为false，则使用 functionCall，如果仍为 false，则使用提示词模式）
       "customCQPrompt": "", // 自定义文本分类提示词（不支持工具和函数调用的模型
       "customExtractPrompt": "", // 自定义内容提取提示词
@@ -94,9 +95,7 @@ weight: 708
       "customExtractPrompt": "",
       "defaultSystemChatPrompt": "",
       "defaultConfig": {
-        "temperature": 1,
-        "max_tokens": null,
-        "stream": false
+        "temperature": 1
       }
     },
     {
@@ -121,9 +120,7 @@ weight: 708
       "customExtractPrompt": "",
       "defaultSystemChatPrompt": "",
       "defaultConfig": {
-        "temperature": 1,
-        "max_tokens": null,
-        "stream": false
+        "temperature": 1
       }
     }
   ],

docSite/content/zh-cn/docs/development/custom-models/marker.md

@@ -0,0 +1,64 @@
+---
+title: '接入 Marker  PDF 文档解析'
+description: '使用 Marker 解析 PDF 文档，可实现图片提取和布局识别'
+icon: 'api'
+draft: false
+toc: true
+weight: 909
+---
+
+## 背景
+
+PDF 是一个相对复杂的文件格式，在 FastGPT 内置的 pdf 解析器中，依赖的是 pdfjs 库解析，该库基于逻辑解析，无法有效的理解复杂的 pdf 文件。所以我们在解析 pdf 时候，如果遇到图片、表格、公式等非简单文本内容，会发现解析效果不佳。
+
+市面上目前有多种解析 PDF 的方法，比如使用 [Marker](https://github.com/VikParuchuri/marker)，该项目使用了 Surya 模型，基于视觉解析，可以有效提取图片、表格、公式等复杂内容。为了可以让 Marker 快速接入 FastGPT，我们做了一个自定义解析的拓展 Demo。
+
+在 FastGPT 4.8.15 版本中，你可以通过增加一个环境变量，来替换掉 FastGPT 系统内置解析器，实现自定义的文档解析服务。该功能只是 Demo 阶段，后期配置模式和交互规则会发生改动。
+
+## 使用教程
+
+### 1. 按照 Marker
+
+参考文档 [Marker 安装教程](https://github.com/labring/FastGPT/tree/main/python/pdf-marker)，安装 Marker 模型。封装的 API 已经适配了 FastGPT 自定义解析服务。
+
+这里介绍快速 Docker 按照的方法：
+
+```
+```
+
+### 2. 添加 FastGPT 环境变量
+
+```
+CUSTOM_READ_FILE_URL=http://xxxx.com/v1/parse/file
+CUSTOM_READ_FILE_EXTENSION=pdf
+```
+
+* CUSTOM_READ_FILE_URL - 自定义解析服务的地址, host改成解析服务的访问地址，path 不能变动。
+* CUSTOM_READ_FILE_EXTENSION - 支持的文件后缀，多个文件类型，可用逗号隔开。
+
+### 3. 测试效果
+
+通过知识库上传一个 pdf 文件，并确认上传，可以在日志中看到 LOG （LOG_LEVEL需要设置 info 或者 debug）：
+
+```
+[Info] 2024-12-05 15:04:42 Parsing files from an external service 
+[Info] 2024-12-05 15:07:08 Custom file parsing is complete, time: 1316ms 
+```
+
+然后你就可以发现，通过 Marker 解析出来的 pdf 会携带图片链接：
+
+![alt text](/imgs/image-10.png)
+
+
+## 效果展示
+
+以清华的 [ChatDev Communicative Agents for Software Develop.pdf](https://arxiv.org/abs/2307.07924) 为例，展示 Marker 解析的效果：
+
+|  |  |  |
+| --- | --- | --- |
+| ![alt text](/imgs/image-11.png) | ![alt text](/imgs/image-12.png) | ![alt text](/imgs/image-13.png)  |
+| ![alt text](/imgs/image-14.png) | ![alt text](/imgs/image-15.png) | ![alt text](/imgs/image-16.png) |
+
+上图是分块后的结果，下图是 pdf 原文。整体图片、公式、表格都可以提取出来，效果还是杠杠的。
+
+不过要注意的是，[Marker](https://github.com/VikParuchuri/marker) 的协议是`GPL-3.0 license`，请在遵守协议的前提下使用。

docSite/content/zh-cn/docs/development/custom-models/xinference.md

@@ -145,7 +145,7 @@ curl --location --request POST 'https://<oneapi_url>/v1/chat/completions' \
       "usedInExtractFields": true, // 是否用于内容提取（务必保证至少有一个为true）
       "usedInToolCall": true, // 是否用于工具调用（务必保证至少有一个为true）
       "usedInQueryExtension": true, // 是否用于问题优化（务必保证至少有一个为true）
-      "toolChoice": true, // 是否支持工具选择（分类，内容提取，工具调用会用到。目前只有gpt支持）
+      "toolChoice": true, // 是否支持工具选择（分类，内容提取，工具调用会用到。）
       "functionCall": false, // 是否支持函数调用（分类，内容提取，工具调用会用到。会优先使用 toolChoice，如果为false，则使用 functionCall，如果仍为 false，则使用提示词模式）
       "customCQPrompt": "", // 自定义文本分类提示词（不支持工具和函数调用的模型
       "customExtractPrompt": "", // 自定义内容提取提示词

docSite/content/zh-cn/docs/development/docker.md

@@ -35,9 +35,7 @@ weight: 707
 
 ### Milvus版本
 
-暂不推荐，部分系统存在精度丢失，等待修复。
-
-对于千万级以上向量性能更优秀。
+生产部署首选，对于千万级以上向量性能更优秀。
 
 [点击查看 Milvus 官方推荐配置](https://milvus.io/docs/prerequisite-docker.md)
 
@@ -51,9 +49,7 @@ weight: 707
 
 ### zilliz cloud版本
 
-暂不推荐，部分系统存在精度丢失，等待修复。
-
-亿级以上向量首选。
+Milvus 的全托管服务，性能优于 Milvus 并提供 SLA，点击使用 [Zilliz Cloud](https://zilliz.com.cn/)。
 
 由于向量库使用了 Cloud，无需占用本地资源，无需太关注。
 
@@ -138,14 +134,16 @@ curl -o docker-compose.yml https://raw.githubusercontent.com/labring/FastGPT/mai
 # curl -o docker-compose.yml https://raw.githubusercontent.com/labring/FastGPT/main/files/docker/docker-compose-zilliz.yml
 ```
 
-### 2. 修改 docker-compose.yml 环境变量
+### 2. 修改环境变量
+
+找到 yml 文件中，fastgpt 容器的环境变量进行下面操作：
 
 {{< tabs tabTotal="3" >}}
 {{< tab tabName="PgVector版本" >}}
 {{< markdownify >}}
 
 ```
-无需操作
+FE_DOMAIN=你的前端你访问地址,例如 http://192.168.0.1:3000;https://cloud.fastgpt.cn
 ```
 
 {{< /markdownify >}}
@@ -154,7 +152,7 @@ curl -o docker-compose.yml https://raw.githubusercontent.com/labring/FastGPT/mai
 {{< markdownify >}}
 
 ```
-无需操作
+FE_DOMAIN=你的前端你访问地址,例如 http://192.168.0.1:3000;https://cloud.fastgpt.cn
 ```
 
 {{< /markdownify >}}
@@ -162,11 +160,14 @@ curl -o docker-compose.yml https://raw.githubusercontent.com/labring/FastGPT/mai
 {{< tab tabName="Zilliz版本" >}}
 {{< markdownify >}}
 
+打开 [Zilliz Cloud](https://zilliz.com.cn/), 创建实例并获取相关秘钥。
+
 ![zilliz_key](/imgs/zilliz_key.png)
 
 {{% alert icon="🤖" context="success" %}}
 
-修改`MILVUS_ADDRESS`和`MILVUS_TOKEN`链接参数，分别对应 `zilliz` 的 `Public Endpoint` 和 `Api key`，记得把自己ip加入白名单。
+1. 修改`MILVUS_ADDRESS`和`MILVUS_TOKEN`链接参数，分别对应 `zilliz` 的 `Public Endpoint` 和 `Api key`，记得把自己ip加入白名单。
+2. 修改FE_DOMAIN=你的前端你访问地址,例如 http://192.168.0.1:3000;https://cloud.fastgpt.cn
 
 {{% /alert %}}
 

docSite/content/zh-cn/docs/development/faq.md

@@ -132,7 +132,11 @@ OneAPI 的 API Key 配置错误，需要修改`OPENAI_API_KEY`环境变量，并
 
 4.8.10 版本新增了错误日志，报错时，会在日志中打印出实际发送的 Body 参数，可以复制该参数后，通过 curl 向 oneapi 发起请求测试。
 
-由于 oneapi 在 stream 模式下，无法正确捕获错误，可以设置成 `stream=false` 后进行测试。
+由于 oneapi 在 stream 模式下，无法正确捕获错误，可以设置成 `stream=false` 后进行测试。可能的问题：
+
+1. 国内模型命中风控
+2. 不支持的模型参数：只保留 messages 和必要参数来测试，删除其他参数测试。
+3. 参数不符合模型要求：例如有的模型 temperature 不支持 0，有些不支持两位小数。max_tokens 超出，上下文超长等。
 
 ### 如何测试模型是否支持工具调用
 
@@ -265,4 +269,4 @@ curl --location --request POST 'https://oneapi.xxxx/v1/chat/completions' \
   ],
   "tool_choice": "auto"
 }'
-```
+```

docSite/content/zh-cn/docs/development/openapi/auth.md

@@ -25,7 +25,7 @@ FastGPT 的 API Key **有 2 类**，一类是全局通用的 key (无法直接
 
 |        通用key               |           应用特定 key            |
 | --------------------- | --------------------- |
-| ![](/imgs/fastgpt-api2.jpg) | ![](/imgs/fastgpt-api.jpg) |
+| ![](/imgs/fastgpt-api2.jpg) | ![](/imgs/fastgpt-api1.jpg) |
 
 ## 基本配置
 

docSite/content/zh-cn/docs/development/openapi/chat.md

@@ -35,9 +35,10 @@ curl --location --request POST 'http://localhost:3000/api/v1/chat/completions' \
 --header 'Authorization: Bearer fastgpt-xxxxxx' \
 --header 'Content-Type: application/json' \
 --data-raw '{
-    "chatId": "abcd",
+    "chatId": "my_chatId",
     "stream": false,
     "detail": false,
+    "responseChatItemId": "my_responseChatItemId",
     "variables": {
         "uid": "asdfadsfasfd2323",
         "name": "张三"
@@ -104,6 +105,7 @@ curl --location --request POST 'http://localhost:3000/api/v1/chat/completions' \
   - 为 `undefined` 时（不传入），不使用 FastGpt 提供的上下文功能，完全通过传入的 messages 构建上下文。 不会将你的记录存储到数据库中，你也无法在记录汇总中查阅到。
   - 为`非空字符串`时，意味着使用 chatId 进行对话，自动从 FastGpt 数据库取历史记录，并使用 messages 数组最后一个内容作为用户问题。请自行确保 chatId 唯一，长度小于250，通常可以是自己系统的对话框ID。
 - messages: 结构与 [GPT接口](https://platform.openai.com/docs/api-reference/chat/object) chat模式一致。
+- responseChatItemId: string | undefined 。如果传入，则会将该值作为本次对话的响应消息的 ID，FastGPT 会自动将该 ID 存入数据库。请确保，在当前`chatId`下，`responseChatItemId`是唯一的。
 - detail: 是否返回中间值（模块状态，响应的完整结果等），`stream模式`下会通过`event`进行区分，`非stream模式`结果保存在`responseData`中。
 - variables: 模块变量，一个对象，会替换模块中，输入框内容里的`{{key}}`
 {{% /alert %}}

docSite/content/zh-cn/docs/development/openapi/dataset.md

@@ -31,17 +31,6 @@ curl --location --request POST 'http://localhost:3000/api/support/wallet/usage/c
 }'
 ```
 
-**x例子**
-
-```bash
-curl --location --request POST 'http://localhost:3000/api/support/wallet/bill/createTrainingBill' \
---header 'Authorization: Bearer {{apikey}}' \
---header 'Content-Type: application/json' \
---data-raw '{
-    "name": "可选，自定义订单名称，例如：文档训练-fastgpt.docx"
-}'
-```
-
 {{< /markdownify >}}
 {{< /tab >}}
 
@@ -418,9 +407,7 @@ curl --location --request POST 'http://localhost:3000/api/core/dataset/collectio
 - parentId： 父级ID，不填则默认为根目录
 - name: 集合名称（必填）
 - metadata： 元数据（暂时没啥用）
-- trainingType:（必填）
-  - chunk: 按文本长度进行分割
-  - qa: QA拆分
+- trainingType: 训练模式（必填）
 - chunkSize: 每个 chunk 的长度（可选）. chunk模式:100~3000; qa模式: 4000~模型最大token（16k模型通常建议不超过10000）
 - chunkSplitter: 自定义最高优先分割符号（可选）
 - qaPrompt: qa拆分自定义提示词（可选）
@@ -494,9 +481,7 @@ curl --location --request POST 'http://localhost:3000/api/core/dataset/collectio
 - datasetId: 知识库的ID(必填)
 - parentId： 父级ID，不填则默认为根目录
 - metadata.webPageSelector: 网页选择器，用于指定网页中的哪个元素作为文本(可选)
-- trainingType:（必填）
-  - chunk: 按文本长度进行分割
-  - qa: QA拆分
+- trainingType:训练模式（必填）
 - chunkSize: 每个 chunk 的长度（可选）. chunk模式:100~3000; qa模式: 4000~模型最大token（16k模型通常建议不超过10000）
 - chunkSplitter: 自定义最高优先分割符号（可选）
 - qaPrompt: qa拆分自定义提示词（可选）
@@ -516,7 +501,13 @@ data 为集合的 ID。
     "statusText": "",
     "message": "",
     "data": {
-        "collectionId": "65abd0ad9d1448617cba6031"
+        "collectionId": "65abd0ad9d1448617cba6031",
+        "results": {
+            "insertLen": 1,
+            "overToken": [],
+            "repeat": [],
+            "error": []
+        }
     }
 }
 ```
@@ -555,9 +546,7 @@ curl --location --request POST 'http://localhost:3000/api/core/dataset/collectio
 - data: 知识库相关信息（json序列化后传入）
   - datasetId: 知识库的ID(必填)
   - parentId： 父级ID，不填则默认为根目录
-  - trainingType:（必填）
-    - chunk: 按文本长度进行分割
-    - qa: QA拆分
+  - trainingType:训练模式（必填）
   - chunkSize: 每个 chunk 的长度（可选）. chunk模式:100~3000; qa模式: 4000~模型最大token（16k模型通常建议不超过10000）
   - chunkSplitter: 自定义最高优先分割符号（可选）
   - qaPrompt: qa拆分自定义提示词（可选）
@@ -592,6 +581,82 @@ data 为集合的 ID。
 {{< /tab >}}
 {{< /tabs >}}
 
+### 创建一个API集合
+
+传入一个文件的 id，创建一个集合，会读取文件内容进行分割。目前支持：pdf, docx, md, txt, html, csv。
+
+{{< tabs tabTotal="3" >}}
+{{< tab tabName="请求示例" >}}
+{{< markdownify >}}
+
+使用代码上传时，请注意中文 filename 需要进行 encode 处理，否则容易乱码。
+
+```bash
+curl --location --request POST 'http://localhost:3000/api/core/dataset/collection/create/apiCollection' \
+--header 'Authorization: Bearer fastgpt-xxx' \
+--header 'Content-Type: application/json' \
+--data-raw '{
+    "name": "A Quick Guide to Building a Discord Bot.pdf",
+    "apiFileId":"A Quick Guide to Building a Discord Bot.pdf",
+
+    "datasetId": "674e9e479c3503c385495027",
+    "parentId": null,
+
+    "trainingType": "chunk",
+    "chunkSize":512,
+    "chunkSplitter":"",
+    "qaPrompt":""
+}'
+```
+
+{{< /markdownify >}}
+{{< /tab >}}
+
+{{< tab tabName="参数说明" >}}
+{{< markdownify >}}
+
+需要使用 POST form-data 的格式上传。包含 file 和 data 两个字段。
+
+{{% alert icon=" " context="success" %}}
+- name: 集合名，建议就用文件名，必填。
+- apiFileId: 文件的ID，必填。
+- datasetId: 知识库的ID(必填)
+- parentId： 父级ID，不填则默认为根目录
+- trainingType:训练模式（必填）
+- chunkSize: 每个 chunk 的长度（可选）. chunk模式:100~3000; qa模式: 4000~模型最大token（16k模型通常建议不超过10000）
+- chunkSplitter: 自定义最高优先分割符号（可选）
+- qaPrompt: qa拆分自定义提示词（可选）
+{{% /alert %}}
+
+{{< /markdownify >}}
+{{< /tab >}}
+
+{{< tab tabName="响应示例" >}}
+{{< markdownify >}}
+
+data 为集合的 ID。
+
+```json
+{
+    "code": 200,
+    "statusText": "",
+    "message": "",
+    "data": {
+        "collectionId": "65abc044e4704bac793fbd81",
+        "results": {
+            "insertLen": 1,
+            "overToken": [],
+            "repeat": [],
+            "error": []
+        }
+    }
+}
+```
+
+{{< /markdownify >}}
+{{< /tab >}}
+{{< /tabs >}}
+
 ### 创建一个外部文件库集合（商业版）
 
 {{< tabs tabTotal="3" >}}
@@ -648,7 +713,12 @@ data 为集合的 ID。
   "message": "",
   "data": {
     "collectionId": "6646fcedfabd823cdc6de746",
-    "insertLen": 3
+    "results": {
+        "insertLen": 1,
+        "overToken": [],
+        "repeat": [],
+        "error": []
+    }
   }
 }
 ```
@@ -1028,9 +1098,7 @@ curl --location --request POST 'https://api.fastgpt.in/api/core/dataset/data/pus
 
 {{% alert icon=" " context="success" %}}
 - collectionId: 集合ID（必填）
-- trainingType:（必填）
-  - chunk: 按文本长度进行分割
-  - qa: QA拆分
+- trainingType:训练模式（必填）
 - prompt: 自定义 QA 拆分提示词，需严格按照模板，建议不要传入。（选填）
 - data：（具体数据）
   - q: 主要数据（必填）

docSite/content/zh-cn/docs/development/upgrading/4811.md

@@ -38,11 +38,7 @@ weight: 813
     "customExtractPrompt": "",
     "defaultSystemChatPrompt": "",
     "defaultConfig": {
-        "temperature": 1,
-        "stream": false
-    },
-    "fieldMap": {
-        "max_tokens": "max_completion_tokens"
+        "temperature": 1
     }
 },
 {
@@ -67,11 +63,7 @@ weight: 813
     "customExtractPrompt": "",
     "defaultSystemChatPrompt": "",
     "defaultConfig": {
-        "temperature": 1,
-        "stream": false
-    },
-    "fieldMap": {
-        "max_tokens": "max_completion_tokens"
+        "temperature": 1
     }
 }
 ```

docSite/content/zh-cn/docs/development/upgrading/4813.md

@@ -19,11 +19,11 @@ weight: 811
 
 ### 3. 添加环境变量
 
-- 给 fastgpt 和 fastgpt-pro 镜像添加环境变量：`FE_DOMAIN=http://xx.com`，值为 fastgpt 前端访问地址，注意后面不要加`/`。如果没加到话，图片识别可能会有问题。
+- 给 fastgpt 和 fastgpt-pro 镜像添加环境变量：`FE_DOMAIN=http://xx.com`，值为 fastgpt 前端访问地址，注意后面不要加`/`。可以自动补齐相对文件地址的前缀。
 
 ### 4. 调整文件上传编排
 
-虽然依然兼容旧版的文件上传编排，但是未来两个版本内将会去除兼容代码，请尽快调整编排，以适应最新的文件上传逻辑。尤其是嵌套应用的文件传递，未来将不会自动传递，必须手动指定传递的文件。
+虽然依然兼容旧版的文件上传编排，但是未来两个版本内将会去除兼容代码，请尽快调整编排，以适应最新的文件上传逻辑。尤其是嵌套应用的文件传递，未来将不会自动传递，必须手动指定传递的文件。具体内容可参考: [文件上传变更](/docs/guide/course/fileinput/#4813%E7%89%88%E6%9C%AC%E8%B5%B7%E5%85%B3%E4%BA%8E%E6%96%87%E4%BB%B6%E4%B8%8A%E4%BC%A0%E7%9A%84%E6%9B%B4%E6%96%B0)
 
 ## 更新说明
 

docSite/content/zh-cn/docs/development/upgrading/4814.md

@@ -1,5 +1,5 @@
 ---
-title: 'V4.8.14(进行中)'
+title: 'V4.8.14'
 description: 'FastGPT V4.8.14 更新说明'
 icon: 'upgrade'
 draft: false
@@ -7,7 +7,48 @@ toc: true
 weight: 810
 ---
 
-## 更新预告
+## 更新指南
 
-1. 
-2. 新增 - 工作流支持进入聊天框/点击开始对话后，自动触发一轮对话。
+### 1. 做好数据备份
+
+### 2. 修改镜像
+
+- 更新 FastGPT 镜像 tag: v4.8.14-fix
+- 更新 FastGPT 商业版镜像 tag: v4.8.14 （fastgpt-pro镜像）
+- Sandbox 镜像，可以不更新
+
+milvus版本使用：v4.8.14-milvus-fix 镜像。
+
+## 新功能预览
+
+### 自动触发工作流
+
+可以允许你配置用户加载对话时，自动触发一次工作流。可以用于一些 CRM 系统，可以快速的引导用户使用，无需等待用户主动触发。
+
+| | |
+| --- | --- |
+| ![alt text](/imgs/image-8.png) | ![alt text](/imgs/image-9.png) |
+
+
+## 完整更新内容
+
+1. 新增 - 工作流支持进入聊天框/点击开始对话后，自动触发一轮对话。
+2. 新增 - 重写 chatContext，对话测试也会有日志，并且刷新后不会丢失对话。
+3. 新增 - 分享链接支持配置是否允许查看原文。
+4. 新增 - 新的 doc2x 插件。
+5. 新增 - 繁体中文-台湾。
+6. 新增 - 分析链接和 chat api 支持传入自定义 uid。
+7. 商业版新增 - 微软 oauth 登录
+8. 优化 - 工作流 ui 细节。
+9. 优化 - 应用编辑记录采用 diff 存储，避免浏览器溢出。
+10. 优化 - 代码入口，增加 register 入口，无需等待首次访问才执行。
+11. 优化 - 工作流检查，增加更多缺失值检查。
+12. 优化 - 增加知识库训练最大重试次数限制。
+13. 优化 - 图片路径问题和示意图任务
+14. 优化 - Milvus description
+15. 修复 - 分块策略，四级标题会被丢失。 同时新增了五级标题的支持。
+16. 修复 - MongoDB 知识库集合唯一索引。
+17. 修复 - 反选知识库引用后可能会报错。
+18. 修复 - 简易模式转工作流，不是使用最新编辑记录进行转移。
+19. 修复 - 表单输入的说明文字不显示。
+20. 修复 - API 无法使用 base64 图片。

docSite/content/zh-cn/docs/development/upgrading/4815.md

@@ -0,0 +1,27 @@
+---
+title: 'V4.8.15(进行中)'
+description: 'FastGPT V4.8.15 更新说明'
+icon: 'upgrade'
+draft: false
+toc: true
+weight: 809
+---
+
+
+## 完整更新内容
+
+1. 新增 - API 知识库, 见 [API 知识库介绍](/docs/guide/knowledge_base/api_dataset/)，外部文件库会被弃用。
+2. 新增 - 工具箱页面，展示所有可用的系统资源。商业版后台可更便捷的配置系统插件和自定义分类。
+3. 新增 - Markdown 中，HTML代码会被额外渲染，可以选择预览模式，会限制所有 script 脚本，仅做展示。
+4. 新增 - 自定义系统级文件解析服务, 见 [接入 Marker PDF 文档解析](/docs/development/custom-models/marker/)
+5. 新增 - 集合直接重新调整参数，无需删除再导入。
+6. 新增 - 商业版后台支持配置侧边栏跳转链接。
+7. 优化 - base64 图片截取判断。
+8. 优化 - i18n cookie 判断。
+9. 优化 - 支持 Markdown 文本分割时，只有标题，无内容。
+10. 优化 - 字符串变量替换，未赋值的变量会转成 undefined，而不是保留原来 id 串。
+11. 优化 - 全局变量默认值在 API 生效，并且自定义变量支持默认值。
+12. 修复 - 分享链接点赞鉴权问题。
+13. 修复 - 对话页面切换自动执行应用时，会误触发非自动执行应用。
+14. 修复 - 语言播放鉴权问题。
+15. 修复 - 插件应用知识库引用上限始终为 3000

docSite/content/zh-cn/docs/guide/DialogBoxes/_index.md

@@ -0,0 +1,9 @@
+---
+weight: 470
+title: '对话框'
+description: '对话框组件，支持多种交互方式，提升用户在应用中的交互体验。'
+icon: 'chat_bubble'
+draft: false
+images: []
+---
+<!-- 470 ~ 500 -->

docSite/content/zh-cn/docs/guide/DialogBoxes/htmlRendering.md

@@ -0,0 +1,57 @@
+---
+title: "对话框与HTML渲染"
+description: "如何在FastGPT中通过Markdown嵌入HTML代码块，并提供全屏、源代码切换等交互功能"
+icon: "group"
+draft: false
+toc: true
+weight: 470
+---
+
+| 源码模式 | 预览模式 | 全屏模式 |
+| --- | --- | --- |
+| ![](/imgs/htmlRendering1.png) | ![](/imgs/htmlRendering2.png) | ![](/imgs/htmlRendering3.png) |
+
+
+### 1. **设计背景**
+
+  尽管Markdown本身支持嵌入HTML标签，但由于安全问题，许多平台和环境对HTML的渲染进行了限制，特别是在渲染动态内容、交互式元素以及外部资源时。这些限制大大降低了用户在撰写和展示复杂文档时的灵活性，尤其是当需要嵌入外部HTML内容时。为了应对这一问题，我们通过使用 `iframe` 来嵌入和渲染HTML内容，并结合 `sandbox` 属性，保障了外部HTML的安全渲染。
+
+### 2. 功能简介
+
+  该功能模块的主要目的是扩展FastGPT在Markdown渲染中的能力，支持嵌入和渲染HTML内容。由于是利用 Iframe 渲染，所以无法确认内容的高度，FastGPT 中会给 Iframe 设置一个固定高度来进行渲染。并且不支持 HTML 中执行 js 脚本。
+
+### 3. 技术实现
+
+  本模块通过以下方式实现了HTML渲染和互动功能：
+
+  - **组件设计**：该模块通过渲染 `iframe` 类型的代码块展示HTML内容。使用自定义的 `IframeBlock` 组件，结合 `sandbox` 属性来保障嵌入内容的安全性。`sandbox` 限制了外部HTML中的行为，如禁用脚本执行、限制表单提交等，确保HTML内容的安全性。通过辅助函数与渲染Markdown内容的部分结合，处理 `iframe` 嵌入的HTML内容。
+  - **安全机制**：通过 `iframe` 的 `sandbox` 属性和 `referrerPolicy` 来防止潜在的安全风险。`sandbox` 属性提供了细粒度的控制，允许特定的功能（如脚本、表单、弹出窗口等）在受限的环境中执行，以确保渲染的HTML内容不会对系统造成威胁。
+  - **展示与互动功能**：用户可以通过不同的展示模式（如全屏、预览、源代码模式）自由切换，以便更灵活地查看和控制嵌入的HTML内容。嵌入的 `iframe` 自适应父容器的宽度，同时保证 `iframe`嵌入的内容能够适当显示。
+
+### 4. 如何使用
+
+你只需要通过 Markdown 代码块格式，并标记语言为 `html` 即可。例如：
+
+```md
+```html
+<!DOCTYPE html>
+<html lang="zh-CN">
+  <head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <meta http-equiv="X-UA-Compatible" content="ie=edge">
+    <title>欢迎使用FastGPT</title>
+  </head>
+  <body>
+    <nav>
+      <ul>
+        <li><a href="#home">首页</a></li>
+        <li><a href="#about">关于我们</a></li>
+        <li><a href="#contact">联系我们</a></li>
+        <li><a href="#gallery">图库</a></li>
+      </ul>
+    </nav>
+  </body>
+</html>
+
+```

docSite/content/zh-cn/docs/guide/knowledge_base/api_dataset.md

@@ -0,0 +1,183 @@
+---
+title: 'API 文件库'
+description: 'FastGPT API 文件库功能介绍和使用方式'
+icon: 'language'
+draft: false
+toc: true
+weight: 405
+---
+
+| | |
+| --- | --- |
+| ![](/imgs/image-18.png) | ![](/imgs/image-19.png) |
+
+## 背景
+
+目前 FastGPT 支持本地文件导入，但是很多时候，用户自身已经有了一套文档库，如果把文件重复导入一遍，会造成二次存储，并且不方便管理。因为 FastGPT 提供了一个 API 文件库的概念，可以通过简单的 API 接口，去拉取已有的文档库，并且可以灵活配置是否导入。
+
+API 文件库能够让用户轻松对接已有的文档库，只需要按照 FastGPT 的 API 文件库规范，提供相应文件接口，然后将服务接口的 baseURL 和 token 填入知识库创建参数中，就能直接在页面上拿到文件库的内容，并选择性导入
+
+## 如何使用 API 文件库
+
+创建知识库时，选择 API 文件库类型，然后需要配置两个关键参数:文件服务接口的 baseURL 和用于身份验证的请求头信息。只要提供的接口规范符合 FastGPT 的要求，系统就能自动获取并展示完整的文件列表，可以根据需要选择性地将文件导入到知识库中。
+
+你需要提供两个参数：
+- baseURL: 文件服务接口的 baseURL
+- authorization: 用于身份验证的请求头信息，实际请求格式为 `Authorization: Bearer <token>`
+
+## 接口规范
+
+接口响应格式：
+
+```ts
+type ResponseType = {
+  success: boolean;
+  message: string;
+  data: any;
+}
+```
+
+数据类型：
+
+```ts
+// 文件列表中，单项的文件类型
+type FileListItem = {
+  id: string;
+  parentId: string | null;
+  name: string;
+  type: 'file' | 'folder';
+  updateTime: Date;
+  createTime: Date;
+}
+```
+
+
+### 1. 获取文件树
+
+{{< tabs tabTotal="2" >}}
+{{< tab tabName="请求示例" >}}
+{{< markdownify >}}
+
+{{% alert icon=" " context="success" %}}
+- parentId - 父级 id，可选，或者 null。
+- searchKey - 检索词，可选
+{{% /alert %}}
+
+```bash
+curl --location --request POST '{{baseURL}}/v1/file/list' \
+--header 'Authorization: Bearer {{authorization}}' \
+--header 'Content-Type: application/json' \
+--data-raw '{
+    "parentId": null,
+    "searchKey": ""
+}'
+```
+
+{{< /markdownify >}}
+{{< /tab >}}
+
+{{< tab tabName="响应示例" >}}
+{{< markdownify >}}
+
+```json
+{
+    "code": 200,
+    "success": true,
+    "message": "",
+    "data": [
+        {
+            "id": "xxxx",
+            "parentId": "xxxx",
+            "type": "file",  // file | folder
+            "name":"test.json",
+            "updateTime":"2024-11-26T03:05:24.759Z",
+            "createTime":"2024-11-26T03:05:24.759Z"
+        }
+   ]
+}
+```
+
+{{< /markdownify >}}
+{{< /tab >}}
+{{< /tabs >}}
+
+### 2. 获取单个文件内容（文本内容或访问链接）
+
+{{< tabs tabTotal="3" >}}
+{{< tab tabName="请求示例" >}}
+{{< markdownify >}}
+
+```bash
+curl --location --request GET '{{baseURL}}/v1/file/content?id=xx' \
+--header 'Authorization: Bearer {{authorization}}'
+```
+
+{{< /markdownify >}}
+{{< /tab >}}
+
+{{< tab tabName="响应示例" >}}
+{{< markdownify >}}
+
+```json
+{
+    "code": 200,
+    "success": true,
+    "message": "",
+    "data": {
+        "content": "FastGPT 是一个基于 LLM 大语言模型的知识库问答系统，提供开箱即用的数据处理、模型调用等能力。同时可以通过 Flow 可视化进行工作流编排，从而实现复杂的问答场景！\n",
+        "previewUrl": "xxxx"
+    }
+}
+```
+
+{{% alert icon=" " context="success" %}}
+二选一返回，如果同时返回则 content 优先级更高。
+
+- content - 文件内容，直接拿来用。
+- previewUrl - 文件链接，系统会请求该地址获取文件内容。
+{{% /alert %}}
+
+{{< /markdownify >}}
+{{< /tab >}}
+{{< /tabs >}}
+
+
+### 3. 获取文件阅读链接（用于查看原文）
+
+{{< tabs tabTotal="2" >}}
+{{< tab tabName="请求示例" >}}
+{{< markdownify >}}
+
+id 为文件的 id。
+
+```bash
+curl --location --request GET '{{baseURL}}/v1/file/read?id=xx' \
+--header 'Authorization: Bearer {{authorization}}'
+```
+
+{{< /markdownify >}}
+{{< /tab >}}
+
+{{< tab tabName="响应示例" >}}
+{{< markdownify >}}
+
+```json
+{
+    "code": 200,
+    "success": true,
+    "message": "",
+    "data": {
+        "url": "xxxx"
+    }
+}
+```
+
+{{% alert icon=" " context="success" %}}
+- url - 文件访问链接，拿到后会自动打开。
+{{% /alert %}}
+
+{{< /markdownify >}}
+{{< /tab >}}
+{{< /tabs >}}
+
+

docSite/content/zh-cn/docs/guide/knowledge_base/externalFile.md

@@ -23,4 +23,17 @@ weight: 408
 - 文件阅读ID：通常情况下，文件访问URL是临时的。如果希望永久可以访问，你需要使用该文件阅读ID，并配合上“外部预览地址”，跳转至新的阅读地址进行原文件访问。
 - 文件名：默认会自动解析文件访问URL上的文件名。如果你手动填写，将会以手动填写的值为准。
 
-[点击查看API导入文档](/docs/development/openapi/dataset/#创建一个外部文件库集合商业版)
+[点击查看API导入文档](/docs/development/openapi/dataset/#创建一个外部文件库集合商业版)
+
+## API 文件库替代方案
+
+4.8.15 提供了新的知识库类型 - API 文件库，对外部文件知识库做了进一步的拓展
+
+通过对接口进行简单的调整，就能使用 API 文件库代替外部文件知识库的功能
+
+你可以直接将外部文件知识库中的外部预览地址，作为 API 文件库接口规范中获取文件阅读链接的接口返回
+
+然后再以相同的 baseURL 实现获取文件列表和获取单个文件内容这两个接口
+
+这样就能轻松地使用 API 文件库替代原有的外部文件知识库，更多详细的内容见 API 文件库的文档
+

docSite/content/zh-cn/docs/shopping_cart/intro.md

@@ -85,16 +85,15 @@ FastGPT 商业版软件根据不同的部署方式，分为 3 类收费模式。
 
 ## QA
 
-1. 如何交付？
+### 如何交付？
 
    完整版应用 = 开源版镜像 + 商业版镜像
 
    我们会提供一个商业版镜像给你使用，该镜像需要一个 License 启动。
 
-2. 二次开发如何操作？
-
-   可自行修改开源版代码进行二次开发，不支持修改商业版镜像。
+### 二次开发如何操作？
 
+   可以修改开源版部分代码，不支持修改商业版镜像。完整版本=开源版+商业版镜像，所以是可以修改部分内容的。但是如果二开了，后续则需要自己进行代码合并升级。
 
 ## Sealos 费用
 

docSite/content/zh-cn/docs/use-cases/external-integration/official_account.md

@@ -37,40 +37,55 @@ weight: 506
 私有部署的用户可自行查阅自己的 IP 地址。
 
 海外版用户（cloud.tryfastgpt.ai)可以填写下面的 IP 白名单：
-如果仍无响应，可输入命令: `nslookup cloud.sealos.io | awk '/^Address: [0-9]/ {print $2}'` 获取最新 IP
 
 ```
-34.143.240.160
-35.197.149.75
-34.87.173.252
-34.87.20.189
-34.87.44.74
-34.124.189.116
-34.126.163.205
-35.247.161.35
-34.87.110.152
-34.87.51.146
-34.87.102.86
-35.247.163.68
 35.240.227.100
-34.142.157.52
-34.87.152.33
 34.124.237.188
-34.143.149.171
+34.143.240.160
+34.87.51.146
 34.87.79.202
-34.87.180.104
+35.247.163.68
+34.87.102.86
 35.198.192.104
+34.126.163.205
+34.124.189.116
+34.143.149.171
+34.87.173.252
+34.142.157.52
+34.87.180.104
+34.87.20.189
+34.87.110.152
+34.87.44.74
+34.87.152.33
+35.197.149.75
+35.247.161.35
 ```
 
 国内版用户（fastgpt.cn)可以填写下面的 IP 白名单：
-如果仍无响应，可输入命令: `nslookup hzh.sealos.run | awk '/^Address: [0-9]/ {print $2}'` 获取最新 IP
 
 ```
-47.98.36.227
-118.31.58.217
-121.40.213.28
-120.26.162.94
-223.4.211.186
+47.97.1.240
+121.43.105.217
+121.41.178.7
+121.40.65.187
+47.97.59.172
+101.37.205.32
+120.55.195.90
+120.26.229.115
+120.55.193.112
+47.98.190.173
+112.124.41.79
+121.196.235.183
+121.41.75.88
+121.43.108.48
+112.124.12.6
+121.43.52.222
+121.199.162.43
+121.199.162.102
+120.55.94.163
+47.99.59.223
+112.124.46.5
+121.40.46.247
 ```
 
 ## 4. 获取AES Key，选择加密方式

files/docker/docker-compose-milvus.yml

@@ -114,15 +114,15 @@ services:
   # fastgpt
   sandbox:
     container_name: sandbox
-    image: ghcr.io/labring/fastgpt-sandbox:v4.8.11 # git
-    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-sandbox:v4.8.11 # 阿里云
+    image: ghcr.io/labring/fastgpt-sandbox:v4.8.14 # git
+    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-sandbox:v4.8.14 # 阿里云
     networks:
       - fastgpt
     restart: always
   fastgpt:
     container_name: fastgpt
-    image: ghcr.io/labring/fastgpt:v4.8.11 # git
-    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.8.11 # 阿里云
+    image: ghcr.io/labring/fastgpt:v4.8.14-milvus-fix # git
+    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.8.14-milvus-fix # 阿里云
     ports:
       - 3000:3000
     networks:
@@ -133,6 +133,8 @@ services:
       - sandbox
     restart: always
     environment:
+      # 前端访问地址: http://localhost:3000
+      - FE_DOMAIN=
       # root 密码，用户名为: root。如果需要修改 root 密码，直接修改这个环境变量，并重启即可。
       - DEFAULT_ROOT_PSW=1234
       # AI模型的API地址哦。务必加 /v1。这里默认填写了OneApi的访问地址。
@@ -154,8 +156,6 @@ services:
       - MILVUS_TOKEN=none
       # sandbox 地址
       - SANDBOX_URL=http://sandbox:3000
-      # 前端地址: http://localhost:3000
-      - FE_DOMAIN=
       # 日志等级: debug, info, warn, error
       - LOG_LEVEL=info
       - STORE_LOG_LEVEL=warn

files/docker/docker-compose-pgvector.yml

@@ -72,15 +72,15 @@ services:
   # fastgpt
   sandbox:
     container_name: sandbox
-    image: ghcr.io/labring/fastgpt-sandbox:v4.8.11 # git
-    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-sandbox:v4.8.11 # 阿里云
+    image: ghcr.io/labring/fastgpt-sandbox:v4.8.13 # git
+    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-sandbox:v4.8.13 # 阿里云
     networks:
       - fastgpt
     restart: always
   fastgpt:
     container_name: fastgpt
-    image: ghcr.io/labring/fastgpt:v4.8.11 # git
-    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.8.11 # 阿里云
+    image: ghcr.io/labring/fastgpt:v4.8.14 # git
+    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.8.14 # 阿里云
     ports:
       - 3000:3000
     networks:
@@ -91,6 +91,8 @@ services:
       - sandbox
     restart: always
     environment:
+      # 前端访问地址: http://localhost:3000
+      - FE_DOMAIN=
       # root 密码，用户名为: root。如果需要修改 root 密码，直接修改这个环境变量，并重启即可。
       - DEFAULT_ROOT_PSW=1234
       # AI模型的API地址哦。务必加 /v1。这里默认填写了OneApi的访问地址。
@@ -111,8 +113,6 @@ services:
       - PG_URL=postgresql://username:password@pg:5432/postgres
       # sandbox 地址
       - SANDBOX_URL=http://sandbox:3000
-      # 前端地址: http://localhost:3000
-      - FE_DOMAIN=
       # 日志等级: debug, info, warn, error
       - LOG_LEVEL=info
       - STORE_LOG_LEVEL=warn

files/docker/docker-compose-zilliz.yml

@@ -53,15 +53,15 @@ services:
         wait $$!
   sandbox:
     container_name: sandbox
-    image: ghcr.io/labring/fastgpt-sandbox:v4.8.11 # git
-    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-sandbox:v4.8.11 # 阿里云
+    image: ghcr.io/labring/fastgpt-sandbox:v4.8.14 # git
+    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-sandbox:v4.8.14 # 阿里云
     networks:
       - fastgpt
     restart: always
   fastgpt:
     container_name: fastgpt
-    image: ghcr.io/labring/fastgpt:v4.8.11 # git
-    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.8.11 # 阿里云
+    image: ghcr.io/labring/fastgpt:v4.8.14-milvus-fix # git
+    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.8.14-milvus-fix # 阿里云
     ports:
       - 3000:3000
     networks:
@@ -71,6 +71,8 @@ services:
       - sandbox
     restart: always
     environment:
+      # 前端访问地址: http://localhost:3000
+      - FE_DOMAIN=
       # root 密码，用户名为: root。如果需要修改 root 密码，直接修改这个环境变量，并重启即可。
       - DEFAULT_ROOT_PSW=1234
       # AI模型的API地址哦。务必加 /v1。这里默认填写了OneApi的访问地址。
@@ -92,8 +94,6 @@ services:
       - MILVUS_TOKEN=zilliz_cloud_token
       # sandbox 地址
       - SANDBOX_URL=http://sandbox:3000
-      # 前端地址: http://localhost:3000
-      - FE_DOMAIN=
       # 日志等级: debug, info, warn, error
       - LOG_LEVEL=info
       - STORE_LOG_LEVEL=warn

package.json

@@ -10,7 +10,8 @@
     "postinstall": "sh ./scripts/postinstall.sh",
     "initIcon": "node ./scripts/icon/init.js",
     "previewIcon": "node ./scripts/icon/index.js",
-    "api:gen": "tsc ./scripts/openapi/index.ts && node ./scripts/openapi/index.js && npx @redocly/cli build-docs ./scripts/openapi/openapi.json -o ./projects/app/public/openapi/index.html"
+    "api:gen": "tsc ./scripts/openapi/index.ts && node ./scripts/openapi/index.js && npx @redocly/cli build-docs ./scripts/openapi/openapi.json -o ./projects/app/public/openapi/index.html",
+    "create:i18n": "node ./scripts/i18n/index.js"
   },
   "devDependencies": {
     "@chakra-ui/cli": "^2.4.1",

packages/global/common/error/code/dataset.ts

@@ -1,3 +1,4 @@
+import { i18nT } from '../../../../web/i18n/utils';
 import { ErrType } from '../errorCode';
 
 /* dataset: 501000 */
@@ -9,9 +10,19 @@ export enum DatasetErrEnum {
   unAuthDatasetData = 'unAuthDatasetData',
   unAuthDatasetFile = 'unAuthDatasetFile',
   unLinkCollection = 'unLinkCollection',
-  invalidVectorModelOrQAModel = 'invalidVectorModelOrQAModel'
+  invalidVectorModelOrQAModel = 'invalidVectorModelOrQAModel',
+  notSupportSync = 'notSupportSync',
+  sameApiCollection = 'sameApiCollection'
 }
 const datasetErr = [
+  {
+    statusText: DatasetErrEnum.sameApiCollection,
+    message: i18nT('dataset:same_api_collection')
+  },
+  {
+    statusText: DatasetErrEnum.notSupportSync,
+    message: i18nT('dataset:collection_not_support_sync')
+  },
   {
     statusText: DatasetErrEnum.unExist,
     message: 'core.dataset.error.unExistDataset'

packages/global/common/error/code/user.ts

@@ -5,7 +5,8 @@ export enum UserErrEnum {
   unAuthUser = 'unAuthUser',
   unAuthRole = 'unAuthRole',
   binVisitor = 'binVisitor',
-  balanceNotEnough = 'balanceNotEnough'
+  balanceNotEnough = 'balanceNotEnough',
+  unAuthSso = 'unAuthSso'
 }
 const errList = [
   {
@@ -23,6 +24,10 @@ const errList = [
   {
     statusText: UserErrEnum.balanceNotEnough,
     message: i18nT('common:code_error.user_error.balance_not_enough')
+  },
+  {
+    statusText: UserErrEnum.unAuthSso,
+    message: i18nT('user:sso_auth_failed')
   }
 ];
 export default errList.reduce((acc, cur, index) => {

packages/global/common/file/icon.ts

@@ -12,5 +12,7 @@ export const fileImgs = [
 ];
 
 export function getFileIcon(name = '', defaultImg = 'file/fill/file') {
-  return fileImgs.find((item) => new RegExp(item.suffix, 'gi').test(name))?.src || defaultImg;
+  return (
+    fileImgs.find((item) => new RegExp(`\.${item.suffix}`, 'gi').test(name))?.src || defaultImg
+  );
 }

packages/global/common/file/tools.ts

@@ -23,6 +23,11 @@ export const parseUrlToFileType = (url: string): UserChatItemValueItemType['file
   const parseUrl = new URL(url, 'https://locaohost:3000');
 
   const filename = (() => {
+    // Check base64 image
+    if (url.startsWith('data:image/')) {
+      const mime = url.split(',')[0].split(':')[1].split(';')[0];
+      return `image.${mime.split('/')[1]}`;
+    }
     // Old version file url: https://xxx.com/file/read?filename=xxx.pdf
     const filenameQuery = parseUrl.searchParams.get('filename');
     if (filenameQuery) return filenameQuery;

packages/global/common/file/type.d.ts

@@ -3,6 +3,7 @@ import { BucketNameEnum } from './constants';
 export type FileTokenQuery = {
   bucketName: `${BucketNameEnum}`;
   teamId: string;
-  tmbId: string;
+  uid: string; // tmbId/ share uid/ teamChat uid
   fileId: string;
+  customExpireMinutes?: number;
 };

packages/global/common/string/markdown.ts

@@ -95,20 +95,23 @@ export const markdownProcess = async ({
 };
 
 export const matchMdImgTextAndUpload = (text: string) => {
-  const base64Regex = /"(data:image\/[^;]+;base64[^"]+)"/g;
+  const base64Regex = /!\[([^\]]*)\]\((data:image\/[^;]+;base64[^)]+)\)/g;
   const imageList: ImageType[] = [];
-  const images = Array.from(text.match(base64Regex) || []);
-  for (const image of images) {
+
+  text = text.replace(base64Regex, (match, altText, base64Url) => {
     const uuid = `IMAGE_${getNanoid(12)}_IMAGE`;
-    const mime = image.split(';')[0].split(':')[1];
-    const base64 = image.split(',')[1];
-    text = text.replace(image, uuid);
+    const mime = base64Url.split(';')[0].split(':')[1];
+    const base64 = base64Url.split(',')[1];
+
     imageList.push({
       uuid,
       base64,
       mime
     });
-  }
+
+    // 保持原有的 alt 文本，只替换 base64 部分
+    return `![${altText}](${uuid})`;
+  });
 
   return {
     text,

packages/global/common/string/textSplitter.ts

@@ -99,7 +99,7 @@ ${mdSplitString}
   5. 标点分割：重叠
 */
 const commonSplit = (props: SplitProps): SplitResponse => {
-  let { text = '', chunkLen, overlapRatio = 0.2, customReg = [] } = props;
+  let { text = '', chunkLen, overlapRatio = 0.15, customReg = [] } = props;
 
   const splitMarker = 'SPLIT_HERE_SPLIT_HERE';
   const codeBlockMarker = 'CODE_BLOCK_LINE_MARKER';
@@ -113,6 +113,8 @@ const commonSplit = (props: SplitProps): SplitResponse => {
   text = text.replace(/(\r?\n|\r){3,}/g, '\n\n\n');
 
   // The larger maxLen is, the next sentence is less likely to trigger splitting
+  const markdownIndex = 4;
+  const forbidOverlapIndex = 8;
   const stepReges: { reg: RegExp; maxLen: number }[] = [
     ...customReg.map((text) => ({
       reg: new RegExp(`(${replaceRegChars(text)})`, 'g'),
@@ -122,9 +124,11 @@ const commonSplit = (props: SplitProps): SplitResponse => {
     { reg: /^(##\s[^\n]+\n)/gm, maxLen: chunkLen * 1.4 },
     { reg: /^(###\s[^\n]+\n)/gm, maxLen: chunkLen * 1.6 },
     { reg: /^(####\s[^\n]+\n)/gm, maxLen: chunkLen * 1.8 },
+    { reg: /^(#####\s[^\n]+\n)/gm, maxLen: chunkLen * 1.8 },
 
     { reg: /([\n]([`~]))/g, maxLen: chunkLen * 4 }, // code block
-    { reg: /([\n](?!\s*[\*\-|>0-9]))/g, maxLen: chunkLen * 2 }, // 增大块，尽可能保证它是一个完整的段落。 (?![\*\-|>`0-9]): markdown special char
+    { reg: /([\n](?=\s*[0-9]+\.))/g, maxLen: chunkLen * 2 }, // 增大块，尽可能保证它是一个完整的段落。 (?![\*\-|>`0-9]): markdown special char
+    { reg: /(\n{2,})/g, maxLen: chunkLen * 1.6 },
     { reg: /([\n])/g, maxLen: chunkLen * 1.2 },
     // ------ There's no overlap on the top
     { reg: /([。]|([a-zA-Z])\.\s)/g, maxLen: chunkLen * 1.2 },
@@ -136,8 +140,10 @@ const commonSplit = (props: SplitProps): SplitResponse => {
 
   const customRegLen = customReg.length;
   const checkIsCustomStep = (step: number) => step < customRegLen;
-  const checkIsMarkdownSplit = (step: number) => step >= customRegLen && step <= 3 + customRegLen;
-  const checkForbidOverlap = (step: number) => step <= 6 + customRegLen;
+  const checkIsMarkdownSplit = (step: number) =>
+    step >= customRegLen && step <= markdownIndex + customRegLen;
+  +customReg.length;
+  const checkForbidOverlap = (step: number) => step <= forbidOverlapIndex + customRegLen;
 
   // if use markdown title split, Separate record title
   const getSplitTexts = ({ text, step }: { text: string; step: number }) => {
@@ -176,7 +182,7 @@ const commonSplit = (props: SplitProps): SplitResponse => {
           title: matchTitle
         };
       })
-      .filter((item) => item.text?.trim());
+      .filter((item) => !!item.title || !!item.text?.trim());
   };
 
   /* Gets the overlap at the end of a text as the beginning of the next block */
@@ -231,7 +237,7 @@ const commonSplit = (props: SplitProps): SplitResponse => {
       // use slice-chunkLen to split text
       const chunks: string[] = [];
       for (let i = 0; i < text.length; i += chunkLen - overlapLen) {
-        chunks.push(`${parentTitle}${text.slice(i, i + chunkLen)}`);
+        chunks.push(text.slice(i, i + chunkLen));
       }
       return chunks;
     }
@@ -241,7 +247,6 @@ const commonSplit = (props: SplitProps): SplitResponse => {
 
     const maxLen = splitTexts.length > 1 ? stepReges[step].maxLen : chunkLen;
     const minChunkLen = chunkLen * 0.7;
-    // console.log(splitTexts, stepReges[step].reg);
 
     const chunks: string[] = [];
     for (let i = 0; i < splitTexts.length; i++) {
@@ -249,12 +254,36 @@ const commonSplit = (props: SplitProps): SplitResponse => {
 
       const lastTextLen = lastText.length;
       const currentText = item.text;
-      const currentTextLen = currentText.length;
       const newText = lastText + currentText;
-      const newTextLen = lastTextLen + currentTextLen;
+      const newTextLen = newText.length;
+
+      // Markdown 模式下，会强制向下拆分最小块，并再最后一个标题时候，给小块都补充上所有标题（包含父级标题）
+      if (isMarkdownStep) {
+        // split new Text, split chunks must will greater 1 (small lastText)
+        const innerChunks = splitTextRecursively({
+          text: newText,
+          step: step + 1,
+          lastText: '',
+          parentTitle: parentTitle + item.title
+        });
+
+        if (innerChunks.length === 0) {
+          chunks.push(`${parentTitle}${item.title}`);
+          continue;
+        }
+
+        chunks.push(
+          ...innerChunks.map(
+            (chunk) =>
+              step === markdownIndex + customRegLen ? `${parentTitle}${item.title}${chunk}` : chunk // 合并进 Markdown 分块时，需要补标题
+          )
+        );
+
+        continue;
+      }
 
       // newText is too large(now, The lastText must be smaller than chunkLen)
-      if (newTextLen > maxLen || isMarkdownStep) {
+      if (newTextLen > maxLen) {
         // lastText greater minChunkLen, direct push it to chunks, not add to next chunk. (large lastText)
         if (lastTextLen > minChunkLen) {
           chunks.push(lastText);
@@ -278,15 +307,6 @@ const commonSplit = (props: SplitProps): SplitResponse => {
 
         if (!lastChunk) continue;
 
-        if (forbidConcat) {
-          chunks.push(
-            ...innerChunks.map(
-              (chunk) => (step === 3 + customRegLen ? `${parentTitle}${chunk}` : chunk) // 合并进 Markdown 分块时，需要补标题
-            )
-          );
-          continue;
-        }
-
         // last chunk is too small, concat it to lastText(next chunk start)
         if (lastChunk.length < minChunkLen) {
           chunks.push(...innerChunks.slice(0, -1));
@@ -304,11 +324,11 @@ const commonSplit = (props: SplitProps): SplitResponse => {
         continue;
       }
 
-      // new text is small
+      // New text is small
 
       // Not overlap
       if (forbidConcat) {
-        chunks.push(`${parentTitle}${item.title}${item.text}`);
+        chunks.push(item.text);
         continue;
       }
 

packages/global/common/system/types/index.d.ts

@@ -10,6 +10,14 @@ import type {
 } from '../../../core/ai/model.d';
 import { SubTypeEnum } from '../../../support/wallet/sub/constants';
 
+export type NavbarItemType = {
+  id: string;
+  name: string;
+  avatar: string;
+  url: string;
+  isActive: boolean;
+};
+
 /* fastgpt main */
 export type FastGPTConfigFileType = {
   feConfigs: FastGPTFeConfigsType;
@@ -38,7 +46,6 @@ export type FastGPTFeConfigsType = {
   concatMd?: string;
 
   docUrl?: string;
-  chatbotUrl?: string;
   openAPIDocUrl?: string;
   systemPluginCourseUrl?: string;
   appTemplateCourse?: string;
@@ -56,7 +63,11 @@ export type FastGPTFeConfigsType = {
     github?: string;
     google?: string;
     wechat?: string;
-    microsoft?: string;
+    microsoft?: {
+      clientId?: string;
+      tenantId?: string;
+      customButton?: string;
+    };
   };
   limit?: {
     exportDatasetLimitMinutes?: number;
@@ -70,6 +81,7 @@ export type FastGPTFeConfigsType = {
   uploadFileMaxAmount?: number;
   uploadFileMaxSize?: number;
   lafEnv?: string;
+  navbarItems?: NavbarItemType[];
 };
 
 export type SystemEnvType = {

packages/global/core/ai/type.d.ts

@@ -49,6 +49,7 @@ export type ChatCompletionMessageParam = (
   | CustomChatCompletionAssistantMessageParam
 ) & {
   dataId?: string;
+  hideInUI?: boolean;
 };
 export type SdkChatCompletionMessageParam = SdkChatCompletionMessageParam;
 

packages/global/core/app/constants.ts

@@ -1,4 +1,9 @@
-import { AppTTSConfigType, AppFileSelectConfigType, AppWhisperConfigType } from './type';
+import {
+  AppTTSConfigType,
+  AppFileSelectConfigType,
+  AppWhisperConfigType,
+  AppAutoExecuteConfigType
+} from './type';
 
 export enum AppTypeEnum {
   folder = 'folder',
@@ -12,6 +17,11 @@ export const AppFolderTypeList = [AppTypeEnum.folder, AppTypeEnum.httpPlugin];
 
 export const defaultTTSConfig: AppTTSConfigType = { type: 'web' };
 
+export const defaultAutoExecuteConfig: AppAutoExecuteConfigType = {
+  open: false,
+  defaultPrompt: ''
+};
+
 export const defaultWhisperConfig: AppWhisperConfigType = {
   open: false,
   autoSend: false,
@@ -38,3 +48,5 @@ export enum AppTemplateTypeEnum {
   roleplay = 'roleplay',
   officeServices = 'office-services'
 }
+
+export const defaultDatasetMaxTokens = 16000;

packages/global/core/app/type.d.ts

@@ -96,6 +96,7 @@ export type AppSimpleEditFormType = {
 export type AppChatConfigType = {
   welcomeText?: string;
   variables?: VariableItemType[];
+  autoExecute?: AppAutoExecuteConfigType;
   questionGuide?: boolean;
   ttsConfig?: AppTTSConfigType;
   whisperConfig?: AppWhisperConfigType;
@@ -158,9 +159,20 @@ export type AppScheduledTriggerConfigType = {
   timezone: string;
   defaultPrompt: string;
 };
+// auto execute
+export type AppAutoExecuteConfigType = {
+  open: boolean;
+  defaultPrompt: string;
+};
 // File
 export type AppFileSelectConfigType = {
   canSelectFile: boolean;
   canSelectImg: boolean;
   maxFiles: number;
 };
+
+export type SystemPluginListItemType = {
+  _id: string;
+  name: string;
+  avatar: string;
+};

packages/global/core/chat/adapt.ts

@@ -76,6 +76,7 @@ export const chats2GPTMessages = ({
 
       results.push({
         dataId,
+        hideInUI: item.hideInUI,
         role: ChatCompletionRequestMessageRoleEnum.User,
         content: simpleUserContentPart(value)
       });
@@ -318,6 +319,7 @@ export const GPTMessages2Chats = (
       return {
         dataId: item.dataId,
         obj,
+        hideInUI: item.hideInUI,
         value
       } as ChatItemType;
     })

packages/global/core/chat/api.d.ts

@@ -1,11 +1,9 @@
-export type UpdateChatFeedbackProps = {
+import { OutLinkChatAuthProps } from '../../support/permission/chat';
+
+export type UpdateChatFeedbackProps = OutLinkChatAuthProps & {
   appId: string;
   chatId: string;
   dataId: string;
-  shareId?: string;
-  teamId?: string;
-  teamToken?: string;
-  outLinkUid?: string;
   userBadFeedback?: string;
   userGoodFeedback?: string;
 };

packages/global/core/chat/type.d.ts

@@ -56,6 +56,7 @@ export type UserChatItemValueItemType = {
 export type UserChatItemType = {
   obj: ChatRoleEnum.Human;
   value: UserChatItemValueItemType[];
+  hideInUI?: boolean;
 };
 export type SystemChatItemValueItemType = {
   type: ChatItemValueTypeEnum.text;

packages/global/core/chat/utils.ts

@@ -101,7 +101,7 @@ export const filterPublicNodeResponseData = ({
       for (let key in item) {
         if (key === 'toolDetail' || key === 'pluginDetail') {
           // @ts-ignore
-          obj[key] = filterPublicNodeResponseData({ flowResponses: item[key] });
+          obj[key] = filterPublicNodeResponseData({ flowResponses: item[key], responseDetail });
         } else if (filedList.includes(key)) {
           // @ts-ignore
           obj[key] = item[key];

packages/global/core/dataset/api.d.ts

@@ -16,6 +16,7 @@ export type DatasetUpdateBody = {
   websiteConfig?: DatasetSchemaType['websiteConfig'];
   externalReadUrl?: DatasetSchemaType['externalReadUrl'];
   defaultPermission?: DatasetSchemaType['defaultPermission'];
+  apiServer?: DatasetSchemaType['apiServer'];
 };
 
 /* ================= collection ===================== */
@@ -34,15 +35,18 @@ export type CreateDatasetCollectionParams = DatasetCollectionChunkMetadataType &
   name: string;
   type: DatasetCollectionTypeEnum;
 
-  tags?: string[];
-
   fileId?: string;
   rawLink?: string;
   externalFileId?: string;
-
   externalFileUrl?: string;
+  apiFileId?: string;
+
   rawTextLength?: number;
   hashRawText?: string;
+
+  tags?: string[];
+
+  createTime?: Date;
 };
 
 export type ApiCreateDatasetCollectionParams = DatasetCollectionChunkMetadataType & {
@@ -56,9 +60,17 @@ export type TextCreateDatasetCollectionParams = ApiCreateDatasetCollectionParams
 export type LinkCreateDatasetCollectionParams = ApiCreateDatasetCollectionParams & {
   link: string;
 };
+export type ApiDatasetCreateDatasetCollectionParams = ApiCreateDatasetCollectionParams & {
+  name: string;
+  apiFileId: string;
+};
 export type FileIdCreateDatasetCollectionParams = ApiCreateDatasetCollectionParams & {
   fileId: string;
 };
+export type reTrainingDatasetFileCollectionParams = DatasetCollectionChunkMetadataType & {
+  datasetId: string;
+  collectionId: string;
+};
 export type FileCreateDatasetCollectionParams = ApiCreateDatasetCollectionParams & {
   fileMetadata?: Record<string, any>;
   collectionMetadata?: Record<string, any>;

packages/global/core/dataset/apiDataset.d.ts

@@ -0,0 +1,24 @@
+export type APIFileItem = {
+  id: string;
+  parentId: string | null;
+  name: string;
+  type: 'file' | 'folder';
+  updateTime: Date;
+  createTime: Date;
+};
+
+export type APIFileServer = {
+  baseUrl: string;
+  authorization: string;
+};
+
+export type APIFileListResponse = APIFileItem[];
+
+export type APIFileContentResponse = {
+  content?: string;
+  previewUrl?: string;
+};
+
+export type APIFileReadResponse = {
+  url: string;
+};

packages/global/core/dataset/collection/utils.ts

@@ -9,7 +9,8 @@ export const getCollectionSourceData = (
       collection?.fileId ||
       collection?.rawLink ||
       collection?.externalFileId ||
-      collection?.externalFileUrl,
+      collection?.externalFileUrl ||
+      collection?.apiFileId,
     sourceName: collection?.name || ''
   };
 };

packages/global/core/dataset/constants.ts

@@ -1,9 +1,12 @@
+import { i18nT } from '../../../web/i18n/utils';
+
 /* ------------ dataset -------------- */
 export enum DatasetTypeEnum {
   folder = 'folder',
   dataset = 'dataset',
   websiteDataset = 'websiteDataset', // depp link
-  externalFile = 'externalFile'
+  externalFile = 'externalFile',
+  apiDataset = 'apiDataset'
 }
 export const DatasetTypeMap = {
   [DatasetTypeEnum.folder]: {
@@ -25,6 +28,11 @@ export const DatasetTypeMap = {
     icon: 'core/dataset/externalDatasetOutline',
     label: 'external_file',
     collectionLabel: 'common.File'
+  },
+  [DatasetTypeEnum.apiDataset]: {
+    icon: 'core/dataset/externalDatasetOutline',
+    label: 'api_file',
+    collectionLabel: 'common.File'
   }
 };
 
@@ -34,10 +42,10 @@ export enum DatasetStatusEnum {
 }
 export const DatasetStatusMap = {
   [DatasetStatusEnum.active]: {
-    label: 'core.dataset.status.active'
+    label: i18nT('common:core.dataset.status.active')
   },
   [DatasetStatusEnum.syncing]: {
-    label: 'core.dataset.status.syncing'
+    label: i18nT('common:core.dataset.status.syncing')
   }
 };
 
@@ -48,23 +56,27 @@ export enum DatasetCollectionTypeEnum {
 
   file = 'file',
   link = 'link', // one link
-  externalFile = 'externalFile'
+  externalFile = 'externalFile',
+  apiFile = 'apiFile'
 }
 export const DatasetCollectionTypeMap = {
   [DatasetCollectionTypeEnum.folder]: {
-    name: 'core.dataset.folder'
+    name: i18nT('common:core.dataset.folder')
   },
   [DatasetCollectionTypeEnum.file]: {
-    name: 'core.dataset.file'
+    name: i18nT('common:core.dataset.file')
   },
   [DatasetCollectionTypeEnum.externalFile]: {
-    name: 'core.dataset.externalFile'
+    name: i18nT('common:core.dataset.externalFile')
   },
   [DatasetCollectionTypeEnum.link]: {
-    name: 'core.dataset.link'
+    name: i18nT('common:core.dataset.link')
   },
   [DatasetCollectionTypeEnum.virtual]: {
-    name: 'core.dataset.Manual collection'
+    name: i18nT('common:core.dataset.Manual collection')
+  },
+  [DatasetCollectionTypeEnum.apiFile]: {
+    name: i18nT('common:core.dataset.apiFile')
   }
 };
 
@@ -74,10 +86,10 @@ export enum DatasetCollectionSyncResultEnum {
 }
 export const DatasetCollectionSyncResultMap = {
   [DatasetCollectionSyncResultEnum.sameRaw]: {
-    label: 'core.dataset.collection.sync.result.sameRaw'
+    label: i18nT('common:core.dataset.collection.sync.result.sameRaw')
   },
   [DatasetCollectionSyncResultEnum.success]: {
-    label: 'core.dataset.collection.sync.result.success'
+    label: i18nT('common:core.dataset.collection.sync.result.success')
   }
 };
 
@@ -89,7 +101,9 @@ export enum ImportDataSourceEnum {
   fileLink = 'fileLink',
   fileCustom = 'fileCustom',
   csvTable = 'csvTable',
-  externalFile = 'externalFile'
+  externalFile = 'externalFile',
+  apiDataset = 'apiDataset',
+  reTraining = 'reTraining'
 }
 
 export enum TrainingModeEnum {
@@ -100,18 +114,18 @@ export enum TrainingModeEnum {
 
 export const TrainingTypeMap = {
   [TrainingModeEnum.chunk]: {
-    label: 'core.dataset.training.Chunk mode',
-    tooltip: 'core.dataset.import.Chunk Split Tip',
+    label: i18nT('common:core.dataset.training.Chunk mode'),
+    tooltip: i18nT('common:core.dataset.import.Chunk Split Tip'),
     openSource: true
   },
   [TrainingModeEnum.auto]: {
-    label: 'core.dataset.training.Auto mode',
-    tooltip: 'core.dataset.training.Auto mode Tip',
+    label: i18nT('common:core.dataset.training.Auto mode'),
+    tooltip: i18nT('common:core.dataset.training.Auto mode Tip'),
     openSource: false
   },
   [TrainingModeEnum.qa]: {
-    label: 'core.dataset.training.QA mode',
-    tooltip: 'core.dataset.import.QA Import Tip',
+    label: i18nT('common:core.dataset.training.QA mode'),
+    tooltip: i18nT('common:core.dataset.import.QA Import Tip'),
     openSource: true
   }
 };
@@ -126,20 +140,20 @@ export enum DatasetSearchModeEnum {
 export const DatasetSearchModeMap = {
   [DatasetSearchModeEnum.embedding]: {
     icon: 'core/dataset/modeEmbedding',
-    title: 'core.dataset.search.mode.embedding',
-    desc: 'core.dataset.search.mode.embedding desc',
+    title: i18nT('common:core.dataset.search.mode.embedding'),
+    desc: i18nT('common:core.dataset.search.mode.embedding desc'),
     value: DatasetSearchModeEnum.embedding
   },
   [DatasetSearchModeEnum.fullTextRecall]: {
     icon: 'core/dataset/fullTextRecall',
-    title: 'core.dataset.search.mode.fullTextRecall',
-    desc: 'core.dataset.search.mode.fullTextRecall desc',
+    title: i18nT('common:core.dataset.search.mode.fullTextRecall'),
+    desc: i18nT('common:core.dataset.search.mode.fullTextRecall desc'),
     value: DatasetSearchModeEnum.fullTextRecall
   },
   [DatasetSearchModeEnum.mixedRecall]: {
     icon: 'core/dataset/mixedRecall',
-    title: 'core.dataset.search.mode.mixedRecall',
-    desc: 'core.dataset.search.mode.mixedRecall desc',
+    title: i18nT('common:core.dataset.search.mode.mixedRecall'),
+    desc: i18nT('common:core.dataset.search.mode.mixedRecall desc'),
     value: DatasetSearchModeEnum.mixedRecall
   }
 };
@@ -152,23 +166,23 @@ export enum SearchScoreTypeEnum {
 }
 export const SearchScoreTypeMap = {
   [SearchScoreTypeEnum.embedding]: {
-    label: 'core.dataset.search.score.embedding',
-    desc: 'core.dataset.search.score.embedding desc',
+    label: i18nT('common:core.dataset.search.score.embedding'),
+    desc: i18nT('common:core.dataset.search.score.embedding desc'),
     showScore: true
   },
   [SearchScoreTypeEnum.fullText]: {
-    label: 'core.dataset.search.score.fullText',
-    desc: 'core.dataset.search.score.fullText desc',
+    label: i18nT('common:core.dataset.search.score.fullText'),
+    desc: i18nT('common:core.dataset.search.score.fullText desc'),
     showScore: false
   },
   [SearchScoreTypeEnum.reRank]: {
-    label: 'core.dataset.search.score.reRank',
-    desc: 'core.dataset.search.score.reRank desc',
+    label: i18nT('common:core.dataset.search.score.reRank'),
+    desc: i18nT('common:core.dataset.search.score.reRank desc'),
     showScore: true
   },
   [SearchScoreTypeEnum.rrf]: {
-    label: 'core.dataset.search.score.rrf',
-    desc: 'core.dataset.search.score.rrf desc',
+    label: i18nT('common:core.dataset.search.score.rrf'),
+    desc: i18nT('common:core.dataset.search.score.rrf desc'),
     showScore: false
   }
 };
@@ -180,5 +194,7 @@ export const LinkCollectionIcon = 'common/linkBlue';
 export enum DatasetSourceReadTypeEnum {
   fileLocal = 'fileLocal',
   link = 'link',
-  externalFile = 'externalFile'
+  externalFile = 'externalFile',
+  apiFile = 'apiFile',
+  reTraining = 'reTraining'
 }

packages/global/core/dataset/read.ts

@@ -1,14 +0,0 @@
-import { DatasetSourceReadTypeEnum, ImportDataSourceEnum } from './constants';
-
-export const importType2ReadType = (type: ImportDataSourceEnum) => {
-  if (type === ImportDataSourceEnum.csvTable || type === ImportDataSourceEnum.fileLocal) {
-    return DatasetSourceReadTypeEnum.fileLocal;
-  }
-  if (type === ImportDataSourceEnum.fileLink) {
-    return DatasetSourceReadTypeEnum.link;
-  }
-  if (type === ImportDataSourceEnum.externalFile) {
-    return DatasetSourceReadTypeEnum.externalFile;
-  }
-  return DatasetSourceReadTypeEnum.link;
-};

packages/global/core/dataset/type.d.ts

@@ -10,6 +10,7 @@ import {
 } from './constants';
 import { DatasetPermission } from '../../support/permission/dataset/controller';
 import { Permission } from '../../support/permission/controller';
+import { APIFileServer } from './apiDataset';
 
 export type DatasetSchemaType = {
   _id: string;
@@ -30,10 +31,11 @@ export type DatasetSchemaType = {
     url: string;
     selector: string;
   };
-  externalReadUrl?: string;
   inheritPermission: boolean;
+  apiServer?: APIFileServer;
 
   // abandon
+  externalReadUrl?: string;
   defaultPermission?: number;
 };
 
@@ -64,6 +66,7 @@ export type DatasetCollectionSchemaType = {
   rawTextLength?: number;
   hashRawText?: string;
   externalFileUrl?: string; // external import url
+  apiFileId?: string; // api file id
   metadata?: {
     webPageSelector?: string;
     relatedImgId?: string; // The id of the associated image collections
@@ -204,7 +207,8 @@ export type DatasetFileSchema = {
   contentType: string;
   metadata: {
     teamId: string;
-    tmbId: string;
+    tmbId?: string;
+    uid: string;
     encoding?: string;
   };
 };

packages/global/core/plugin/type.d.ts

@@ -39,6 +39,7 @@ export type PluginTemplateType = PluginRuntimeType & {
 };
 
 export type PluginRuntimeType = {
+  id: string;
   teamId?: string;
   name: string;
   avatar: string;
@@ -46,4 +47,6 @@ export type PluginRuntimeType = {
   isTool?: boolean;
   nodes: StoreNodeItemType[];
   edges: StoreEdgeItemType[];
+  currentCost?: number;
+  hasTokenFee?: boolean;
 };

packages/global/core/workflow/constants.ts

@@ -106,6 +106,7 @@ export enum NodeInputKeyEnum {
   variables = 'variables',
   scheduleTrigger = 'scheduleTrigger',
   chatInputGuide = 'chatInputGuide',
+  autoExecute = 'autoExecute',
 
   // plugin config
   instruction = 'instruction',

packages/global/core/workflow/runtime/type.d.ts

@@ -82,17 +82,6 @@ export type RuntimeNodeItemType = {
   version: string;
 };
 
-export type PluginRuntimeType = {
-  id: string;
-  teamId?: string;
-  name: string;
-  avatar: string;
-  showStatus?: boolean;
-  currentCost?: number;
-  nodes: StoreNodeItemType[];
-  edges: StoreEdgeItemType[];
-};
-
 export type RuntimeEdgeItemType = StoreEdgeItemType & {
   status: 'waiting' | 'active' | 'skipped';
 };

packages/global/core/workflow/runtime/utils.ts

@@ -283,68 +283,47 @@ export const getReferenceVariableValue = ({
 export function replaceEditorVariable({
   text,
   nodes,
-  variables,
-  runningNode
+  variables
 }: {
   text: any;
   nodes: RuntimeNodeItemType[];
   variables: Record<string, any>; // global variables
-  runningNode: RuntimeNodeItemType;
 }) {
   if (typeof text !== 'string') return text;
 
-  const globalVariables = Object.keys(variables).map((key) => {
-    return {
-      nodeId: VARIABLE_NODE_ID,
-      id: key,
-      value: variables[key]
-    };
-  });
+  const variablePattern = /\{\{\$([^.]+)\.([^$]+)\$\}\}/g;
+  const matches = [...text.matchAll(variablePattern)];
+  if (matches.length === 0) return text;
 
-  // Upstream node outputs
-  const nodeVariables = nodes
-    .map((node) => {
-      return node.outputs.map((output) => {
-        return {
-          nodeId: node.nodeId,
-          id: output.id,
-          value: output.value
-        };
-      });
-    })
-    .flat();
+  matches.forEach((match) => {
+    const nodeId = match[1];
+    const id = match[2];
 
-  // Get runningNode inputs(Will be replaced with reference)
-  const customInputs = runningNode.inputs.flatMap((item) => {
-    return [
-      {
-        id: item.key,
-        value: getReferenceVariableValue({
-          value: item.value,
-          nodes,
-          variables
-        }),
-        nodeId: runningNode.nodeId
+    const variableVal = (() => {
+      if (nodeId === VARIABLE_NODE_ID) {
+        return variables[id];
       }
-    ];
-  });
+      // Find upstream node input/output
+      const node = nodes.find((node) => node.nodeId === nodeId);
+      if (!node) return;
 
-  const allVariables = [...globalVariables, ...nodeVariables, ...customInputs];
+      const output = node.outputs.find((output) => output.id === id);
+      if (output) return output.value;
 
-  // Replace {{$xxx.xxx$}} to value
-  for (const key in allVariables) {
-    const variable = allVariables[key];
-    const val = variable.value;
-    const formatVal = (() => {
-      if (val === undefined) return '';
-      if (val === null) return 'null';
-
-      return typeof val === 'object' ? JSON.stringify(val) : String(val);
+      const input = node.inputs.find((input) => input.key === id);
+      if (input) return getReferenceVariableValue({ value: input.value, nodes, variables });
     })();
 
-    const regex = new RegExp(`\\{\\{\\$(${variable.nodeId}\\.${variable.id})\\$\\}\\}`, 'g');
+    const formatVal = (() => {
+      if (variableVal === undefined) return 'undefined';
+      if (variableVal === null) return 'null';
+      return typeof variableVal === 'object' ? JSON.stringify(variableVal) : String(variableVal);
+    })();
+
+    const regex = new RegExp(`\\{\\{\\$(${nodeId}\\.${id})\\$\\}\\}`, 'g');
     text = text.replace(regex, formatVal);
-  }
+  });
+
   return text || '';
 }
 

packages/global/core/workflow/type/index.d.ts

@@ -63,15 +63,20 @@ export type TemplateMarketListItemType = {
 // system plugin
 export type SystemPluginTemplateItemType = WorkflowTemplateType & {
   customWorkflow?: string;
+  associatedPluginId?: string;
+  userGuide?: string;
 
-  templateType: FlowNodeTemplateTypeEnum;
+  templateType: string;
   isTool?: boolean;
 
   // commercial plugin config
   originCost: number; // n points/one time
   currentCost: number;
+  hasTokenFee: boolean;
+  pluginOrder: number;
 
   isActive?: boolean;
+  isOfficial?: boolean;
   inputConfig?: {
     // Render config input form. Find the corresponding node and replace the variable directly
     key: string;

packages/global/core/workflow/type/node.d.ts

@@ -54,7 +54,7 @@ type HandleType = {
 // system template
 export type FlowNodeTemplateType = FlowNodeCommonType & {
   id: string; // node id, unique
-  templateType: FlowNodeTemplateTypeEnum;
+  templateType: string;
 
   // show handle
   sourceHandle?: HandleType;
@@ -76,7 +76,7 @@ export type NodeTemplateListItemType = {
   flowNodeType: FlowNodeTypeEnum; // render node card
   parentId?: ParentIdType;
   isFolder?: boolean;
-  templateType: FlowNodeTemplateTypeEnum;
+  templateType: string;
   avatar?: string;
   name: string;
   intro?: string; // template list intro
@@ -85,10 +85,12 @@ export type NodeTemplateListItemType = {
   author?: string;
   unique?: boolean; // 唯一的
   currentCost?: number; // 当前积分消耗
+  hasTokenFee?: boolean; // 是否配置积分
+  instructions?: string; // 使用说明
 };
 
 export type NodeTemplateListType = {
-  type: FlowNodeTemplateTypeEnum;
+  type: string;
   label: string;
   list: NodeTemplateListItemType[];
 }[];

packages/global/core/workflow/utils.ts

@@ -25,10 +25,12 @@ import type {
   AppWhisperConfigType,
   AppScheduledTriggerConfigType,
   ChatInputGuideConfigType,
-  AppChatConfigType
+  AppChatConfigType,
+  AppAutoExecuteConfigType
 } from '../app/type';
 import { EditorVariablePickerType } from '../../../web/components/common/Textarea/PromptEditor/type';
 import {
+  defaultAutoExecuteConfig,
   defaultChatInputGuideConfig,
   defaultTTSConfig,
   defaultWhisperConfig
@@ -69,34 +71,37 @@ export const getGuideModule = (modules: StoreNodeItemType[]) =>
   );
 export const splitGuideModule = (guideModules?: StoreNodeItemType) => {
   const welcomeText: string =
-    guideModules?.inputs?.find((item) => item.key === NodeInputKeyEnum.welcomeText)?.value || '';
+    guideModules?.inputs?.find((item) => item.key === NodeInputKeyEnum.welcomeText)?.value ?? '';
 
   const variables: VariableItemType[] =
-    guideModules?.inputs.find((item) => item.key === NodeInputKeyEnum.variables)?.value || [];
+    guideModules?.inputs.find((item) => item.key === NodeInputKeyEnum.variables)?.value ?? [];
 
   const questionGuide: boolean =
-    !!guideModules?.inputs?.find((item) => item.key === NodeInputKeyEnum.questionGuide)?.value ||
+    !!guideModules?.inputs?.find((item) => item.key === NodeInputKeyEnum.questionGuide)?.value ??
     false;
 
   const ttsConfig: AppTTSConfigType =
-    guideModules?.inputs?.find((item) => item.key === NodeInputKeyEnum.tts)?.value ||
+    guideModules?.inputs?.find((item) => item.key === NodeInputKeyEnum.tts)?.value ??
     defaultTTSConfig;
 
   const whisperConfig: AppWhisperConfigType =
-    guideModules?.inputs?.find((item) => item.key === NodeInputKeyEnum.whisper)?.value ||
+    guideModules?.inputs?.find((item) => item.key === NodeInputKeyEnum.whisper)?.value ??
     defaultWhisperConfig;
 
-  const scheduledTriggerConfig: AppScheduledTriggerConfigType = guideModules?.inputs?.find(
-    (item) => item.key === NodeInputKeyEnum.scheduleTrigger
-  )?.value;
+  const scheduledTriggerConfig: AppScheduledTriggerConfigType =
+    guideModules?.inputs?.find((item) => item.key === NodeInputKeyEnum.scheduleTrigger)?.value ??
+    undefined;
 
   const chatInputGuide: ChatInputGuideConfigType =
-    guideModules?.inputs?.find((item) => item.key === NodeInputKeyEnum.chatInputGuide)?.value ||
+    guideModules?.inputs?.find((item) => item.key === NodeInputKeyEnum.chatInputGuide)?.value ??
     defaultChatInputGuideConfig;
 
-  // plugin
   const instruction: string =
-    guideModules?.inputs?.find((item) => item.key === NodeInputKeyEnum.instruction)?.value || '';
+    guideModules?.inputs?.find((item) => item.key === NodeInputKeyEnum.instruction)?.value ?? '';
+
+  const autoExecute: AppAutoExecuteConfigType =
+    guideModules?.inputs?.find((item) => item.key === NodeInputKeyEnum.autoExecute)?.value ??
+    defaultAutoExecuteConfig;
 
   return {
     welcomeText,
@@ -106,7 +111,8 @@ export const splitGuideModule = (guideModules?: StoreNodeItemType) => {
     whisperConfig,
     scheduledTriggerConfig,
     chatInputGuide,
-    instruction
+    instruction,
+    autoExecute
   };
 };
 
@@ -132,7 +138,8 @@ export const getAppChatConfig = ({
     whisperConfig,
     scheduledTriggerConfig,
     chatInputGuide,
-    instruction
+    instruction,
+    autoExecute
   } = splitGuideModule(systemConfigNode);
 
   const config: AppChatConfigType = {
@@ -142,6 +149,7 @@ export const getAppChatConfig = ({
     scheduledTriggerConfig,
     chatInputGuide,
     instruction,
+    autoExecute,
     ...chatConfig,
     variables: storeVariables ?? chatConfig?.variables ?? variables,
     welcomeText: storeWelcomeText ?? chatConfig?.welcomeText ?? welcomeText

packages/global/support/user/constant.ts

@@ -15,5 +15,6 @@ export enum OAuthEnum {
   github = 'github',
   google = 'google',
   wechat = 'wechat',
-  microsoft = 'microsoft'
+  microsoft = 'microsoft',
+  sso = 'sso'
 }

packages/global/support/wallet/sub/api.d.ts

@@ -12,6 +12,7 @@ export type StandardSubPlanUpdateResponse = {
   payPrice?: number;
   planPrice: number;
   planPointPrice: number;
+  name?: string;
 
   currentMode: `${SubModeEnum}`;
   nextMode: `${SubModeEnum}`;

packages/global/support/wallet/sub/type.d.ts

@@ -2,6 +2,7 @@ import { StandardSubLevelEnum, SubModeEnum, SubTypeEnum } from './constants';
 
 // Content of plan
 export type TeamStandardSubPlanItemType = {
+  name?: string;
   price: number; // read price / month
   pointPrice: number; // read price/ one thousand
   totalPoints: number; // n
@@ -24,6 +25,7 @@ export type StandSubPlanLevelMapType = Record<
 
 export type SubPlanType = {
   [SubTypeEnum.standard]: StandSubPlanLevelMapType;
+  planDescriptionUrl?: string;
   [SubTypeEnum.extraDatasetSize]: {
     price: number;
   };

packages/plugins/register.ts

@@ -40,7 +40,8 @@ export const getCommunityPlugins = () => {
       id: `${PluginSourceEnum.community}-${name}`,
       isFolder,
       parentId,
-      isActive: true
+      isActive: true,
+      isOfficial: true
     };
   });
 };

packages/plugins/src/Doc2X/PDF2text/index.ts

@@ -4,6 +4,7 @@ import { getErrText } from '@fastgpt/global/common/error/utils';
 
 type Props = {
   apikey: string;
+  HTMLtable: boolean;
   files: string[];
 };
 
@@ -14,7 +15,88 @@ type Response = Promise<{
   error?: Record<string, any>;
 }>;
 
-const main = async ({ apikey, files }: Props): Response => {
+function processContent(content: string, HTMLtable: boolean): string {
+  if (HTMLtable) {
+    return content;
+  }
+  return content.replace(/<table>[\s\S]*?<\/table>/g, (htmlTable) => {
+    try {
+      // Clean up whitespace and newlines
+      const cleanHtml = htmlTable.replace(/\n\s*/g, '');
+      const rows = cleanHtml.match(/<tr>(.*?)<\/tr>/g);
+      if (!rows) return htmlTable;
+
+      // Parse table data
+      let tableData: string[][] = [];
+      let maxColumns = 0;
+
+      // Try to convert to markdown table
+      try {
+        rows.forEach((row, rowIndex) => {
+          if (!tableData[rowIndex]) {
+            tableData[rowIndex] = [];
+          }
+          let colIndex = 0;
+          const cells = row.match(/<td.*?>(.*?)<\/td>/g) || [];
+
+          cells.forEach((cell) => {
+            while (tableData[rowIndex][colIndex]) {
+              colIndex++;
+            }
+            const colspan = parseInt(cell.match(/colspan="(\d+)"/)?.[1] || '1');
+            const rowspan = parseInt(cell.match(/rowspan="(\d+)"/)?.[1] || '1');
+            const content = cell.replace(/<td.*?>|<\/td>/g, '').trim();
+
+            for (let i = 0; i < rowspan; i++) {
+              for (let j = 0; j < colspan; j++) {
+                if (!tableData[rowIndex + i]) {
+                  tableData[rowIndex + i] = [];
+                }
+                tableData[rowIndex + i][colIndex + j] = i === 0 && j === 0 ? content : '^^';
+              }
+            }
+            colIndex += colspan;
+            maxColumns = Math.max(maxColumns, colIndex);
+          });
+
+          for (let i = 0; i < maxColumns; i++) {
+            if (!tableData[rowIndex][i]) {
+              tableData[rowIndex][i] = ' ';
+            }
+          }
+        });
+        const chunks: string[] = [];
+
+        const headerCells = tableData[0]
+          .slice(0, maxColumns)
+          .map((cell) => (cell === '^^' ? ' ' : cell || ' '));
+        const headerRow = '| ' + headerCells.join(' | ') + ' |';
+        chunks.push(headerRow);
+
+        const separator = '| ' + Array(headerCells.length).fill('---').join(' | ') + ' |';
+        chunks.push(separator);
+
+        tableData.slice(1).forEach((row) => {
+          const paddedRow = row
+            .slice(0, maxColumns)
+            .map((cell) => (cell === '^^' ? ' ' : cell || ' '));
+          while (paddedRow.length < maxColumns) {
+            paddedRow.push(' ');
+          }
+          chunks.push('| ' + paddedRow.join(' | ') + ' |');
+        });
+
+        return chunks.join('\n');
+      } catch (error) {
+        return htmlTable;
+      }
+    } catch (error) {
+      return htmlTable;
+    }
+  });
+}
+
+const main = async ({ apikey, files, HTMLtable }: Props): Response => {
   // Check the apikey
   if (!apikey) {
     return Promise.reject(`API key is required`);
@@ -30,77 +112,88 @@ const main = async ({ apikey, files }: Props): Response => {
   for await (const url of files) {
     try {
       //Fetch the pdf and check its content type
-      const PDFResponse = await axiosInstance.get(url, { responseType: 'arraybuffer' });
+      const PDFResponse = await axios
+        .get(url, {
+          responseType: 'arraybuffer',
+          proxy: false,
+          timeout: 20000
+        })
+        .catch((error) => {
+          throw new Error(`[Fetch PDF Error] Failed to fetch PDF: ${getErrText(error)}`);
+        });
+
       if (PDFResponse.status !== 200) {
         throw new Error(
-          `File:${url} \n<Content>\nFailed to fetch PDF from URL: ${PDFResponse.statusText}\n</Content>`
+          `[Fetch PDF Error] Failed with status ${PDFResponse.status}: ${PDFResponse.data}`
         );
       }
 
       const contentType = PDFResponse.headers['content-type'];
       const file_name = url.match(/read\/([^?]+)/)?.[1] || 'unknown.pdf';
       if (!contentType || !contentType.startsWith('application/pdf')) {
-        throw new Error(
-          `File:${file_name}\n<Content>\nThe provided file does not point to a PDF: ${contentType}\n</Content>`
-        );
+        throw new Error(`The provided file does not point to a PDF: ${contentType}`);
       }
 
       const blob = new Blob([PDFResponse.data], { type: 'application/pdf' });
       // Get pre-upload URL first
-      const preupload_response = await axiosInstance.post(
-        'https://v2.doc2x.noedgeai.com/api/v2/parse/preupload',
-        null,
-        {
+      const preupload_response = await axiosInstance
+        .post('https://v2.doc2x.noedgeai.com/api/v2/parse/preupload', null, {
           headers: {
             Authorization: `Bearer ${apikey}`
           }
-        }
-      );
+        })
+        .catch((error) => {
+          throw new Error(`[Pre-upload Error] Failed to get pre-upload URL: ${getErrText(error)}`);
+        });
 
       if (preupload_response.status !== 200) {
-        throw new Error(
-          `File:${file_name}\n<Content>\nFailed to get pre-upload URL: ${preupload_response.statusText}\n</Content>`
-        );
+        throw new Error(`Failed to get pre-upload URL: ${preupload_response.data}`);
       }
 
       const preupload_data = preupload_response.data;
       if (preupload_data.code !== 'success') {
-        throw new Error(
-          `File:${file_name}\n<Content>\nFailed to get pre-upload URL: ${JSON.stringify(preupload_data)}\n</Content>`
-        );
+        throw new Error(`Failed to get pre-upload URL: ${JSON.stringify(preupload_data)}`);
       }
 
       const upload_url = preupload_data.data.url;
       const uid = preupload_data.data.uid;
       // Upload file to pre-signed URL with binary stream
 
-      const response = await axiosInstance.put(upload_url, blob, {
-        headers: {
-          'Content-Type': 'application/pdf'
-        }
-      });
+      const response = await axiosInstance
+        .put(upload_url, blob, {
+          headers: {
+            'Content-Type': 'application/pdf'
+          }
+        })
+        .catch((error) => {
+          throw new Error(`[Upload Error] Failed to upload file: ${getErrText(error)}`);
+        });
+
       if (response.status !== 200) {
         throw new Error(`Upload failed with status ${response.status}: ${response.statusText}`);
       }
 
       // Get the result by uid
 
-      // Wait for the result, at most 90s
-      const checkResult = async (retry = 30) => {
+      // Wait for the result
+      const checkResult = async (retry = 20) => {
         if (retry <= 0)
           return Promise.reject(
-            `File:${file_name}\n<Content>\nFailed to get result (uid: ${uid}): Get result timeout\n</Content>`
+            `File:${file_name}\n<Content>\n[Parse Timeout Error] Failed to get result (uid: ${uid}): Process timeout\n</Content>`
           );
 
         try {
-          const result_response = await axiosInstance.get(
-            `https://v2.doc2x.noedgeai.com/api/v2/parse/status?uid=${uid}`,
-            {
+          const result_response = await axiosInstance
+            .get(`https://v2.doc2x.noedgeai.com/api/v2/parse/status?uid=${uid}`, {
               headers: {
                 Authorization: `Bearer ${apikey}`
               }
-            }
-          );
+            })
+            .catch((error) => {
+              throw new Error(
+                `[Parse Status Error] Failed to get parse status: ${getErrText(error)}`
+              );
+            });
 
           const result_data = result_response.data;
           if (!['ok', 'success'].includes(result_data.code)) {
@@ -110,29 +203,35 @@ const main = async ({ apikey, files }: Props): Response => {
           }
 
           if (['ready', 'processing'].includes(result_data.data.status)) {
-            await delay(3000);
+            await delay(4000);
             return checkResult(retry - 1);
           }
 
           if (result_data.data.status === 'success') {
-            const result = (
+            const result = processContent(
               await Promise.all(
                 result_data.data.result.pages.map((page: { md: any }) => page.md)
-              ).then((pages) => pages.join('\n'))
+              ).then((pages) => pages.join('\n')),
+              HTMLtable
             )
               // Do some post-processing
               .replace(/\\[\(\)]/g, '$')
               .replace(/\\[\[\]]/g, '$$')
-              .replace(/<img\s+src="([^"]+)"(?:\s*\?[^>]*)?(?:\s*\/>|>)/g, '![img]($1)');
+              .replace(/<img\s+src="([^"]+)"(?:\s*\?[^>]*)?(?:\s*\/>|>)/g, '![img]($1)')
+              .replace(/<!-- Media -->/g, '')
+              .replace(/<!-- Footnote -->/g, '')
+              .replace(/\$(.+?)\s+\\tag\{(.+?)\}\$/g, '$$$1 \\qquad \\qquad ($2)$$')
+              .replace(/\\text\{([^}]*?)(\b\w+)_(\w+\b)([^}]*?)\}/g, '\\text{$1$2\\_$3$4}');
 
             return `File:${file_name}\n<Content>\n${result}\n</Content>`;
           }
-
-          await delay(100);
           return checkResult(retry - 1);
         } catch (error) {
-          await delay(100);
-          return checkResult(retry - 1);
+          if (retry > 1) {
+            await delay(100);
+            return checkResult(retry - 1);
+          }
+          throw error;
         }
       };
 
@@ -140,7 +239,7 @@ const main = async ({ apikey, files }: Props): Response => {
       successResult.push(result);
     } catch (error) {
       failedResult.push(
-        `File:${url} \n<Content>\nFailed to fetch image from URL: ${getErrText(error)}\n</Content>`
+        `File:${url} \n<Content>\nFailed to fetch file from URL: ${getErrText(error)}\n</Content>`
       );
     }
   }

packages/plugins/src/Doc2X/PDF2text/template.json

@@ -7,10 +7,8 @@
   "courseUrl": "https://fael3z0zfze.feishu.cn/wiki/Rkc5witXWiJoi5kORd2cofh6nDg?fromScene=spaceOverview",
   "showStatus": true,
   "weight": 10,
-
   "isTool": true,
   "templateType": "tools",
-
   "workflow": {
     "nodes": [
       {
@@ -52,6 +50,26 @@
             "canSelectImg": false,
             "maxFiles": 14,
             "defaultValue": ""
+          },
+          {
+            "renderTypeList": ["switch", "reference"],
+            "selectedTypeIndex": 0,
+            "valueType": "boolean",
+            "canEdit": true,
+            "key": "HTMLtable",
+            "label": "HTMLtable",
+            "description": "是否以HTML格式输出表格。如果需要精确地输出表格，请打开此开关以使用HTML格式。关闭后，表格将转换为Markdown形式输出，但这可能会损失一些表格特性，如合并单元格。",
+            "defaultValue": false,
+            "list": [
+              {
+                "label": "",
+                "value": ""
+              }
+            ],
+            "maxFiles": 5,
+            "canSelectFile": true,
+            "canSelectImg": true,
+            "required": true
           }
         ],
         "outputs": [
@@ -68,6 +86,13 @@
             "key": "files",
             "label": "files",
             "type": "hidden"
+          },
+          {
+            "id": "htmltable",
+            "valueType": "boolean",
+            "key": "HTMLtable",
+            "label": "HTMLtable",
+            "type": "hidden"
           }
         ]
       },
@@ -220,7 +245,7 @@
             "key": "system_httpJsonBody",
             "renderTypeList": ["hidden"],
             "valueType": "any",
-            "value": "{\n  \"apikey\": \"{{apikey}}\",\n  \"files\": {{files}}\n}",
+            "value": "{\n  \"apikey\": \"{{apikey}}\",\n  \"HTMLtable\": {{HTMLtable}},\n  \"files\": {{files}}\n}",
             "label": "",
             "required": false,
             "debugLabel": "",
@@ -305,6 +330,36 @@
             },
             "required": true,
             "value": [["pluginInput", "url"]]
+          },
+          {
+            "renderTypeList": ["reference"],
+            "valueType": "boolean",
+            "canEdit": true,
+            "key": "HTMLtable",
+            "label": "HTMLtable",
+            "customInputConfig": {
+              "selectValueTypeList": [
+                "string",
+                "number",
+                "boolean",
+                "object",
+                "arrayString",
+                "arrayNumber",
+                "arrayBoolean",
+                "arrayObject",
+                "arrayAny",
+                "any",
+                "chatHistory",
+                "datasetQuote",
+                "dynamic",
+                "selectApp",
+                "selectDataset"
+              ],
+              "showDescription": false,
+              "showDefaultValue": true
+            },
+            "required": true,
+            "value": ["pluginInput", "htmltable"]
           }
         ],
         "outputs": [

packages/plugins/type.d.ts

@@ -1,6 +1,7 @@
 import { PluginTemplateType } from '@fastgpt/global/core/plugin/type.d';
 import { systemPluginResponseEnum } from '@fastgpt/global/core/workflow/runtime/constants';
 import { SystemPluginTemplateItemType } from '@fastgpt/global/core/workflow/type';
+import { PluginGroupSchemaType } from '@fastgpt/service/core/app/plugin/type';
 
 export type SystemPluginResponseType = Promise<Record<string, any>>;
 export type SystemPluginSpecialResponse = {
@@ -10,6 +11,7 @@ export type SystemPluginSpecialResponse = {
 };
 
 declare global {
+  var pluginGroups: PluginGroupSchemaType[];
   var systemPlugins: SystemPluginTemplateItemType[];
   var systemPluginCb: Record<string, (e: any) => SystemPluginResponseType>;
 }

packages/service/common/api/serverRequest.ts

@@ -83,8 +83,8 @@ export function request(url: string, data: any, config: ConfigType, method: Meth
       baseURL: serverRequestBaseUrl,
       url,
       method,
-      data: ['POST', 'PUT'].includes(method) ? data : null,
-      params: !['POST', 'PUT'].includes(method) ? data : null,
+      data: ['POST', 'PUT'].includes(method) ? data : undefined,
+      params: !['POST', 'PUT'].includes(method) ? data : undefined,
       ...config // custom config
     })
     .then((res) => checkRes(res.data))

packages/service/common/file/gridfs/controller.ts

@@ -32,7 +32,7 @@ export function getGridBucket(bucket: `${BucketNameEnum}`) {
 export async function uploadFile({
   bucketName,
   teamId,
-  tmbId,
+  uid,
   path,
   filename,
   contentType,
@@ -41,7 +41,7 @@ export async function uploadFile({
 }: {
   bucketName: `${BucketNameEnum}`;
   teamId: string;
-  tmbId: string;
+  uid: string; // tmbId / outLinkUId
   path: string;
   filename: string;
   contentType?: string;
@@ -58,7 +58,7 @@ export async function uploadFile({
 
   // Add default metadata
   metadata.teamId = teamId;
-  metadata.tmbId = tmbId;
+  metadata.uid = uid;
   metadata.encoding = encoding;
 
   // create a gridfs bucket

packages/service/common/file/multer.ts

@@ -4,7 +4,7 @@ import path from 'path';
 import { BucketNameEnum, bucketNameMap } from '@fastgpt/global/common/file/constants';
 import { getNanoid } from '@fastgpt/global/common/string/tools';
 
-type FileType = {
+export type FileType = {
   fieldname: string;
   originalname: string;
   encoding: string;
@@ -41,7 +41,7 @@ export const getUploadModel = ({ maxSize = 500 }: { maxSize?: number }) => {
       })
     }).single('file');
 
-    async doUpload<T = Record<string, any>>(
+    async doUpload<T = any>(
       req: NextApiRequest,
       res: NextApiResponse,
       originBucketName?: `${BucketNameEnum}`

packages/service/common/file/read/utils.ts

@@ -66,6 +66,7 @@ export const readRawContentByFileBuffer = async ({
       return;
 
     const start = Date.now();
+    addLog.info('Parsing files from an external service');
 
     const data = new FormData();
     data.append('file', buffer, {
@@ -88,7 +89,7 @@ export const readRawContentByFileBuffer = async ({
       }
     });
 
-    addLog.info(`Use custom read file service, time: ${Date.now() - start}ms`);
+    addLog.info(`Custom file parsing is complete, time: ${Date.now() - start}ms`);
 
     const rawText = response.data.markdown;
     const { text, imageList } = matchMdImgTextAndUpload(rawText);

packages/service/common/response/index.ts

@@ -31,6 +31,8 @@ export const jsonRes = <T = any>(
       clearCookie(res);
     }
 
+    addLog.error(`Api response error: ${url}`, ERROR_RESPONSE[errResponseKey]);
+
     return res.json(ERROR_RESPONSE[errResponseKey]);
   }
 

packages/service/core/ai/config.ts

@@ -6,6 +6,7 @@ import {
 } from '@fastgpt/global/core/ai/type';
 import { getErrText } from '@fastgpt/global/common/error/utils';
 import { addLog } from '../../common/system/log';
+import { i18nT } from '../../../web/i18n/utils';
 
 export const openaiBaseUrl = process.env.OPENAI_BASE_URL || 'https://api.openai.com/v1';
 
@@ -62,6 +63,7 @@ export const createChatCompletion = async <T extends CompletionsBodyType>({
 }): Promise<{
   response: InferResponseType<T>;
   isStreamResponse: boolean;
+  getEmptyResponseTip: () => string;
 }> => {
   try {
     const formatTimeout = timeout ? timeout : body.stream ? 60000 : 600000;
@@ -76,9 +78,21 @@ export const createChatCompletion = async <T extends CompletionsBodyType>({
       response !== null &&
       ('iterator' in response || 'controller' in response);
 
+    const getEmptyResponseTip = () => {
+      addLog.warn(`LLM response empty`, {
+        baseUrl: userKey?.baseUrl,
+        requestBody: body
+      });
+      if (userKey?.baseUrl) {
+        return `您的 OpenAI key 没有响应: ${JSON.stringify(body)}`;
+      }
+      return i18nT('chat:LLM_model_response_empty');
+    };
+
     return {
       response: response as InferResponseType<T>,
-      isStreamResponse
+      isStreamResponse,
+      getEmptyResponseTip
     };
   } catch (error) {
     addLog.error(`LLM response error`, error);

packages/service/core/ai/functions/queryExtension.ts

@@ -5,6 +5,7 @@ import { countGptMessagesTokens } from '../../../common/string/tiktoken/index';
 import { chatValue2RuntimePrompt } from '@fastgpt/global/core/chat/adapt';
 import { getLLMModel } from '../model';
 import { llmCompletionsBodyFormat } from '../utils';
+import { addLog } from '../../../common/system/log';
 
 /* 
     query extension - 问题扩展
@@ -183,7 +184,7 @@ A: ${chatBg}
       tokens: await countGptMessagesTokens(messages)
     };
   } catch (error) {
-    console.log(error);
+    addLog.error(`Query extension error`, error);
     return {
       rawQuery: query,
       extensionQueries: [],

packages/service/core/ai/rerank/index.ts

@@ -51,7 +51,6 @@ export function reRankRecall({
       }));
     })
     .catch((err) => {
-      console.log(err);
       addLog.error('rerank error', err);
 
       return [];

packages/service/core/app/controller.ts

@@ -5,39 +5,44 @@ import { getLLMModel } from '../ai/model';
 import { MongoApp } from './schema';
 
 export const beforeUpdateAppFormat = <T extends AppSchema['modules'] | undefined>({
-  nodes
+  nodes,
+  isPlugin
 }: {
   nodes: T;
+  isPlugin: boolean;
 }) => {
   if (nodes) {
-    let maxTokens = 3000;
+    // Check dataset maxTokens
+    if (isPlugin) {
+      let maxTokens = 16000;
 
-    nodes.forEach((item) => {
-      if (
-        item.flowNodeType === FlowNodeTypeEnum.chatNode ||
-        item.flowNodeType === FlowNodeTypeEnum.tools
-      ) {
-        const model =
-          item.inputs.find((item) => item.key === NodeInputKeyEnum.aiModel)?.value || '';
-        const chatModel = getLLMModel(model);
-        const quoteMaxToken = chatModel.quoteMaxToken || 3000;
+      nodes.forEach((item) => {
+        if (
+          item.flowNodeType === FlowNodeTypeEnum.chatNode ||
+          item.flowNodeType === FlowNodeTypeEnum.tools
+        ) {
+          const model =
+            item.inputs.find((item) => item.key === NodeInputKeyEnum.aiModel)?.value || '';
+          const chatModel = getLLMModel(model);
+          const quoteMaxToken = chatModel.quoteMaxToken || 16000;
 
-        maxTokens = Math.max(maxTokens, quoteMaxToken);
-      }
-    });
+          maxTokens = Math.max(maxTokens, quoteMaxToken);
+        }
+      });
 
-    nodes.forEach((item) => {
-      if (item.flowNodeType === FlowNodeTypeEnum.datasetSearchNode) {
-        item.inputs.forEach((input) => {
-          if (input.key === NodeInputKeyEnum.datasetMaxTokens) {
-            const val = input.value as number;
-            if (val > maxTokens) {
-              input.value = maxTokens;
+      nodes.forEach((item) => {
+        if (item.flowNodeType === FlowNodeTypeEnum.datasetSearchNode) {
+          item.inputs.forEach((input) => {
+            if (input.key === NodeInputKeyEnum.datasetMaxTokens) {
+              const val = input.value as number;
+              if (val > maxTokens) {
+                input.value = maxTokens;
+              }
             }
-          }
-        });
-      }
-    });
+          });
+        }
+      });
+    }
   }
 
   return {

packages/service/core/app/plugin/controller.ts

@@ -2,7 +2,6 @@ import { FlowNodeTemplateType } from '@fastgpt/global/core/workflow/type/node.d'
 import { FlowNodeTypeEnum, defaultNodeVersion } from '@fastgpt/global/core/workflow/node/constant';
 import { appData2FlowNodeIO, pluginData2FlowNodeIO } from '@fastgpt/global/core/workflow/utils';
 import { PluginSourceEnum } from '@fastgpt/global/core/plugin/constants';
-import type { PluginRuntimeType } from '@fastgpt/global/core/workflow/runtime/type';
 import { FlowNodeTemplateTypeEnum } from '@fastgpt/global/core/workflow/constants';
 import { getHandleConfig } from '@fastgpt/global/core/workflow/template/utils';
 import { getNanoid } from '@fastgpt/global/common/string/tools';
@@ -11,6 +10,9 @@ import { MongoApp } from '../schema';
 import { SystemPluginTemplateItemType } from '@fastgpt/global/core/workflow/type';
 import { getSystemPluginTemplates } from '../../../../plugins/register';
 import { getAppLatestVersion, getAppVersionById } from '../version/controller';
+import { PluginRuntimeType } from '@fastgpt/global/core/plugin/type';
+import { MongoSystemPlugin } from './systemPluginSchema';
+import { PluginErrEnum } from '@fastgpt/global/common/error/code/plugin';
 
 /* 
   plugin id rule:
@@ -37,15 +39,45 @@ export async function splitCombinePluginId(id: string) {
 
 type ChildAppType = SystemPluginTemplateItemType & { teamId?: string };
 const getSystemPluginTemplateById = async (
-  pluginId: string
+  pluginId: string,
+  versionId?: string
 ): Promise<SystemPluginTemplateItemType> => {
   const item = getSystemPluginTemplates().find((plugin) => plugin.id === pluginId);
-  if (!item) return Promise.reject('plugin not found');
+  if (!item) return Promise.reject(PluginErrEnum.unAuth);
 
-  return cloneDeep(item);
+  const plugin = cloneDeep(item);
+
+  if (plugin.associatedPluginId) {
+    // The verification plugin is set as a system plugin
+    const systemPlugin = await MongoSystemPlugin.findOne(
+      { pluginId: plugin.id, 'customConfig.associatedPluginId': plugin.associatedPluginId },
+      'associatedPluginId'
+    ).lean();
+    if (!systemPlugin) return Promise.reject(PluginErrEnum.unAuth);
+
+    const app = await MongoApp.findById(plugin.associatedPluginId).lean();
+    if (!app) return Promise.reject(PluginErrEnum.unAuth);
+
+    const version = versionId
+      ? await getAppVersionById({
+          appId: plugin.associatedPluginId,
+          versionId,
+          app
+        })
+      : await getAppLatestVersion(plugin.associatedPluginId, app);
+    if (!version.versionId) return Promise.reject('App version not found');
+
+    plugin.workflow = {
+      nodes: version.nodes,
+      edges: version.edges,
+      chatConfig: version.chatConfig
+    };
+    plugin.version = versionId || String(version.versionId);
+  }
+  return plugin;
 };
 
-/* format plugin modules to plugin preview module */
+/* Format plugin to workflow preview node data */
 export async function getChildAppPreviewNode({
   id
 }: {
@@ -77,7 +109,9 @@ export async function getChildAppPreviewNode({
         templateType: FlowNodeTemplateTypeEnum.teamApp,
         version: version.versionId,
         originCost: 0,
-        currentCost: 0
+        currentCost: 0,
+        hasTokenFee: false,
+        pluginOrder: 0
       };
     } else {
       return getSystemPluginTemplateById(pluginId);
@@ -147,10 +181,12 @@ export async function getChildAppRuntimeById(
         // 用不到
         version: item?.pluginData?.nodeVersion || defaultNodeVersion,
         originCost: 0,
-        currentCost: 0
+        currentCost: 0,
+        hasTokenFee: false,
+        pluginOrder: 0
       };
     } else {
-      return getSystemPluginTemplateById(pluginId);
+      return getSystemPluginTemplateById(pluginId, versionId);
     }
   })();
 
@@ -162,6 +198,7 @@ export async function getChildAppRuntimeById(
     showStatus: app.showStatus,
     currentCost: app.currentCost,
     nodes: app.workflow.nodes,
-    edges: app.workflow.edges
+    edges: app.workflow.edges,
+    hasTokenFee: app.hasTokenFee
   };
 }

packages/service/core/app/plugin/pluginGroupSchema.ts

@@ -0,0 +1,35 @@
+import { connectionMongo, getMongoModel } from '../../../common/mongo/index';
+import { PluginGroupSchemaType, TGroupType } from './type';
+const { Schema } = connectionMongo;
+
+export const collectionName = 'app_plugin_groups';
+
+const PluginGroupSchema = new Schema({
+  groupId: {
+    type: String,
+    required: true
+  },
+  groupAvatar: {
+    type: String,
+    default: ''
+  },
+  groupName: {
+    type: String,
+    required: true
+  },
+  groupTypes: {
+    type: Array<TGroupType>,
+    default: []
+  },
+  groupOrder: {
+    type: Number,
+    default: 0
+  }
+});
+
+PluginGroupSchema.index({ groupId: 1 }, { unique: true });
+
+export const MongoPluginGroups = getMongoModel<PluginGroupSchemaType>(
+  collectionName,
+  PluginGroupSchema
+);

packages/service/core/app/plugin/systemPluginSchema.ts

@@ -25,12 +25,20 @@ const SystemPluginSchema = new Schema({
     type: Number,
     default: 0
   },
+  hasTokenFee: {
+    type: Boolean,
+    default: false
+  },
+  pluginOrder: {
+    type: Number,
+    default: 0
+  },
   customConfig: Object
 });
 
 SystemPluginSchema.index({ pluginId: 1 });
 
-export const MongoSystemPluginSchema = getMongoModel<SystemPluginConfigSchemaType>(
+export const MongoSystemPlugin = getMongoModel<SystemPluginConfigSchemaType>(
   collectionName,
   SystemPluginSchema
 );

packages/service/core/app/plugin/type.d.ts

@@ -1,3 +1,4 @@
+import { SystemPluginListItemType } from '@fastgpt/global/core/app/type';
 import { FlowNodeTemplateTypeEnum } from '@fastgpt/global/core/workflow/constants';
 import {
   SystemPluginTemplateItemType,
@@ -9,7 +10,9 @@ export type SystemPluginConfigSchemaType = {
 
   originCost: number; // n points/one time
   currentCost: number;
+  hasTokenFee: boolean;
   isActive: boolean;
+  pluginOrder: number;
   inputConfig: SystemPluginTemplateItemType['inputConfig'];
 
   customConfig?: {
@@ -19,6 +22,21 @@ export type SystemPluginConfigSchemaType = {
     version: string;
     weight?: number;
     workflow: WorkflowTemplateBasicType;
-    templateType: FlowNodeTemplateTypeEnum;
+    templateType: string;
+    associatedPluginId: string;
+    userGuide: string;
   };
 };
+
+export type TGroupType = {
+  typeName: string;
+  typeId: string;
+};
+
+export type PluginGroupSchemaType = {
+  groupId: string;
+  groupAvatar: string;
+  groupName: string;
+  groupTypes: TGroupType[];
+  groupOrder: number;
+};

packages/service/core/app/plugin/utils.ts

@@ -1,11 +1,11 @@
-import { PluginRuntimeType } from '@fastgpt/global/core/workflow/runtime/type';
 import { ChatNodeUsageType } from '@fastgpt/global/support/wallet/bill/type';
-import { splitCombinePluginId } from './controller';
-import { PluginSourceEnum } from '@fastgpt/global/core/plugin/constants';
+import { PluginRuntimeType } from '@fastgpt/global/core/plugin/type';
 
 /* 
-  1. Commercial plugin: n points per times
-  2. Other plugin: sum of children points
+  Plugin points calculation:
+  1. Return 0 if error
+  2. Add configured points if commercial plugin
+  3. Add sum of child nodes points
 */
 export const computedPluginUsage = async ({
   plugin,
@@ -16,13 +16,13 @@ export const computedPluginUsage = async ({
   childrenUsage: ChatNodeUsageType[];
   error?: boolean;
 }) => {
-  const { source } = await splitCombinePluginId(plugin.id);
-
-  // Commercial plugin: n points per times
-  if (source === PluginSourceEnum.commercial) {
-    if (error) return 0;
-    return plugin.currentCost ?? 0;
+  if (error) {
+    return 0;
   }
 
-  return childrenUsage.reduce((sum, item) => sum + (item.totalPoints || 0), 0);
+  const childrenIUsages = childrenUsage.reduce((sum, item) => sum + (item.totalPoints || 0), 0);
+
+  const pluginCurrentCose = plugin.currentCost ?? 0;
+
+  return plugin.hasTokenFee ? pluginCurrentCose + childrenIUsages : pluginCurrentCose;
 };

packages/service/core/app/schema.ts

@@ -17,7 +17,8 @@ export const chatConfigType = {
   scheduledTriggerConfig: Object,
   chatInputGuide: Object,
   fileSelectConfig: Object,
-  instruction: String
+  instruction: String,
+  autoExecute: Object
 };
 
 // schema

packages/service/core/chat/chatItemSchema.ts

@@ -46,6 +46,10 @@ const ChatItemSchema = new Schema({
     type: Date,
     default: () => new Date()
   },
+  hideInUI: {
+    type: Boolean,
+    default: false
+  },
   obj: {
     // chat role
     type: String,

packages/service/core/chat/saveChat.ts

@@ -1,15 +1,6 @@
-import type {
-  AIChatItemType,
-  ChatItemType,
-  UserChatItemType
-} from '@fastgpt/global/core/chat/type.d';
-import axios from 'axios';
+import type { AIChatItemType, UserChatItemType } from '@fastgpt/global/core/chat/type.d';
 import { MongoApp } from '../app/schema';
-import {
-  ChatItemValueTypeEnum,
-  ChatRoleEnum,
-  ChatSourceEnum
-} from '@fastgpt/global/core/chat/constants';
+import { ChatItemValueTypeEnum, ChatRoleEnum } from '@fastgpt/global/core/chat/constants';
 import { MongoChatItem } from './chatItemSchema';
 import { MongoChat } from './chatSchema';
 import { addLog } from '../../common/system/log';
@@ -133,21 +124,15 @@ export async function saveChat({
 export const updateInteractiveChat = async ({
   chatId,
   appId,
-  teamId,
-  tmbId,
   userInteractiveVal,
   aiResponse,
-  newVariables,
-  newTitle
+  newVariables
 }: {
   chatId: string;
   appId: string;
-  teamId: string;
-  tmbId: string;
   userInteractiveVal: string;
   aiResponse: AIChatItemType & { dataId?: string };
   newVariables?: Record<string, any>;
-  newTitle: string;
 }) => {
   if (!chatId) return;
 
@@ -232,7 +217,6 @@ export const updateInteractiveChat = async ({
       {
         $set: {
           variables: newVariables,
-          title: newTitle,
           updateTime: new Date()
         }
       },

packages/service/core/chat/utils.ts

@@ -118,6 +118,11 @@ export const loadRequestMessages = async ({
             return item.image_url.url;
           })();
 
+          // base64 image
+          if (imgUrl.startsWith('data:image/')) {
+            return item;
+          }
+
           try {
             // If imgUrl is a local path, load image from local, and set url to base64
             if (imgUrl.startsWith('/')) {

packages/service/core/dataset/apiDataset/api.ts

@@ -0,0 +1,143 @@
+import type {
+  APIFileContentResponse,
+  APIFileListResponse,
+  APIFileReadResponse,
+  APIFileServer
+} from '@fastgpt/global/core/dataset/apiDataset';
+import axios, { Method } from 'axios';
+import { addLog } from '../../../common/system/log';
+import { readFileRawTextByUrl } from '../read';
+import { ParentIdType } from '@fastgpt/global/common/parentFolder/type';
+
+type ResponseDataType = {
+  success: boolean;
+  message: string;
+  data: any;
+};
+
+export const useApiDatasetRequest = ({ apiServer }: { apiServer: APIFileServer }) => {
+  const instance = axios.create({
+    baseURL: apiServer.baseUrl,
+    timeout: 60000, // 超时时间
+    headers: {
+      'content-type': 'application/json',
+      Authorization: `Bearer ${apiServer.authorization}`
+    }
+  });
+
+  /**
+   * 响应数据检查
+   */
+  const checkRes = (data: ResponseDataType) => {
+    if (data === undefined) {
+      addLog.info('Api dataset data is empty');
+      return Promise.reject('服务器异常');
+    } else if (!data.success) {
+      return Promise.reject(data);
+    }
+    return data.data;
+  };
+  const responseError = (err: any) => {
+    console.log('error->', '请求错误', err);
+
+    if (!err) {
+      return Promise.reject({ message: '未知错误' });
+    }
+    if (typeof err === 'string') {
+      return Promise.reject({ message: err });
+    }
+    if (typeof err.message === 'string') {
+      return Promise.reject({ message: err.message });
+    }
+    if (typeof err.data === 'string') {
+      return Promise.reject({ message: err.data });
+    }
+    if (err?.response?.data) {
+      return Promise.reject(err?.response?.data);
+    }
+    return Promise.reject(err);
+  };
+
+  const request = <T>(url: string, data: any, method: Method): Promise<T> => {
+    /* 去空 */
+    for (const key in data) {
+      if (data[key] === undefined) {
+        delete data[key];
+      }
+    }
+
+    return instance
+      .request({
+        url,
+        method,
+        data: ['POST', 'PUT'].includes(method) ? data : undefined,
+        params: !['POST', 'PUT'].includes(method) ? data : undefined
+      })
+      .then((res) => checkRes(res.data))
+      .catch((err) => responseError(err));
+  };
+
+  const listFiles = async ({
+    searchKey,
+    parentId
+  }: {
+    searchKey?: string;
+    parentId?: ParentIdType;
+  }) => {
+    const files = await request<APIFileListResponse>(
+      `/v1/file/list`,
+      {
+        searchKey,
+        parentId
+      },
+      'POST'
+    );
+
+    if (!Array.isArray(files)) {
+      return Promise.reject('Invalid file list format');
+    }
+    if (files.some((file) => !file.id || !file.name || typeof file.type === 'undefined')) {
+      return Promise.reject('Invalid file data format');
+    }
+    return files;
+  };
+
+  const getFileContent = async ({ teamId, apiFileId }: { teamId: string; apiFileId: string }) => {
+    const data = await request<APIFileContentResponse>(
+      `/v1/file/content`,
+      { id: apiFileId },
+      'GET'
+    );
+    const content = data.content;
+    const previewUrl = data.previewUrl;
+
+    if (content) {
+      return content;
+    }
+    if (previewUrl) {
+      const rawText = await readFileRawTextByUrl({
+        teamId,
+        url: previewUrl,
+        relatedId: apiFileId
+      });
+      return rawText;
+    }
+    return Promise.reject('Invalid content type: content or previewUrl is required');
+  };
+
+  const getFilePreviewUrl = async ({ apiFileId }: { apiFileId: string }) => {
+    const { url } = await request<APIFileReadResponse>(`/v1/file/read`, { id: apiFileId }, 'GET');
+
+    if (!url || typeof url !== 'string') {
+      return Promise.reject('Invalid response url');
+    }
+
+    return url;
+  };
+
+  return {
+    getFileContent,
+    listFiles,
+    getFilePreviewUrl
+  };
+};

packages/service/core/dataset/collection/controller.ts

@@ -3,7 +3,8 @@ import type { CreateDatasetCollectionParams } from '@fastgpt/global/core/dataset
 import { MongoDatasetCollection } from './schema';
 import {
   CollectionWithDatasetType,
-  DatasetCollectionSchemaType
+  DatasetCollectionSchemaType,
+  DatasetSchemaType
 } from '@fastgpt/global/core/dataset/type';
 import { MongoDatasetTraining } from '../training/schema';
 import { MongoDatasetData } from '../data/schema';
@@ -13,7 +14,132 @@ import { delFileByFileIdList } from '../../../common/file/gridfs/controller';
 import { BucketNameEnum } from '@fastgpt/global/common/file/constants';
 import { ClientSession } from '../../../common/mongo';
 import { createOrGetCollectionTags } from './utils';
+import { rawText2Chunks } from '../read';
+import { checkDatasetLimit } from '../../../support/permission/teamLimit';
+import { predictDataLimitLength } from '../../../../global/core/dataset/utils';
+import { mongoSessionRun } from '../../../common/mongo/sessionRun';
+import { createTrainingUsage } from '../../../support/wallet/usage/controller';
+import { UsageSourceEnum } from '@fastgpt/global/support/wallet/usage/constants';
+import { getLLMModel, getVectorModel } from '../../ai/model';
+import { pushDataListToTrainingQueue } from '../training/controller';
+import { MongoImage } from '../../../common/file/image/schema';
+import { hashStr } from '@fastgpt/global/common/string/tools';
 
+export const createCollectionAndInsertData = async ({
+  dataset,
+  rawText,
+  relatedId,
+  createCollectionParams,
+  isQAImport = false,
+  session
+}: {
+  dataset: DatasetSchemaType;
+  rawText: string;
+  relatedId?: string;
+  createCollectionParams: CreateOneCollectionParams;
+
+  isQAImport?: boolean;
+  session?: ClientSession;
+}) => {
+  const teamId = createCollectionParams.teamId;
+  const tmbId = createCollectionParams.tmbId;
+  // Chunk split params
+  const trainingType = createCollectionParams.trainingType || TrainingModeEnum.chunk;
+  const chunkSize = createCollectionParams.chunkSize;
+  const chunkSplitter = createCollectionParams.chunkSplitter;
+  const qaPrompt = createCollectionParams.qaPrompt;
+  const usageName = createCollectionParams.name;
+
+  // 1. split chunks
+  const chunks = rawText2Chunks({
+    rawText,
+    chunkLen: chunkSize,
+    overlapRatio: trainingType === TrainingModeEnum.chunk ? 0.2 : 0,
+    customReg: chunkSplitter ? [chunkSplitter] : [],
+    isQAImport
+  });
+
+  // 2. auth limit
+  await checkDatasetLimit({
+    teamId,
+    insertLen: predictDataLimitLength(trainingType, chunks)
+  });
+
+  const fn = async (session: ClientSession) => {
+    // 3. create collection
+    const { _id: collectionId } = await createOneCollection({
+      ...createCollectionParams,
+
+      hashRawText: hashStr(rawText),
+      rawTextLength: rawText.length,
+      session
+    });
+
+    // 4. create training bill
+    const { billId } = await createTrainingUsage({
+      teamId,
+      tmbId,
+      appName: usageName,
+      billSource: UsageSourceEnum.training,
+      vectorModel: getVectorModel(dataset.vectorModel)?.name,
+      agentModel: getLLMModel(dataset.agentModel)?.name,
+      session
+    });
+
+    // 5. insert to training queue
+    const insertResults = await pushDataListToTrainingQueue({
+      teamId,
+      tmbId,
+      datasetId: dataset._id,
+      collectionId,
+      agentModel: dataset.agentModel,
+      vectorModel: dataset.vectorModel,
+      trainingMode: trainingType,
+      prompt: qaPrompt,
+      billId,
+      data: chunks.map((item, index) => ({
+        ...item,
+        chunkIndex: index
+      })),
+      session
+    });
+
+    // 6. remove related image ttl
+    if (relatedId) {
+      await MongoImage.updateMany(
+        {
+          teamId,
+          'metadata.relatedId': relatedId
+        },
+        {
+          // Remove expiredTime to avoid ttl expiration
+          $unset: {
+            expiredTime: 1
+          }
+        },
+        {
+          session
+        }
+      );
+    }
+
+    return {
+      collectionId,
+      insertResults
+    };
+  };
+
+  if (session) {
+    return fn(session);
+  }
+  return mongoSessionRun(fn);
+};
+
+export type CreateOneCollectionParams = CreateDatasetCollectionParams & {
+  teamId: string;
+  tmbId: string;
+  session?: ClientSession;
+};
 export async function createOneCollection({
   teamId,
   tmbId,
@@ -33,18 +159,15 @@ export async function createOneCollection({
   externalFileId,
   externalFileUrl,
 
+  apiFileId,
+
   hashRawText,
   rawTextLength,
   metadata = {},
   session,
   tags,
-  ...props
-}: CreateDatasetCollectionParams & {
-  teamId: string;
-  tmbId: string;
-  [key: string]: any;
-  session?: ClientSession;
-}) {
+  createTime
+}: CreateOneCollectionParams) {
   // Create collection tags
   const collectionTags = await createOrGetCollectionTags({ tags, teamId, datasetId, session });
 
@@ -52,7 +175,6 @@ export async function createOneCollection({
   const [collection] = await MongoDatasetCollection.create(
     [
       {
-        ...props,
         teamId,
         tmbId,
         parentId: parentId || null,
@@ -64,16 +186,18 @@ export async function createOneCollection({
         chunkSize,
         chunkSplitter,
         qaPrompt,
+        metadata,
 
-        fileId,
-        rawLink,
-        externalFileId,
-        externalFileUrl,
+        ...(fileId ? { fileId } : {}),
+        ...(rawLink ? { rawLink } : {}),
+        ...(externalFileId ? { externalFileId } : {}),
+        ...(externalFileUrl ? { externalFileUrl } : {}),
+        ...(apiFileId ? { apiFileId } : {}),
 
         rawTextLength,
         hashRawText,
-        metadata,
-        tags: collectionTags
+        tags: collectionTags,
+        createTime
       }
     ],
     { session }
@@ -116,7 +240,68 @@ export const delCollectionRelatedSource = async ({
 /**
  * delete collection and it related data
  */
-export async function delCollectionAndRelatedSources({
+export async function delCollection({
+  collections,
+  session,
+  delRelatedSource
+}: {
+  collections: (CollectionWithDatasetType | DatasetCollectionSchemaType)[];
+  session: ClientSession;
+  delRelatedSource: boolean;
+}) {
+  if (collections.length === 0) return;
+
+  const teamId = collections[0].teamId;
+
+  if (!teamId) return Promise.reject('teamId is not exist');
+
+  const datasetIds = Array.from(
+    new Set(
+      collections.map((item) => {
+        if (typeof item.datasetId === 'string') {
+          return String(item.datasetId);
+        }
+        return String(item.datasetId._id);
+      })
+    )
+  );
+  const collectionIds = collections.map((item) => String(item._id));
+
+  // delete training data
+  await MongoDatasetTraining.deleteMany({
+    teamId,
+    datasetIds: { $in: datasetIds },
+    collectionId: { $in: collectionIds }
+  });
+
+  /* file and imgs */
+  if (delRelatedSource) {
+    await delCollectionRelatedSource({ collections, session });
+  }
+
+  // delete dataset.datas
+  await MongoDatasetData.deleteMany(
+    { teamId, datasetIds: { $in: datasetIds }, collectionId: { $in: collectionIds } },
+    { session }
+  );
+
+  // delete collections
+  await MongoDatasetCollection.deleteMany(
+    {
+      teamId,
+      _id: { $in: collectionIds }
+    },
+    { session }
+  );
+
+  // no session delete: delete files, vector data
+  await deleteDatasetDataVector({ teamId, datasetIds, collectionIds });
+}
+
+/**
+ * delete delOnlyCollection
+ */
+export async function delOnlyCollection({
   collections,
   session
 }: {
@@ -148,9 +333,6 @@ export async function delCollectionAndRelatedSources({
     collectionId: { $in: collectionIds }
   });
 
-  /* file and imgs */
-  await delCollectionRelatedSource({ collections, session });
-
   // delete dataset.datas
   await MongoDatasetData.deleteMany(
     { teamId, datasetIds: { $in: datasetIds }, collectionId: { $in: collectionIds } },

packages/service/core/dataset/collection/schema.ts

@@ -10,90 +10,100 @@ import {
 
 export const DatasetColCollectionName = 'dataset_collections';
 
-const DatasetCollectionSchema = new Schema({
-  parentId: {
-    type: Schema.Types.ObjectId,
-    ref: DatasetColCollectionName,
-    default: null
-  },
-  teamId: {
-    type: Schema.Types.ObjectId,
-    ref: TeamCollectionName,
-    required: true
-  },
-  tmbId: {
-    type: Schema.Types.ObjectId,
-    ref: TeamMemberCollectionName,
-    required: true
-  },
-  datasetId: {
-    type: Schema.Types.ObjectId,
-    ref: DatasetCollectionName,
-    required: true
-  },
-  type: {
-    type: String,
-    enum: Object.keys(DatasetCollectionTypeMap),
-    required: true
-  },
-  name: {
-    type: String,
-    required: true
-  },
-  createTime: {
-    type: Date,
-    default: () => new Date()
-  },
-  updateTime: {
-    type: Date,
-    default: () => new Date()
-  },
-  forbid: {
-    type: Boolean,
-    default: false
-  },
+const DatasetCollectionSchema = new Schema(
+  {
+    parentId: {
+      type: Schema.Types.ObjectId,
+      ref: DatasetColCollectionName,
+      default: null
+    },
+    teamId: {
+      type: Schema.Types.ObjectId,
+      ref: TeamCollectionName,
+      required: true
+    },
+    tmbId: {
+      type: Schema.Types.ObjectId,
+      ref: TeamMemberCollectionName,
+      required: true
+    },
+    datasetId: {
+      type: Schema.Types.ObjectId,
+      ref: DatasetCollectionName,
+      required: true
+    },
+    type: {
+      type: String,
+      enum: Object.keys(DatasetCollectionTypeMap),
+      required: true
+    },
+    name: {
+      type: String,
+      required: true
+    },
+    createTime: {
+      type: Date,
+      default: () => new Date()
+    },
+    updateTime: {
+      type: Date,
+      default: () => new Date()
+    },
+    forbid: {
+      type: Boolean,
+      default: false
+    },
 
-  // chunk filed
-  trainingType: {
-    type: String,
-    enum: Object.keys(TrainingTypeMap)
-  },
-  chunkSize: {
-    type: Number,
-    required: true
-  },
-  chunkSplitter: {
-    type: String
-  },
-  qaPrompt: {
-    type: String
-  },
-  ocrParse: Boolean,
+    // chunk filed
+    trainingType: {
+      type: String,
+      enum: Object.keys(TrainingTypeMap)
+    },
+    chunkSize: {
+      type: Number,
+      required: true
+    },
+    chunkSplitter: {
+      type: String
+    },
+    qaPrompt: {
+      type: String
+    },
+    ocrParse: Boolean,
 
-  tags: {
-    type: [String],
-    default: []
-  },
+    tags: {
+      type: [String],
+      default: []
+    },
 
-  // local file collection
-  fileId: {
-    type: Schema.Types.ObjectId,
-    ref: 'dataset.files'
-  },
-  // web link collection
-  rawLink: String,
-  // external collection
-  externalFileId: String,
+    // local file collection
+    fileId: {
+      type: Schema.Types.ObjectId,
+      ref: 'dataset.files'
+    },
+    // web link collection
+    rawLink: String,
+    // api collection
+    apiFileId: String,
+    // external collection
+    externalFileId: String,
+    externalFileUrl: String, // external import url
 
-  // metadata
-  rawTextLength: Number,
-  hashRawText: String,
-  externalFileUrl: String, // external import url
-  metadata: {
-    type: Object,
-    default: {}
+    // metadata
+    rawTextLength: Number,
+    hashRawText: String,
+    metadata: {
+      type: Object,
+      default: {}
+    }
+  },
+  {
+    // Auto update updateTime
+    timestamps: {
+      updatedAt: 'updateTime'
+    }
   }
-});
+);
 
 try {
   // auth file

packages/service/core/dataset/collection/utils.ts

@@ -1,17 +1,19 @@
-import type { CollectionWithDatasetType } from '@fastgpt/global/core/dataset/type.d';
 import { MongoDatasetCollection } from './schema';
-import { splitText2Chunks } from '@fastgpt/global/common/string/textSplitter';
-import { MongoDatasetTraining } from '../training/schema';
-import { urlsFetch } from '../../../common/string/cheerio';
-import {
-  DatasetCollectionTypeEnum,
-  TrainingModeEnum
-} from '@fastgpt/global/core/dataset/constants';
-import { hashStr } from '@fastgpt/global/common/string/tools';
 import { ClientSession } from '../../../common/mongo';
-import { PushDatasetDataResponse } from '@fastgpt/global/core/dataset/api';
 import { MongoDatasetCollectionTags } from '../tag/schema';
 import { readFromSecondary } from '../../../common/mongo/utils';
+import { CollectionWithDatasetType } from '@fastgpt/global/core/dataset/type';
+import {
+  DatasetCollectionSyncResultEnum,
+  DatasetCollectionTypeEnum,
+  DatasetSourceReadTypeEnum,
+  DatasetTypeEnum
+} from '@fastgpt/global/core/dataset/constants';
+import { DatasetErrEnum } from '@fastgpt/global/common/error/code/dataset';
+import { readDatasetSourceRawText } from '../read';
+import { hashStr } from '@fastgpt/global/common/string/tools';
+import { mongoSessionRun } from '../../../common/mongo/sessionRun';
+import { createCollectionAndInsertData, delCollection } from './controller';
 
 /**
  * get all collection by top collectionId
@@ -61,148 +63,6 @@ export function getCollectionUpdateTime({ name, time }: { time?: Date; name: str
   return new Date();
 }
 
-/**
- * Get collection raw text by Collection or collectionId
- */
-export const getCollectionAndRawText = async ({
-  collectionId,
-  collection,
-  newRawText
-}: {
-  collectionId?: string;
-  collection?: CollectionWithDatasetType;
-  newRawText?: string;
-}) => {
-  const col = await (async () => {
-    if (collection) return collection;
-    if (collectionId) {
-      return (await MongoDatasetCollection.findById(collectionId).populate(
-        'datasetId'
-      )) as CollectionWithDatasetType;
-    }
-
-    return null;
-  })();
-
-  if (!col) {
-    return Promise.reject('Collection not found');
-  }
-
-  const { title, rawText } = await (async () => {
-    if (newRawText)
-      return {
-        title: '',
-        rawText: newRawText
-      };
-    // link
-    if (col.type === DatasetCollectionTypeEnum.link && col.rawLink) {
-      // crawl new data
-      const result = await urlsFetch({
-        urlList: [col.rawLink],
-        selector: col.datasetId?.websiteConfig?.selector || col?.metadata?.webPageSelector
-      });
-
-      return {
-        title: result[0]?.title,
-        rawText: result[0]?.content
-      };
-    }
-
-    // file
-
-    return {
-      title: '',
-      rawText: ''
-    };
-  })();
-
-  const hashRawText = hashStr(rawText);
-  const isSameRawText = rawText && col.hashRawText === hashRawText;
-
-  return {
-    collection: col,
-    title,
-    rawText,
-    isSameRawText
-  };
-};
-
-/* link collection start load data */
-export const reloadCollectionChunks = async ({
-  collection,
-  tmbId,
-  billId,
-  rawText,
-  session
-}: {
-  collection: CollectionWithDatasetType;
-  tmbId: string;
-  billId?: string;
-  rawText?: string;
-  session: ClientSession;
-}): Promise<PushDatasetDataResponse> => {
-  const {
-    title,
-    rawText: newRawText,
-    collection: col,
-    isSameRawText
-  } = await getCollectionAndRawText({
-    collection,
-    newRawText: rawText
-  });
-
-  if (isSameRawText)
-    return {
-      insertLen: 0
-    };
-
-  // split data
-  const { chunks } = splitText2Chunks({
-    text: newRawText,
-    chunkLen: col.chunkSize || 512,
-    customReg: col.chunkSplitter ? [col.chunkSplitter] : []
-  });
-
-  // insert to training queue
-  const model = await (() => {
-    if (col.trainingType === TrainingModeEnum.chunk) return col.datasetId.vectorModel;
-    if (col.trainingType === TrainingModeEnum.qa) return col.datasetId.agentModel;
-    return Promise.reject('Training model error');
-  })();
-
-  const result = await MongoDatasetTraining.insertMany(
-    chunks.map((item, i) => ({
-      teamId: col.teamId,
-      tmbId,
-      datasetId: col.datasetId._id,
-      collectionId: col._id,
-      billId,
-      mode: col.trainingType,
-      prompt: '',
-      model,
-      q: item,
-      a: '',
-      chunkIndex: i
-    })),
-    { session }
-  );
-
-  // update raw text
-  await MongoDatasetCollection.findByIdAndUpdate(
-    col._id,
-    {
-      ...(title && { name: title }),
-      rawTextLength: newRawText.length,
-      hashRawText: hashStr(newRawText)
-    },
-    { session }
-  );
-
-  return {
-    insertLen: result.length
-  };
-};
-
 export const createOrGetCollectionTags = async ({
   tags,
   datasetId,
@@ -268,3 +128,88 @@ export const collectionTagsToTagLabel = async ({
     })
     .filter(Boolean);
 };
+
+export const syncCollection = async (collection: CollectionWithDatasetType) => {
+  const dataset = collection.datasetId;
+
+  if (
+    collection.type !== DatasetCollectionTypeEnum.link &&
+    dataset.type !== DatasetTypeEnum.apiDataset
+  ) {
+    return Promise.reject(DatasetErrEnum.notSupportSync);
+  }
+
+  // Get new text
+  const sourceReadType = await (async () => {
+    if (collection.type === DatasetCollectionTypeEnum.link) {
+      if (!collection.rawLink) return Promise.reject('rawLink is missing');
+      return {
+        type: DatasetSourceReadTypeEnum.link,
+        sourceId: collection.rawLink,
+        selector: collection.metadata?.webPageSelector
+      };
+    }
+
+    if (!collection.apiFileId) return Promise.reject('apiFileId is missing');
+    if (!dataset.apiServer) return Promise.reject('apiServer not found');
+    return {
+      type: DatasetSourceReadTypeEnum.apiFile,
+      sourceId: collection.apiFileId,
+      apiServer: dataset.apiServer
+    };
+  })();
+  const rawText = await readDatasetSourceRawText({
+    teamId: collection.teamId,
+    ...sourceReadType
+  });
+
+  // Check if the original text is the same: skip if same
+  const hashRawText = hashStr(rawText);
+  if (collection.hashRawText && hashRawText === collection.hashRawText) {
+    return DatasetCollectionSyncResultEnum.sameRaw;
+  }
+
+  await mongoSessionRun(async (session) => {
+    // Create new collection
+    await createCollectionAndInsertData({
+      session,
+      dataset,
+      rawText: rawText,
+      createCollectionParams: {
+        teamId: collection.teamId,
+        tmbId: collection.tmbId,
+        datasetId: collection.datasetId._id,
+        name: collection.name,
+        type: collection.type,
+
+        fileId: collection.fileId,
+        rawLink: collection.rawLink,
+        externalFileId: collection.externalFileId,
+        externalFileUrl: collection.externalFileUrl,
+        apiFileId: collection.apiFileId,
+
+        rawTextLength: rawText.length,
+        hashRawText,
+
+        tags: collection.tags,
+        createTime: collection.createTime,
+
+        parentId: collection.parentId,
+        trainingType: collection.trainingType,
+        chunkSize: collection.chunkSize,
+        chunkSplitter: collection.chunkSplitter,
+        qaPrompt: collection.qaPrompt,
+        metadata: collection.metadata
+      }
+    });
+
+    // Delete old collection
+    await delCollection({
+      collections: [collection],
+      delRelatedSource: false,
+      session
+    });
+  });
+
+  return DatasetCollectionSyncResultEnum.success;
+};

packages/service/core/dataset/read.ts

@@ -7,6 +7,8 @@ import { TextSplitProps, splitText2Chunks } from '@fastgpt/global/common/string/
 import axios from 'axios';
 import { readRawContentByFileBuffer } from '../../common/file/read/utils';
 import { parseFileExtensionFromUrl } from '@fastgpt/global/common/string/tools';
+import { APIFileServer } from '@fastgpt/global/core/dataset/apiDataset';
+import { useApiDatasetRequest } from './apiDataset/api';
 
 export const readFileRawTextByUrl = async ({
   teamId,
@@ -15,7 +17,7 @@ export const readFileRawTextByUrl = async ({
 }: {
   teamId: string;
   url: string;
-  relatedId?: string;
+  relatedId: string; // externalFileId / apiFileId
 }) => {
   const response = await axios({
     method: 'get',
@@ -40,9 +42,9 @@ export const readFileRawTextByUrl = async ({
 };
 
 /* 
-    fileId - local file, read from mongo
-    link - request
-    externalFile = request read
+  fileId - local file, read from mongo
+  link - request
+  externalFile/apiFile = request read
 */
 export const readDatasetSourceRawText = async ({
   teamId,
@@ -50,14 +52,17 @@ export const readDatasetSourceRawText = async ({
   sourceId,
   isQAImport,
   selector,
-  relatedId
+  externalFileId,
+  apiServer
 }: {
   teamId: string;
   type: DatasetSourceReadTypeEnum;
   sourceId: string;
-  isQAImport?: boolean;
-  selector?: string;
-  relatedId?: string;
+
+  isQAImport?: boolean; // csv data
+  selector?: string; // link selector
+  externalFileId?: string; // external file dataset
+  apiServer?: APIFileServer; // api dataset
 }): Promise<string> => {
   if (type === DatasetSourceReadTypeEnum.fileLocal) {
     const { rawText } = await readFileContentFromMongo({
@@ -75,10 +80,19 @@ export const readDatasetSourceRawText = async ({
 
     return result[0]?.content || '';
   } else if (type === DatasetSourceReadTypeEnum.externalFile) {
+    if (!externalFileId) return Promise.reject('FileId not found');
     const rawText = await readFileRawTextByUrl({
       teamId,
       url: sourceId,
-      relatedId
+      relatedId: externalFileId
+    });
+    return rawText;
+  } else if (type === DatasetSourceReadTypeEnum.apiFile) {
+    if (!apiServer) return Promise.reject('apiServer not found');
+    const rawText = await readApiServerFileContent({
+      apiServer,
+      apiFileId: sourceId,
+      teamId
     });
     return rawText;
   }
@@ -86,6 +100,18 @@ export const readDatasetSourceRawText = async ({
   return '';
 };
 
+export const readApiServerFileContent = async ({
+  apiServer,
+  apiFileId,
+  teamId
+}: {
+  apiServer: APIFileServer;
+  apiFileId: string;
+  teamId: string;
+}) => {
+  return useApiDatasetRequest({ apiServer }).getFileContent({ teamId, apiFileId });
+};
+
 export const rawText2Chunks = ({
   rawText,
   isQAImport,

packages/service/core/dataset/schema.ts

@@ -83,15 +83,18 @@ const DatasetSchema = new Schema({
       }
     }
   },
-  externalReadUrl: {
-    type: String
-  },
   inheritPermission: {
     type: Boolean,
     default: true
   },
+  apiServer: {
+    type: Object
+  },
 
   // abandoned
+  externalReadUrl: {
+    type: String
+  },
   defaultPermission: Number
 });