4.6.7 fix (#752)

Co-authored-by: Archer <545436317@qq.com>
Co-authored-by: heheer <71265218+newfish-cmyk@users.noreply.github.com>

.gitignore

@@ -36,4 +36,7 @@ dist/
 docSite/public/
 docSite/resources/_gen/
 docSite/.vercel
-*.local.*
+*.local.*
+
+
+.idea/

dev.md

@@ -0,0 +1,17 @@
+# 打包命令
+
+```sh
+# Build image, not proxy
+docker build -t registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.4.7 --build-arg name=app .
+
+# build image with proxy
+docker build -t registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.4.7 --build-arg name=app --build-arg proxy=taobao .
+```
+
+# Pg 常用索引
+
+```sql
+CREATE INDEX IF NOT EXISTS modelData_dataset_id_index ON modeldata (dataset_id);
+CREATE INDEX IF NOT EXISTS modelData_collection_id_index ON modeldata (collection_id);
+CREATE INDEX IF NOT EXISTS modelData_teamId_index ON modeldata (team_id);
+```

docSite/content/docs/commercial/intro.md

@@ -44,15 +44,19 @@ FastGPT 商业版软件根据不同的部署方式，分为 3 类收费模式。
 **特有服务**
 
 {{< table "table-hover table-striped-columns" >}}
-| 部署方式 | 特有服务 | 上线时长 | 价格 |
+| 部署方式 | 特有服务 | 上线时长 | 标品价格 |
 | ---- | ---- | ---- | ---- |
 | Sealos全托管 |  1. 有效期内免费升级。<br>2. 免运维服务&数据库。 |  半天  | 3000元起/月（3个月起）<br>或<br>30000元起/年  |
 | 自有服务器-单机版 |  1. 6个版本的升级服务。 | 14天内 |  60000元/套（不限时长） | 
-| 自有服务器-Sealos版 | 1. 6个版本的升级服务。 | 14天内 | 150000元/套（不限时长）|
+| 自有服务器-高可用版 | 1. 6个版本的升级服务。 | 14天内 | 150000元/套（不限时长）|
 {{< /table >}}
 
 {{% alert icon="🤖 " context="success" %}}
-6个版本的升级服务不是指只能用 6 个版本，而是指依赖 FastGPT 团队提供的升级服务。大部分时候，建议自行升级，也不麻烦。
+- 6个版本的升级服务不是指只能用 6 个版本，而是指依赖 FastGPT 团队提供的升级服务。大部分时候，建议自行升级，也不麻烦。
+- 全托管版本适合技术人员紧缺的团队，仅需关注业务推动，无需关心服务是否正常运行。
+- 单机版和高可用版可以完全部署在自己服务器中。
+- 单机版适合中小团队对内提供服务，需要自己维护数据库备份等。
+- 高可用版适合对外提供在线服务，包含可视化监控、多副本、负载均衡、数据库自动备份等生产环境的基础设施。
 {{% /alert %}}
 
 

docSite/content/docs/course/data_search.md

@@ -29,7 +29,7 @@ weight: 106
 
 ### 全文检索
 
-才用传统的全文检索方式。适合查找关键的主谓语等。
+采用传统的全文检索方式。适合查找关键的主谓语等。
 
 ### 混合检索
 
@@ -55,4 +55,4 @@ FastGPT 会使用 `RRF` 对重排结果、向量搜索结果、全文检索结
 
 一个`0-1`的数值，会过滤掉一些低相关度的搜索结果。
 
-该值仅在`语义检索`或使用`结果重排`时生效。
+该值仅在`语义检索`或使用`结果重排`时生效。

docSite/content/docs/development/configuration.md

@@ -277,7 +277,7 @@ weight: 708
       "maxContext": 1600,
       "maxResponse": 4000,
       "inputPrice": 0,
-      "outputPrice": 0,
+      "outputPrice": 0
     }
   ],
   "vectorModels": [ // 向量模型

docSite/content/docs/development/custom-models/reranker.md

@@ -28,7 +28,7 @@ weight: 910
 ### 源码部署
 
 1. 根据上面的环境配置配置好环境，具体教程自行 GPT；
-2. 下载 [python 文件](app.py)
+2. 下载 [python 文件](https://github.com/labring/FastGPT/tree/main/python/reranker/bge-reranker-base)
 3. 在命令行输入命令 `pip install -r requirments.txt`；
 4. 按照[https://huggingface.co/BAAI/bge-reranker-base](https://huggingface.co/BAAI/bge-reranker-base)下载模型仓库到app.py同级目录
 5. 添加环境变量 `export ACCESS_TOKEN=XXXXXX` 配置 token，这里的 token 只是加一层验证，防止接口被人盗用，默认值为 `ACCESS_TOKEN` ；

docSite/content/docs/development/docker.md

@@ -17,6 +17,11 @@ weight: 707
 | 500w 组向量 | 8c32g | 16c64g 200GB |
 {{< /table >}}
 
+## 部署架构图
+
+![](/imgs/sealos-fastgpt.webp)
+
+
 ### 1. 准备好代理环境（国外服务器可忽略）
 
 确保可以访问 OpenAI，具体方案可以参考：[代理方案](/docs/development/proxy/)。或直接在 Sealos 上 [部署 OneAPI](/docs/development/one-api)，既解决代理问题也能实现多 Key 轮询、接入其他大模型。

docSite/content/docs/development/intro.md

@@ -62,7 +62,7 @@ git clone git@github.com:<github_username>/FastGPT.git
 
 **注意：json 配置文件不能包含注释，介绍中为了方便看才加入的注释**
 
-这个文件大部分时候不需要修改。只需要关注 SystemParams 里的参数：
+这个文件大部分时候不需要修改。只需要关注 `systemEnv` 里的参数：
 
 - `vectorMaxProcess`: 向量生成最大进程，根据数据库和 key 的并发数来决定，通常单个 120 号，2c4g 服务器设置 10~15。
 - `qaMaxProcess`: QA 生成最大进程

docSite/content/docs/development/qa.md

@@ -19,13 +19,17 @@ images: []
 
 ## 通用问题
 
+### 能否纯本地允许
+
+可以。需要准备好向量模型和LLM模型。
+
 ### insufficient_user_quota user quota is not enough 
 
 OneAPI 账号的余额不足，默认 root 用户只有 200 刀，可以手动修改。
 
 ### xxx渠道找不到
 
-OneAPI 中没有配置该模型渠道。
+OneAPI 中没有配置该模型渠道。或者是修改了配置文件中一部分的模型，但没有全部修改。
 
 ### 页面中可以正常回复，API 报错
 
@@ -35,6 +39,15 @@ OneAPI 中没有配置该模型渠道。
 
 OneAPI 的 API Key 配置错误，需要修改`OPENAI_API_KEY`环境变量，并重启容器（先 stop 然后 rm 掉，最后再 up -d 运行一次）。可以`exec`进入容器，`env`查看环境变量是否生效。
 
+### 其他模型没法进行问题分类/内容提取
+
+需要给其他模型配置`toolChoice=false`，就会默认走提示词模式。目前内置提示词仅针对了商业模型API进行测试，国内外的商业模型基本都可用。
+   
+### 页面崩溃
+
+1. 关闭翻译
+2. 检查配置文件是否正常加载，如果没有正常加载会导致缺失系统信息，在某些操作下会导致空指针。
+
 ## Docker 部署常见问题
 
 ### 如何更新？
@@ -96,7 +109,7 @@ mongo连接失败，检查
 
 ### TypeError: Cannot read properties of null (reading 'useMemo' )
 
-用 Node18 试试，可能最新的 Node 有问题。 本地开发流程：
+删除所有的`node_modules`，用 Node18 重新 install 试试，可能最新的 Node 有问题。 本地开发流程：
 
 1. 根目录: `pnpm i`
 2. 复制 `config.json` -> `config.local.json`

docSite/content/docs/development/upgrading/467.md

@@ -0,0 +1,33 @@
+---
+title: 'V4.6.7（需要初始化）'
+description: 'FastGPT V4.6.7'
+icon: 'upgrade'
+draft: false
+toc: true
+weight: 829
+---
+
+## 1。执行初始化 API
+
+发起 1 个 HTTP 请求 ({{rootkey}} 替换成环境变量里的 `rootkey`，{{host}} 替换成自己域名)
+
+1. https://xxxxx/api/admin/initv464
+
+```bash
+curl --location --request POST 'https://{{host}}/api/admin/initv467' \
+--header 'rootkey: {{rootkey}}' \
+--header 'Content-Type: application/json'
+```
+
+初始化说明：
+1. 将 images 重新关联到数据集（不初始化也问题不大，就是可能会留下永久脏数据）
+
+
+## V4.6.7 更新说明
+
+1. 修改了知识库UI及新的导入交互方式。
+2. 优化知识库和对话的数据索引。
+3. 知识库 openAPI，支持通过 API 操作知识库。（文档待补充）
+4. 新增 - 输入框变量提示。输入 { 号后将会获得可用变量提示。根据社区针对高级编排的反馈，我们计划于 2 月份的版本中，优化变量内容，支持模块的局部变量以及更多全局变量写入。
+5. 修复 - API 对话时，chatId 冲突问题。
+6. 修复 - Iframe 嵌入网页可能导致的 window.onLoad 冲突。

docSite/content/docs/use-cases/datasetEngine.md

@@ -25,7 +25,9 @@ FastGPT 采用了 RAG 中的 Embedding 方案构建知识库，要使用好 Fast
 
 FastGPT 采用了 `PostgresSQL` 的 `PG Vector` 插件作为向量检索器，索引为`HNSW`。且`PostgresSQL`仅用于向量检索，`MongoDB`用于其他数据的存取。
 
-在`PostgresSQL`的表中，设置一个 `index` 字段用于存储向量，以及一个`data_id`用于在`MongoDB`中寻找对应的映射值。多个`index`可以对应一组`data_id`，也就是说，一组向量可以对应多组数据。在进行检索时，相同数据会进行合并。
+在`MongoDB`的`dataset.datas`表中，会存储向量原数据的信息，同时有一个`indexes`字段，会记录其对应的向量ID，这是一个数组，也就是说，一组向量可以对应多组数据。
+
+在`PostgresSQL`的表中，设置一个 `index` 字段用于存储向量。在检索时，会先召回向量，再根据向量的ID，去`MongoDB`中寻找原数据内容，如果对应了同一组原数据，则进行合并，向量得分取最高得分。
 
 ![](/imgs/datasetSetting1.png)
 

files/deploy/fastgpt/clash/config.yaml

@@ -1,43 +0,0 @@
-mixed-port: 7890
-allow-lan: false
-bind-address: '*'
-mode: rule
-log-level: warning
-dns:
-  enable: true
-  ipv6: false
-  nameserver:
-    - 8.8.8.8
-    - 8.8.4.4
-  cache-size: 400
-proxies:
-
-proxy-groups:
-  - {
-      name: '♻️ 自动选择',
-      type: url-test,
-      proxies:
-        [
-          香港V02×1.5,
-          ABC,
-          印度01,
-          台湾03,
-          新加坡02,
-          新加坡03,
-          日本01,
-          日本02,
-          新加坡01,
-          美国01,
-          美国02,
-          台湾01,
-          台湾02
-        ],
-      url: 'https://api.openai.com',
-      interval: 3600
-    }
-rules:
-  - 'DOMAIN-SUFFIX,google.com,♻️ 自动选择'
-  - 'DOMAIN-SUFFIX,ai.fastgpt.in,♻️ 自动选择'
-  - 'DOMAIN-SUFFIX,openai.com,♻️ 自动选择'
-  - 'DOMAIN-SUFFIX,api.openai.com,♻️ 自动选择'
-  - 'MATCH,DIRECT'

files/deploy/fastgpt/clash/proxy.sh

@@ -1,18 +0,0 @@
-export ALL_PROXY=socks5://127.0.0.1:7891
-export http_proxy=http://127.0.0.1:7890
-export https_proxy=http://127.0.0.1:7890
-export HTTP_PROXY=http://127.0.0.1:7890
-export HTTPS_PROXY=http://127.0.0.1:7890
-
-OLD_PROCESS=$(pgrep clash)
-if [ ! -z "$OLD_PROCESS" ]; then
-  echo "Killing old process: $OLD_PROCESS"
-  kill $OLD_PROCESS
-fi
-sleep 2
-
-cd  /root/fastgpt/clash/fast
-rm -f ./nohup.out || true
-rm -f ./cache.db || true
-nohup ./clash-linux-amd64-v3  -d ./ &
-echo "Restart clash fast"

files/deploy/fastgpt/clash/stop.sh

@@ -1,10 +0,0 @@
-export ALL_PROXY=''
-export http_proxy=''
-export https_proxy=''
-export HTTP_PROXY=''
-export HTTPS_PROXY=''
-OLD_PROCESS=$(pgrep clash)
-if [ ! -z "$OLD_PROCESS" ]; then
-  echo "Killing old process: $OLD_PROCESS"
-  kill $OLD_PROCESS
-fi

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

@@ -1,9 +1,15 @@
-export type UploadImgProps = {
-  base64Img: string;
+import { MongoImageTypeEnum } from './image/constants';
+
+export type preUploadImgProps = {
+  type: `${MongoImageTypeEnum}`;
+
   expiredTime?: Date;
   metadata?: Record<string, any>;
   shareId?: string;
 };
+export type UploadImgProps = preUploadImgProps & {
+  base64Img: string;
+};
 
 export type UrlFetchParams = {
   urlList: string[];
@@ -11,6 +17,7 @@ export type UrlFetchParams = {
 };
 export type UrlFetchResponse = {
   url: string;
+  title: string;
   content: string;
   selector?: string;
 }[];

packages/global/common/file/icon.ts

@@ -1,12 +1,14 @@
 export const fileImgs = [
-  { suffix: 'pdf', src: '/imgs/files/pdf.svg' },
-  { suffix: 'csv', src: '/imgs/files/csv.svg' },
-  { suffix: '(doc|docs)', src: '/imgs/files/doc.svg' },
-  { suffix: 'txt', src: '/imgs/files/txt.svg' },
-  { suffix: 'md', src: '/imgs/files/markdown.svg' }
+  { suffix: 'pdf', src: 'file/fill/pdf' },
+  { suffix: 'csv', src: 'file/fill/csv' },
+  { suffix: '(doc|docs)', src: 'file/fill/doc' },
+  { suffix: 'txt', src: 'file/fill/txt' },
+  { suffix: 'md', src: 'file/fill/markdown' },
+  { suffix: 'html', src: 'file/fill/html' }
+
   // { suffix: '.', src: '/imgs/files/file.svg' }
 ];
 
-export function getFileIcon(name = '', defaultImg = '/imgs/files/file.svg') {
+export function getFileIcon(name = '', defaultImg = 'file/fill/file') {
   return fileImgs.find((item) => new RegExp(item.suffix, 'gi').test(name))?.src || defaultImg;
 }

packages/global/common/file/image/constants.ts

@@ -0,0 +1,52 @@
+export const imageBaseUrl = '/api/system/img/';
+
+export enum MongoImageTypeEnum {
+  systemAvatar = 'systemAvatar',
+  appAvatar = 'appAvatar',
+  pluginAvatar = 'pluginAvatar',
+  datasetAvatar = 'datasetAvatar',
+  userAvatar = 'userAvatar',
+  teamAvatar = 'teamAvatar',
+
+  chatImage = 'chatImage',
+  collectionImage = 'collectionImage'
+}
+export const mongoImageTypeMap = {
+  [MongoImageTypeEnum.systemAvatar]: {
+    label: 'common.file.type.appAvatar',
+    unique: true
+  },
+  [MongoImageTypeEnum.appAvatar]: {
+    label: 'common.file.type.appAvatar',
+    unique: true
+  },
+  [MongoImageTypeEnum.pluginAvatar]: {
+    label: 'common.file.type.pluginAvatar',
+    unique: true
+  },
+  [MongoImageTypeEnum.datasetAvatar]: {
+    label: 'common.file.type.datasetAvatar',
+    unique: true
+  },
+  [MongoImageTypeEnum.userAvatar]: {
+    label: 'common.file.type.userAvatar',
+    unique: true
+  },
+  [MongoImageTypeEnum.teamAvatar]: {
+    label: 'common.file.type.teamAvatar',
+    unique: true
+  },
+
+  [MongoImageTypeEnum.chatImage]: {
+    label: 'common.file.type.chatImage',
+    unique: false
+  },
+  [MongoImageTypeEnum.collectionImage]: {
+    label: 'common.file.type.collectionImage',
+    unique: false
+  }
+};
+
+export const uniqueImageTypeList = Object.entries(mongoImageTypeMap)
+  .filter(([key, value]) => value.unique)
+  .map(([key]) => key as `${MongoImageTypeEnum}`);

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

@@ -0,0 +1,14 @@
+import { MongoImageTypeEnum } from './constants';
+
+export type MongoImageSchemaType = {
+  _id: string;
+  teamId: string;
+  binary: Buffer;
+  createTime: Date;
+  expiredTime?: Date;
+  type: `${MongoImageTypeEnum}`;
+
+  metadata?: {
+    relatedId?: string; // This id is associated with a set of images
+  };
+};

packages/global/common/math/date.ts

@@ -0,0 +1,10 @@
+// The number of days left in the month is calculated as 30 days per month, and less than 1 day is calculated as 1 day
+export const getMonthRemainingDays = () => {
+  const now = new Date();
+  const year = now.getFullYear();
+  const month = now.getMonth();
+  const date = now.getDate();
+  const days = new Date(year, month + 1, 0).getDate();
+  const remainingDays = days - date;
+  return remainingDays + 1;
+};

packages/global/common/string/markdown.ts

@@ -15,10 +15,10 @@ export const simpleMarkdownText = (rawText: string) => {
     return `[${cleanedLinkText}](${url})`;
   });
 
-  // replace special \.* ……
-  const reg1 = /\\([-.!`_(){}\[\]])/g;
+  // replace special #\.* ……
+  const reg1 = /\\([#`!*()+-_\[\]{}\\.])/g;
   if (reg1.test(rawText)) {
-    rawText = rawText.replace(/\\([`!*()+-_\[\]{}\\.])/g, '$1');
+    rawText = rawText.replace(reg1, '$1');
   }
 
   // replace \\n
@@ -45,14 +45,15 @@ export const uploadMarkdownBase64 = async ({
   uploadImgController
 }: {
   rawText: string;
-  uploadImgController: (base64: string) => Promise<string>;
+  uploadImgController?: (base64: string) => Promise<string>;
 }) => {
-  // match base64, upload and replace it
-  const base64Regex = /data:image\/.*;base64,([^\)]+)/g;
-  const base64Arr = rawText.match(base64Regex) || [];
-  // upload base64 and replace it
-  await Promise.all(
-    base64Arr.map(async (base64Img) => {
+  if (uploadImgController) {
+    // match base64, upload and replace it
+    const base64Regex = /data:image\/.*;base64,([^\)]+)/g;
+    const base64Arr = rawText.match(base64Regex) || [];
+
+    // upload base64 and replace it
+    for await (const base64Img of base64Arr) {
       try {
         const str = await uploadImgController(base64Img);
 
@@ -61,8 +62,8 @@ export const uploadMarkdownBase64 = async ({
         rawText = rawText.replace(base64Img, '');
         rawText = rawText.replace(/!\[.*\]\(\)/g, '');
       }
-    })
-  );
+    }
+  }
 
   // Remove white space on both sides of the picture
   const trimReg = /(!\[.*\]\(.*\))\s*/g;
@@ -70,5 +71,20 @@ export const uploadMarkdownBase64 = async ({
     rawText = rawText.replace(trimReg, '$1');
   }
 
-  return simpleMarkdownText(rawText);
+  return rawText;
+};
+
+export const markdownProcess = async ({
+  rawText,
+  uploadImgController
+}: {
+  rawText: string;
+  uploadImgController?: (base64: string) => Promise<string>;
+}) => {
+  const imageProcess = await uploadMarkdownBase64({
+    rawText,
+    uploadImgController
+  });
+
+  return simpleMarkdownText(imageProcess);
 };

packages/global/common/string/textSplitter.ts

@@ -13,13 +13,12 @@ export const splitText2Chunks = (props: {
   chunkLen: number;
   overlapRatio?: number;
   customReg?: string[];
-  countTokens?: boolean;
 }): {
   chunks: string[];
-  tokens: number;
+  chars: number;
   overlapRatio?: number;
 } => {
-  let { text = '', chunkLen, overlapRatio = 0.2, customReg = [], countTokens = true } = props;
+  let { text = '', chunkLen, overlapRatio = 0.2, customReg = [] } = props;
   const splitMarker = 'SPLIT_HERE_SPLIT_HERE';
   const codeBlockMarker = 'CODE_BLOCK_LINE_MARKER';
   const overlapLen = Math.round(chunkLen * overlapRatio);
@@ -240,13 +239,11 @@ export const splitText2Chunks = (props: {
       mdTitle: ''
     }).map((chunk) => chunk?.replaceAll(codeBlockMarker, '\n') || ''); // restore code block
 
-    const tokens = countTokens
-      ? chunks.reduce((sum, chunk) => sum + countPromptTokens(chunk, 'system'), 0)
-      : 0;
+    const chars = chunks.reduce((sum, chunk) => sum + chunk.length, 0);
 
     return {
       chunks,
-      tokens
+      chars
     };
   } catch (err) {
     throw new Error(getErrText(err));

packages/global/common/string/tiktoken/index.ts

@@ -33,6 +33,12 @@ export function countPromptTokens(
 ) {
   const enc = getTikTokenEnc();
   const text = `${role}\n${prompt}`;
+
+  // too large a text will block the thread
+  if (text.length > 15000) {
+    return text.length * 1.7;
+  }
+
   try {
     const encodeText = enc.encode(text);
     return encodeText.length + role.length; // 补充 role 估算值

packages/global/common/string/time.ts

@@ -1,3 +1,4 @@
 import dayjs from 'dayjs';
 
-export const formatTime2YMDHM = (time: Date) => dayjs(time).format('YYYY-MM-DD HH:mm');
+export const formatTime2YMDHM = (time?: Date) =>
+  time ? dayjs(time).format('YYYY-MM-DD HH:mm') : '';

packages/global/common/string/tools.ts

@@ -1,4 +1,5 @@
 import crypto from 'crypto';
+import { customAlphabet } from 'nanoid';
 
 /* check string is a web link */
 export function strIsLink(str?: string) {
@@ -36,3 +37,7 @@ export function replaceVariable(text: string, obj: Record<string, string | numbe
   }
   return text || '';
 }
+
+export const getNanoid = (size = 12) => {
+  return customAlphabet('abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ1234567890', size)();
+};

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

@@ -51,6 +51,12 @@ export type FastGPTFeConfigsType = {
   favicon?: string;
   customApiDomain?: string;
   customSharePageDomain?: string;
+  subscription?: {
+    datasetStoreFreeSize?: number;
+    datasetStorePrice?: number;
+  };
+
+  uploadFileMaxSize?: number;
 };
 
 export type SystemEnvType = {
@@ -63,4 +69,5 @@ export type SystemEnvType = {
 declare global {
   var feConfigs: FastGPTFeConfigsType;
   var systemEnv: SystemEnvType;
+  var systemInitd: boolean;
 }

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

@@ -4,7 +4,7 @@ import { PermissionTypeEnum } from '../../support/permission/constant';
 import type { AIChatModuleProps, DatasetModuleProps } from '../module/node/type.d';
 import { VariableInputEnum } from '../module/constants';
 import { SelectedDatasetType } from '../module/api';
-import { DatasetSearchModeEnum } from '../dataset/constant';
+import { DatasetSearchModeEnum } from '../dataset/constants';
 
 export interface AppSchema {
   _id: string;

packages/global/core/app/utils.ts

@@ -4,7 +4,7 @@ import { ModuleOutputKeyEnum, ModuleInputKeyEnum } from '../module/constants';
 import type { FlowNodeInputItemType } from '../module/node/type.d';
 import { getGuideModule, splitGuideModule } from '../module/utils';
 import { ModuleItemType } from '../module/type.d';
-import { DatasetSearchModeEnum } from '../dataset/constant';
+import { DatasetSearchModeEnum } from '../dataset/constants';
 
 export const getDefaultAppForm = (templateId = 'fastgpt-universal'): AppSimpleEditFormType => {
   return {

packages/global/core/chat/constants.ts

@@ -31,16 +31,16 @@ export enum ChatSourceEnum {
 }
 export const ChatSourceMap = {
   [ChatSourceEnum.test]: {
-    name: 'chat.logs.test'
+    name: 'core.chat.logs.test'
   },
   [ChatSourceEnum.online]: {
-    name: 'chat.logs.online'
+    name: 'core.chat.logs.online'
   },
   [ChatSourceEnum.share]: {
-    name: 'chat.logs.share'
+    name: 'core.chat.logs.share'
   },
   [ChatSourceEnum.api]: {
-    name: 'chat.logs.api'
+    name: 'core.chat.logs.api'
   }
 };
 

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

@@ -4,7 +4,7 @@ import { ChatRoleEnum, ChatSourceEnum, ChatStatusEnum } from './constants';
 import { FlowNodeTypeEnum } from '../module/node/constant';
 import { ModuleOutputKeyEnum } from '../module/constants';
 import { AppSchema } from '../app/type';
-import { DatasetSearchModeEnum } from '../dataset/constant';
+import { DatasetSearchModeEnum } from '../dataset/constants';
 
 export type ChatSchema = {
   _id: string;
@@ -22,6 +22,7 @@ export type ChatSchema = {
   shareId?: string;
   outLinkUid?: string;
   content: ChatItemType[];
+  metadata?: Record<string, any>;
 };
 
 export type ChatWithAppSchema = Omit<ChatSchema, 'appId'> & {
@@ -91,6 +92,7 @@ export type moduleDispatchResType = {
   runningTime?: number;
   inputTokens?: number;
   outputTokens?: number;
+  charsLength?: number;
   model?: string;
   query?: string;
   contextTotalLen?: number;

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

@@ -1,5 +1,5 @@
 import { DatasetDataIndexItemType, DatasetSchemaType } from './type';
-import { DatasetCollectionTrainingModeEnum, DatasetCollectionTypeEnum } from './constant';
+import { TrainingModeEnum, DatasetCollectionTypeEnum } from './constants';
 import type { LLMModelItemType } from '../ai/model.d';
 
 /* ================= dataset ===================== */
@@ -16,28 +16,47 @@ export type DatasetUpdateBody = {
 };
 
 /* ================= collection ===================== */
-export type CreateDatasetCollectionParams = {
-  datasetId: string;
+export type DatasetCollectionChunkMetadataType = {
   parentId?: string;
+  trainingType?: `${TrainingModeEnum}`;
+  chunkSize?: number;
+  chunkSplitter?: string;
+  qaPrompt?: string;
+  metadata?: Record<string, any>;
+};
+export type CreateDatasetCollectionParams = DatasetCollectionChunkMetadataType & {
+  datasetId: string;
   name: string;
   type: `${DatasetCollectionTypeEnum}`;
-  trainingType?: `${DatasetCollectionTrainingModeEnum}`;
-  chunkSize?: number;
   fileId?: string;
   rawLink?: string;
-  qaPrompt?: string;
   rawTextLength?: number;
   hashRawText?: string;
-  metadata?: Record<string, any>;
+};
+
+export type ApiCreateDatasetCollectionParams = DatasetCollectionChunkMetadataType & {
+  datasetId: string;
+};
+export type TextCreateDatasetCollectionParams = ApiCreateDatasetCollectionParams & {
+  name: string;
+  text: string;
+};
+export type LinkCreateDatasetCollectionParams = ApiCreateDatasetCollectionParams & {
+  link: string;
+};
+export type FileCreateDatasetCollectionParams = ApiCreateDatasetCollectionParams & {
+  name: string;
+  rawTextLength: number;
+  hashRawText: string;
+
+  fileMetadata?: Record<string, any>;
+  collectionMetadata?: Record<string, any>;
 };
 
 /* ================= data ===================== */
 export type PgSearchRawType = {
   id: string;
-  team_id: string;
-  tmb_id: string;
   collection_id: string;
-  data_id: string;
   score: number;
 };
 export type PushDatasetDataChunkProps = {
@@ -51,3 +70,14 @@ export type PostWebsiteSyncParams = {
   datasetId: string;
   billId: string;
 };
+
+export type PushDatasetDataProps = {
+  collectionId: string;
+  data: PushDatasetDataChunkProps[];
+  trainingMode: `${TrainingModeEnum}`;
+  prompt?: string;
+  billId?: string;
+};
+export type PushDatasetDataResponse = {
+  insertLen: number;
+};

packages/global/core/dataset/constants.ts

@@ -6,7 +6,7 @@ export enum DatasetTypeEnum {
 }
 export const DatasetTypeMap = {
   [DatasetTypeEnum.folder]: {
-    icon: 'core/dataset/folderDataset',
+    icon: 'common/folderFill',
     label: 'core.dataset.Folder Dataset',
     collectionLabel: 'common.Folder'
   },
@@ -53,23 +53,7 @@ export const DatasetCollectionTypeMap = {
     name: 'core.dataset.link'
   },
   [DatasetCollectionTypeEnum.virtual]: {
-    name: 'core.dataset.Virtual File'
-  }
-};
-export enum DatasetCollectionTrainingModeEnum {
-  manual = 'manual',
-  chunk = 'chunk',
-  qa = 'qa'
-}
-export const DatasetCollectionTrainingTypeMap = {
-  [DatasetCollectionTrainingModeEnum.manual]: {
-    label: 'core.dataset.collection.training.type manual'
-  },
-  [DatasetCollectionTrainingModeEnum.chunk]: {
-    label: 'core.dataset.collection.training.type chunk'
-  },
-  [DatasetCollectionTrainingModeEnum.qa]: {
-    label: 'core.dataset.collection.training.type qa'
+    name: 'core.dataset.Manual collection'
   }
 };
 
@@ -120,10 +104,12 @@ export enum TrainingModeEnum {
 
 export const TrainingTypeMap = {
   [TrainingModeEnum.chunk]: {
-    label: 'core.dataset.training.type chunk'
+    label: 'core.dataset.training.Chunk mode',
+    tooltip: 'core.dataset.import.Chunk Split Tip'
   },
   [TrainingModeEnum.qa]: {
-    label: 'core.dataset.training.type qa'
+    label: 'core.dataset.training.QA mode',
+    tooltip: 'core.dataset.import.QA Import Tip'
   }
 };
 
@@ -184,4 +170,8 @@ export const SearchScoreTypeMap = {
   }
 };
 
-export const FolderAvatarSrc = '/imgs/files/folder.svg';
+export const FolderIcon = 'file/fill/folder';
+export const FolderImgUrl = '/imgs/files/folder.svg';
+
+export const CustomCollectionIcon = 'common/linkBlue';
+export const LinkCollectionIcon = 'common/linkBlue';

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

@@ -21,7 +21,7 @@ export type UpdateDatasetDataProps = {
 };
 
 export type PatchIndexesProps = {
-  type: 'create' | 'update' | 'delete';
+  type: 'create' | 'update' | 'delete' | 'unChange';
   index: Omit<DatasetDataIndexItemType, 'dataId'> & {
     dataId?: string;
   };

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

@@ -8,7 +8,7 @@ import {
   DatasetTypeEnum,
   SearchScoreTypeEnum,
   TrainingModeEnum
-} from './constant';
+} from './constants';
 
 /* schema */
 export type DatasetSchemaType = {
@@ -42,15 +42,21 @@ export type DatasetCollectionSchemaType = {
   type: `${DatasetCollectionTypeEnum}`;
   createTime: Date;
   updateTime: Date;
+
   trainingType: `${TrainingModeEnum}`;
   chunkSize: number;
+  chunkSplitter?: string;
+  qaPrompt?: string;
+
   fileId?: string;
   rawLink?: string;
-  qaPrompt?: string;
+
   rawTextLength?: number;
   hashRawText?: string;
   metadata?: {
     webPageSelector?: string;
+    relatedImgId?: string; // The id of the associated image collections
+
     [key: string]: any;
   };
 };

packages/global/core/dataset/utils.ts

@@ -1,4 +1,4 @@
-import { DatasetCollectionTypeEnum, DatasetDataIndexTypeEnum } from './constant';
+import { TrainingModeEnum, DatasetCollectionTypeEnum, DatasetDataIndexTypeEnum } from './constants';
 import { getFileIcon } from '../../common/file/icon';
 import { strIsLink } from '../../common/string/tools';
 
@@ -7,18 +7,13 @@ export function getCollectionIcon(
   name = ''
 ) {
   if (type === DatasetCollectionTypeEnum.folder) {
-    return '/imgs/files/folder.svg';
+    return 'common/folderFill';
   }
   if (type === DatasetCollectionTypeEnum.link) {
-    return '/imgs/files/link.svg';
+    return 'common/linkBlue';
   }
   if (type === DatasetCollectionTypeEnum.virtual) {
-    if (name === '手动录入') {
-      return '/imgs/files/manual.svg';
-    } else if (name === '手动标注') {
-      return '/imgs/files/mark.svg';
-    }
-    return '/imgs/files/collection.svg';
+    return 'file/fill/manual';
   }
   return getFileIcon(name);
 }
@@ -30,19 +25,14 @@ export function getSourceNameIcon({
   sourceId?: string;
 }) {
   if (strIsLink(sourceId)) {
-    return '/imgs/files/link.svg';
+    return 'common/linkBlue';
   }
   const fileIcon = getFileIcon(sourceName, '');
   if (fileIcon) {
     return fileIcon;
   }
 
-  if (sourceName === '手动录入') {
-    return '/imgs/files/manual.svg';
-  } else if (sourceName === '手动标注') {
-    return '/imgs/files/mark.svg';
-  }
-  return '/imgs/files/collection.svg';
+  return 'file/fill/manual';
 }
 
 export function getDefaultIndex(props?: { q?: string; a?: string; dataId?: string }) {
@@ -55,3 +45,8 @@ export function getDefaultIndex(props?: { q?: string; a?: string; dataId?: strin
     dataId
   };
 }
+
+export const predictDataLimitLength = (mode: `${TrainingModeEnum}`, data: any[]) => {
+  if (mode === TrainingModeEnum.qa) return data.length * 20;
+  return data.length;
+};

packages/global/core/module/constants.ts

@@ -113,5 +113,16 @@ export enum VariableInputEnum {
   textarea = 'textarea',
   select = 'select'
 }
+export const variableMap = {
+  [VariableInputEnum.input]: {
+    icon: 'core/app/variable/input'
+  },
+  [VariableInputEnum.textarea]: {
+    icon: 'core/app/variable/textarea'
+  },
+  [VariableInputEnum.select]: {
+    icon: 'core/app/variable/select'
+  }
+};
 
 export const DYNAMIC_INPUT_KEY = 'DYNAMIC_INPUT_KEY';

packages/global/core/module/node/constant.ts

@@ -54,10 +54,9 @@ export enum FlowNodeTypeEnum {
   pluginModule = 'pluginModule',
   pluginInput = 'pluginInput',
   pluginOutput = 'pluginOutput',
-  cfr = 'cfr',
+  cfr = 'cfr'
 
   // abandon
-  variable = 'variable'
 }
 
 export const EDGE_TYPE = 'default';

packages/global/core/module/template/system/aiChat.ts

@@ -23,15 +23,15 @@ export const AiChatModule: FlowModuleTemplateType = {
   templateType: ModuleTemplateTypeEnum.textAnswer,
   flowType: FlowNodeTypeEnum.chatNode,
   avatar: '/imgs/module/AI.png',
-  name: 'AI 对话',
-  intro: 'AI 大模型对话',
+  name: 'core.module.template.Ai chat',
+  intro: 'core.module.template.Ai chat intro',
   showStatus: true,
   inputs: [
     Input_Template_Switch,
     {
       key: ModuleInputKeyEnum.aiModel,
       type: FlowNodeInputTypeEnum.selectChatModel,
-      label: '对话模型',
+      label: 'core.module.input.label.aiModel',
       required: true,
       valueType: ModuleIOValueTypeEnum.string,
       showTargetInApp: false,
@@ -41,42 +41,31 @@ export const AiChatModule: FlowModuleTemplateType = {
     {
       key: ModuleInputKeyEnum.aiChatTemperature,
       type: FlowNodeInputTypeEnum.hidden, // Set in the pop-up window
-      label: '温度',
+      label: '',
       value: 0,
       valueType: ModuleIOValueTypeEnum.number,
       min: 0,
       max: 10,
       step: 1,
-      markList: [
-        { label: '严谨', value: 0 },
-        { label: '发散', value: 10 }
-      ],
       showTargetInApp: false,
       showTargetInPlugin: false
     },
     {
       key: ModuleInputKeyEnum.aiChatMaxToken,
       type: FlowNodeInputTypeEnum.hidden, // Set in the pop-up window
-      label: '回复上限',
+      label: '',
       value: 2000,
       valueType: ModuleIOValueTypeEnum.number,
       min: 100,
       max: 4000,
       step: 50,
-      markList: [
-        { label: '100', value: 100 },
-        {
-          label: `${4000}`,
-          value: 4000
-        }
-      ],
       showTargetInApp: false,
       showTargetInPlugin: false
     },
     {
       key: ModuleInputKeyEnum.aiChatIsResponseText,
       type: FlowNodeInputTypeEnum.hidden,
-      label: '返回AI内容',
+      label: '',
       value: true,
       valueType: ModuleIOValueTypeEnum.boolean,
       showTargetInApp: false,
@@ -85,7 +74,7 @@ export const AiChatModule: FlowModuleTemplateType = {
     {
       key: ModuleInputKeyEnum.aiChatQuoteTemplate,
       type: FlowNodeInputTypeEnum.hidden,
-      label: '引用内容模板',
+      label: '',
       valueType: ModuleIOValueTypeEnum.string,
       showTargetInApp: false,
       showTargetInPlugin: false
@@ -93,7 +82,7 @@ export const AiChatModule: FlowModuleTemplateType = {
     {
       key: ModuleInputKeyEnum.aiChatQuotePrompt,
       type: FlowNodeInputTypeEnum.hidden,
-      label: '引用内容提示词',
+      label: '',
       valueType: ModuleIOValueTypeEnum.string,
       showTargetInApp: false,
       showTargetInPlugin: false
@@ -110,7 +99,7 @@ export const AiChatModule: FlowModuleTemplateType = {
     {
       key: ModuleInputKeyEnum.aiSystemPrompt,
       type: FlowNodeInputTypeEnum.textarea,
-      label: '系统提示词',
+      label: 'core.ai.Prompt',
       max: 300,
       valueType: ModuleIOValueTypeEnum.string,
       description: chatNodeSystemPromptTip,
@@ -122,8 +111,8 @@ export const AiChatModule: FlowModuleTemplateType = {
     {
       key: ModuleInputKeyEnum.aiChatDatasetQuote,
       type: FlowNodeInputTypeEnum.target,
-      label: '引用内容',
-      description: "对象数组格式，结构：\n [{q:'问题',a:'回答'}]",
+      label: 'core.module.input.label.Quote',
+      description: 'core.module.input.description.Quote',
       valueType: ModuleIOValueTypeEnum.datasetQuote,
       showTargetInApp: true,
       showTargetInPlugin: true
@@ -134,16 +123,16 @@ export const AiChatModule: FlowModuleTemplateType = {
     Output_Template_UserChatInput,
     {
       key: ModuleOutputKeyEnum.history,
-      label: '新的上下文',
-      description: '将本次回复内容拼接上历史记录，作为新的上下文返回',
+      label: 'core.module.output.label.New context',
+      description: 'core.module.output.description.New context',
       valueType: ModuleIOValueTypeEnum.chatHistory,
       type: FlowNodeOutputTypeEnum.source,
       targets: []
     },
     {
       key: ModuleOutputKeyEnum.answerText,
-      label: 'AI回复内容',
-      description: '将在 stream 回复完毕后触发',
+      label: 'core.module.output.label.Ai response content',
+      description: 'core.module.output.description.Ai response content',
       valueType: ModuleIOValueTypeEnum.string,
       type: FlowNodeOutputTypeEnum.source,
       targets: []

packages/global/core/module/template/system/assignedAnswer.ts

@@ -9,19 +9,17 @@ export const AssignedAnswerModule: FlowModuleTemplateType = {
   templateType: ModuleTemplateTypeEnum.textAnswer,
   flowType: FlowNodeTypeEnum.answerNode,
   avatar: '/imgs/module/reply.png',
-  name: '指定回复',
-  intro: '该模块可以直接回复一段指定的内容。常用于引导、提示',
+  name: 'core.module.template.Assigned reply',
+  intro: 'core.module.template.Assigned reply intro',
   inputs: [
     Input_Template_Switch,
     {
       key: ModuleInputKeyEnum.answerText,
       type: FlowNodeInputTypeEnum.textarea,
       valueType: ModuleIOValueTypeEnum.any,
-      label: '回复的内容',
-      description:
-        '可以使用 \\n 来实现连续换行。\n可以通过外部模块输入实现回复，外部模块输入时会覆盖当前填写的内容。\n如传入非字符串类型数据将会自动转成字符串',
-      placeholder:
-        '可以使用 \\n 来实现连续换行。\n可以通过外部模块输入实现回复，外部模块输入时会覆盖当前填写的内容。\n如传入非字符串类型数据将会自动转成字符串',
+      label: 'core.module.input.label.Response content',
+      description: 'core.module.input.description.Response content',
+      placeholder: 'core.module.input.description.Response content',
       showTargetInApp: true,
       showTargetInPlugin: true
     }

packages/global/core/module/template/system/classifyQuestion.ts

@@ -17,12 +17,8 @@ export const ClassifyQuestionModule: FlowModuleTemplateType = {
   templateType: ModuleTemplateTypeEnum.functionCall,
   flowType: FlowNodeTypeEnum.classifyQuestion,
   avatar: '/imgs/module/cq.png',
-  name: '问题分类',
-  intro: `根据用户的历史记录和当前问题判断该次提问的类型。可以添加多组问题类型，下面是一个模板例子：
-类型1: 打招呼
-类型2: 关于商品“使用”问题
-类型3: 关于商品“购买”问题
-类型4: 其他问题`,
+  name: 'core.module.template.Classify question',
+  intro: `core.module.template.Classify question intro`,
   showStatus: true,
   inputs: [
     Input_Template_Switch,
@@ -30,7 +26,7 @@ export const ClassifyQuestionModule: FlowModuleTemplateType = {
       key: ModuleInputKeyEnum.aiModel,
       type: FlowNodeInputTypeEnum.selectCQModel,
       valueType: ModuleIOValueTypeEnum.string,
-      label: '分类模型',
+      label: 'core.module.input.label.Classify model',
       required: true,
       showTargetInApp: false,
       showTargetInPlugin: false
@@ -39,11 +35,9 @@ export const ClassifyQuestionModule: FlowModuleTemplateType = {
       key: ModuleInputKeyEnum.aiSystemPrompt,
       type: FlowNodeInputTypeEnum.textarea,
       valueType: ModuleIOValueTypeEnum.string,
-      label: '背景知识',
-      description:
-        '你可以添加一些特定内容的介绍，从而更好的识别用户的问题类型。这个内容通常是给模型介绍一个它不知道的内容。',
-      placeholder:
-        '例如: \n1. AIGC（人工智能生成内容）是指使用人工智能技术自动或半自动地生成数字内容，如文本、图像、音乐、视频等。\n2. AIGC技术包括但不限于自然语言处理、计算机视觉、机器学习和深度学习。这些技术可以创建新内容或修改现有内容，以满足特定的创意、教育、娱乐或信息需求。',
+      label: 'core.module.input.label.Background',
+      description: 'core.module.input.description.Background',
+      placeholder: 'core.module.input.placeholder.Classify background',
       showTargetInApp: true,
       showTargetInPlugin: true
     },

packages/global/core/module/template/system/contextExtract.ts

@@ -17,8 +17,8 @@ export const ContextExtractModule: FlowModuleTemplateType = {
   templateType: ModuleTemplateTypeEnum.functionCall,
   flowType: FlowNodeTypeEnum.contentExtract,
   avatar: '/imgs/module/extract.png',
-  name: '文本内容提取',
-  intro: '可从文本中提取指定的数据，例如：sql语句、搜索关键词、代码等',
+  name: 'core.module.template.Extract field',
+  intro: 'core.module.template.Extract field intro',
   showStatus: true,
   inputs: [
     Input_Template_Switch,
@@ -26,7 +26,7 @@ export const ContextExtractModule: FlowModuleTemplateType = {
       key: ModuleInputKeyEnum.aiModel,
       type: FlowNodeInputTypeEnum.selectExtractModel,
       valueType: ModuleIOValueTypeEnum.string,
-      label: '提取模型',
+      label: 'core.module.input.label.LLM',
       required: true,
       showTargetInApp: false,
       showTargetInPlugin: false

packages/global/core/module/template/system/datasetSearch.ts

@@ -12,22 +12,22 @@ import {
 } from '../../constants';
 import { Input_Template_Switch, Input_Template_UserChatInput } from '../input';
 import { Output_Template_Finish, Output_Template_UserChatInput } from '../output';
-import { DatasetSearchModeEnum } from '../../../dataset/constant';
+import { DatasetSearchModeEnum } from '../../../dataset/constants';
 
 export const DatasetSearchModule: FlowModuleTemplateType = {
   id: FlowNodeTypeEnum.datasetSearchNode,
   templateType: ModuleTemplateTypeEnum.functionCall,
   flowType: FlowNodeTypeEnum.datasetSearchNode,
   avatar: '/imgs/module/db.png',
-  name: '知识库搜索',
-  intro: '去知识库中搜索对应的答案。可作为 AI 对话引用参考。',
+  name: 'core.module.template.Dataset search',
+  intro: 'core.module.template.Dataset search intro',
   showStatus: true,
   inputs: [
     Input_Template_Switch,
     {
       key: ModuleInputKeyEnum.datasetSelectList,
       type: FlowNodeInputTypeEnum.selectDataset,
-      label: '关联的知识库',
+      label: 'core.module.input.label.Select dataset',
       value: [],
       valueType: ModuleIOValueTypeEnum.selectDataset,
       list: [],
@@ -38,7 +38,7 @@ export const DatasetSearchModule: FlowModuleTemplateType = {
     {
       key: ModuleInputKeyEnum.datasetSimilarity,
       type: FlowNodeInputTypeEnum.hidden,
-      label: '最低相关性',
+      label: '',
       value: 0.4,
       valueType: ModuleIOValueTypeEnum.number,
       min: 0,
@@ -54,8 +54,7 @@ export const DatasetSearchModule: FlowModuleTemplateType = {
     {
       key: ModuleInputKeyEnum.datasetLimit,
       type: FlowNodeInputTypeEnum.hidden,
-      label: '引用上限',
-      description: '单次搜索最大的 Tokens 数量，中文约1字=1.7Tokens，英文约1字=1Tokens',
+      label: '',
       value: 1500,
       valueType: ModuleIOValueTypeEnum.number,
       showTargetInApp: false,
@@ -93,23 +92,22 @@ export const DatasetSearchModule: FlowModuleTemplateType = {
     Output_Template_UserChatInput,
     {
       key: ModuleOutputKeyEnum.datasetIsEmpty,
-      label: '搜索结果为空',
+      label: 'core.module.output.label.Search result empty',
       type: FlowNodeOutputTypeEnum.source,
       valueType: ModuleIOValueTypeEnum.boolean,
       targets: []
     },
     {
       key: ModuleOutputKeyEnum.datasetUnEmpty,
-      label: '搜索结果不为空',
+      label: 'core.module.output.label.Search result not empty',
       type: FlowNodeOutputTypeEnum.source,
       valueType: ModuleIOValueTypeEnum.boolean,
       targets: []
     },
     {
       key: ModuleOutputKeyEnum.datasetQuoteQA,
-      label: '引用内容',
-      description:
-        '始终返回数组，如果希望搜索结果为空时执行额外操作，需要用到上面的两个输入以及目标模块的触发器',
+      label: 'core.module.output.label.Quote',
+      description: 'core.module.output.label.Quote intro',
       type: FlowNodeOutputTypeEnum.source,
       valueType: ModuleIOValueTypeEnum.datasetQuote,
       targets: []

packages/global/core/module/template/system/http.ts

@@ -17,8 +17,8 @@ export const HttpModule: FlowModuleTemplateType = {
   templateType: ModuleTemplateTypeEnum.externalCall,
   flowType: FlowNodeTypeEnum.httpRequest,
   avatar: '/imgs/module/http.png',
-  name: 'HTTP模块',
-  intro: '可以发出一个 HTTP POST 请求，实现更为复杂的操作（联网搜索、数据库查询等）',
+  name: 'core.module.template.Http request',
+  intro: 'core.module.template.Http request intro',
   showStatus: true,
   inputs: [
     Input_Template_Switch,

packages/global/core/module/template/system/runApp.ts

@@ -22,8 +22,8 @@ export const RunAppModule: FlowModuleTemplateType = {
   templateType: ModuleTemplateTypeEnum.externalCall,
   flowType: FlowNodeTypeEnum.runApp,
   avatar: '/imgs/module/app.png',
-  name: '应用调用',
-  intro: '可以选择一个其他应用进行调用',
+  name: 'core.module.template.Running app',
+  intro: 'core.module.template.Running app intro',
   showStatus: true,
   inputs: [
     Input_Template_Switch,

packages/global/core/module/template/system/runPlugin.ts

@@ -8,7 +8,7 @@ export const RunPluginModule: FlowModuleTemplateType = {
   flowType: FlowNodeTypeEnum.pluginModule,
   avatar: '/imgs/module/custom.png',
   intro: '',
-  name: '自定义模块',
+  name: '',
   showStatus: false,
   inputs: [], // [{key:'pluginId'},...]
   outputs: []

packages/global/core/module/template/system/userGuide.ts

@@ -8,14 +8,14 @@ export const UserGuideModule: FlowModuleTemplateType = {
   templateType: ModuleTemplateTypeEnum.userGuide,
   flowType: FlowNodeTypeEnum.userGuide,
   avatar: '/imgs/module/userGuide.png',
-  name: '用户引导',
+  name: 'core.module.template.User guide',
   intro: userGuideTip,
   inputs: [
     {
       key: ModuleInputKeyEnum.welcomeText,
       type: FlowNodeInputTypeEnum.hidden,
       valueType: ModuleIOValueTypeEnum.string,
-      label: '开场白',
+      label: 'core.app.Welcome Text',
       showTargetInApp: false,
       showTargetInPlugin: false
     },
@@ -23,7 +23,7 @@ export const UserGuideModule: FlowModuleTemplateType = {
       key: ModuleInputKeyEnum.variables,
       type: FlowNodeInputTypeEnum.hidden,
       valueType: ModuleIOValueTypeEnum.any,
-      label: '对话框变量',
+      label: 'core.module.Variable',
       value: [],
       showTargetInApp: false,
       showTargetInPlugin: false
@@ -32,7 +32,7 @@ export const UserGuideModule: FlowModuleTemplateType = {
       key: ModuleInputKeyEnum.questionGuide,
       valueType: ModuleIOValueTypeEnum.boolean,
       type: FlowNodeInputTypeEnum.switch,
-      label: '问题引导',
+      label: '',
       showTargetInApp: false,
       showTargetInPlugin: false
     },
@@ -40,7 +40,7 @@ export const UserGuideModule: FlowModuleTemplateType = {
       key: ModuleInputKeyEnum.tts,
       type: FlowNodeInputTypeEnum.hidden,
       valueType: ModuleIOValueTypeEnum.any,
-      label: '语音播报',
+      label: '',
       showTargetInApp: false,
       showTargetInPlugin: false
     }

packages/global/core/module/template/system/userInput.ts

@@ -16,14 +16,14 @@ export const UserInputModule: FlowModuleTemplateType = {
   templateType: ModuleTemplateTypeEnum.systemInput,
   flowType: FlowNodeTypeEnum.questionInput,
   avatar: '/imgs/module/userChatInput.png',
-  name: '用户问题(入口)',
-  intro: '用户输入的内容。该模块通常作为应用的入口，用户在发送消息后会首先执行该模块。',
+  name: 'core.module.template.Chat entrance',
+  intro: 'core.module.template.Chat entrance intro',
   inputs: [
     {
       key: ModuleInputKeyEnum.userChatInput,
       type: FlowNodeInputTypeEnum.systemInput,
       valueType: ModuleIOValueTypeEnum.string,
-      label: '用户问题',
+      label: 'core.module.input.label.user question',
       showTargetInApp: false,
       showTargetInPlugin: false
     }
@@ -31,7 +31,7 @@ export const UserInputModule: FlowModuleTemplateType = {
   outputs: [
     {
       key: ModuleOutputKeyEnum.userChatInput,
-      label: '用户问题',
+      label: 'core.module.input.label.user question',
       type: FlowNodeOutputTypeEnum.source,
       valueType: ModuleIOValueTypeEnum.string,
       targets: []

packages/global/core/module/template/tip.ts

@@ -1,7 +1,4 @@
-export const chatNodeSystemPromptTip =
-  '模型固定的引导词，通过调整该内容，可以引导模型聊天方向。该内容会被固定在上下文的开头。可使用变量，例如 {{language}}';
-export const userGuideTip = '可以在对话前设置引导语，设置全局变量，设置下一步指引';
-export const welcomeTextTip =
-  '每次对话开始前，发送一个初始内容。支持标准 Markdown 语法，可使用的额外标记:\n[快捷按键]: 用户点击后可以直接发送该问题';
-export const variableTip =
-  '可以在对话开始前，要求用户填写一些内容作为本轮对话的特定变量。该模块位于开场引导之后。\n变量可以通过 {{变量key}} 的形式注入到其他模块 string 类型的输入中，例如：提示词、限定词等';
+export const chatNodeSystemPromptTip = 'core.app.tip.chatNodeSystemPromptTip';
+export const userGuideTip = 'core.app.tip.userGuideTip';
+export const welcomeTextTip = 'core.app.tip.welcomeTextTip';
+export const variableTip = 'core.app.tip.variableTip';

packages/global/core/module/utils.ts

@@ -1,5 +1,5 @@
 import { FlowNodeInputTypeEnum, FlowNodeTypeEnum } from './node/constant';
-import { ModuleIOValueTypeEnum, ModuleInputKeyEnum } from './constants';
+import { ModuleIOValueTypeEnum, ModuleInputKeyEnum, variableMap } from './constants';
 import { FlowNodeInputItemType, FlowNodeOutputItemType } from './node/type';
 import { AppTTSConfigType, ModuleItemType, VariableItemType } from './type';
 import { Input_Template_Switch } from './template/input';
@@ -94,3 +94,12 @@ export function plugin2ModuleIO(
       : []
   };
 }
+
+export const formatVariablesIcon = (
+  variables: VariableItemType[]
+): (VariableItemType & { icon: string })[] => {
+  return variables.map((item) => ({
+    ...item,
+    icon: variableMap[item.type]?.icon
+  }));
+};

packages/global/package.json

@@ -7,7 +7,7 @@
     "encoding": "^0.1.13",
     "js-tiktoken": "^1.0.7",
     "openai": "4.23.0",
-    "pdfjs-dist": "^4.0.269",
+    "nanoid": "^4.0.1",
     "timezones-list": "^3.0.2"
   },
   "devDependencies": {

packages/global/support/user/api.d.ts

@@ -3,7 +3,6 @@ import { OAuthEnum } from './constant';
 export type PostLoginProps = {
   username: string;
   password: string;
-  tmbId?: string;
 };
 
 export type OauthLoginProps = {

packages/global/support/user/team/type.d.ts

@@ -9,7 +9,6 @@ export type TeamSchema = {
   createTime: Date;
   balance: number;
   maxSize: number;
-  lastDatasetBillTime: Date;
   limit: {
     lastExportDatasetTime: Date;
     lastWebsiteSyncTime: Date;

packages/global/support/user/type.d.ts

@@ -13,6 +13,7 @@ export type UserModelSchema = {
   createTime: number;
   timezone: string;
   status: `${UserStatusEnum}`;
+  lastLoginTmbId?: string;
   openaiAccount?: {
     key: string;
     baseUrl: string;

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

@@ -3,8 +3,7 @@ import { BillListItemCountType, BillListItemType } from './type';
 
 export type CreateTrainingBillProps = {
   name: string;
-  vectorModel?: string;
-  agentModel?: string;
+  datasetId: string;
 };
 
 export type ConcatBillProps = BillListItemCountType & {

packages/global/support/wallet/bill/constants.ts

@@ -7,7 +7,7 @@ export enum BillSourceEnum {
   api = 'api',
   shareLink = 'shareLink',
   training = 'training',
-  datasetStore = 'datasetStore'
+  datasetExpand = 'datasetExpand'
 }
 
 export const BillSourceMap: Record<`${BillSourceEnum}`, string> = {
@@ -15,5 +15,5 @@ export const BillSourceMap: Record<`${BillSourceEnum}`, string> = {
   [BillSourceEnum.api]: 'Api',
   [BillSourceEnum.shareLink]: '免登录链接',
   [BillSourceEnum.training]: '数据训练',
-  [BillSourceEnum.datasetStore]: '知识库存储'
+  [BillSourceEnum.datasetExpand]: '知识库扩容'
 };

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

@@ -4,9 +4,8 @@ import { BillSourceEnum } from './constants';
 export type BillListItemCountType = {
   inputTokens?: number;
   outputTokens?: number;
-  textLen?: number;
+  charsLength?: number;
   duration?: number;
-  dataLen?: number;
 
   // abandon
   tokenLen?: number;

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

@@ -0,0 +1,4 @@
+export type SubDatasetSizeParams = {
+  size: number;
+  renew: boolean;
+};

packages/global/support/wallet/sub/constants.ts

@@ -0,0 +1,37 @@
+export enum SubTypeEnum {
+  datasetStore = 'datasetStore'
+}
+
+export const subTypeMap = {
+  [SubTypeEnum.datasetStore]: {
+    label: 'support.user.team.subscription.type.datasetStore'
+  }
+};
+
+export enum SubModeEnum {
+  month = 'month',
+  year = 'year'
+}
+
+export const subModeMap = {
+  [SubModeEnum.month]: {
+    label: 'support.user.team.subscription.mode.month'
+  },
+  [SubModeEnum.year]: {
+    label: 'support.user.team.subscription.mode.year'
+  }
+};
+
+export enum SubStatusEnum {
+  active = 'active',
+  expired = 'expired'
+}
+
+export const subStatusMap = {
+  [SubStatusEnum.active]: {
+    label: 'support.user.team.subscription.status.active'
+  },
+  [SubStatusEnum.expired]: {
+    label: 'support.user.team.subscription.status.expired'
+  }
+};

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

@@ -0,0 +1,12 @@
+import { SubModeEnum, SubStatusEnum, SubTypeEnum } from './constants';
+
+export type TeamSubSchema = {
+  teamId: string;
+  type: `${SubTypeEnum}`;
+  mode: `${SubModeEnum}`;
+  status: `${SubStatusEnum}`;
+  renew: boolean;
+  startTime: Date;
+  expiredTime: Date;
+  datasetStoreAmount?: number;
+};

packages/service/common/file/constants.ts

@@ -0,0 +1,6 @@
+import path from 'path';
+
+export const tmpFileDirPath =
+  process.env.NODE_ENV === 'production' ? '/app/tmp' : path.join(process.cwd(), 'tmp');
+
+export const previewMaxCharCount = 3000;

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

@@ -3,9 +3,10 @@ import { BucketNameEnum } from '@fastgpt/global/common/file/constants';
 import fsp from 'fs/promises';
 import fs from 'fs';
 import { DatasetFileSchema } from '@fastgpt/global/core/dataset/type';
-import { delImgByFileIdList } from '../image/controller';
+import { MongoFileSchema } from './schema';
 
 export function getGFSCollection(bucket: `${BucketNameEnum}`) {
+  MongoFileSchema;
   return connectionMongo.connection.db.collection(`${bucket}.files`);
 }
 export function getGridBucket(bucket: `${BucketNameEnum}`) {
@@ -21,6 +22,7 @@ export async function uploadFile({
   tmbId,
   path,
   filename,
+  contentType,
   metadata = {}
 }: {
   bucketName: `${BucketNameEnum}`;
@@ -28,6 +30,7 @@ export async function uploadFile({
   tmbId: string;
   path: string;
   filename: string;
+  contentType?: string;
   metadata?: Record<string, any>;
 }) {
   if (!path) return Promise.reject(`filePath is empty`);
@@ -44,7 +47,7 @@ export async function uploadFile({
 
   const stream = bucket.openUploadStream(filename, {
     metadata,
-    contentType: metadata?.contentType
+    contentType
   });
 
   // save to gridfs
@@ -96,40 +99,6 @@ export async function delFileByFileIdList({
     }
   }
 }
-// delete file by metadata(datasetId)
-export async function delFileByMetadata({
-  bucketName,
-  datasetId
-}: {
-  bucketName: `${BucketNameEnum}`;
-  datasetId?: string;
-}) {
-  const bucket = getGridBucket(bucketName);
-
-  const files = await bucket
-    .find(
-      {
-        ...(datasetId && { 'metadata.datasetId': datasetId })
-      },
-      {
-        projection: {
-          _id: 1
-        }
-      }
-    )
-    .toArray();
-
-  const idList = files.map((item) => String(item._id));
-
-  // delete img
-  await delImgByFileIdList(idList);
-
-  // delete file
-  await delFileByFileIdList({
-    bucketName,
-    fileIdList: idList
-  });
-}
 
 export async function getDownloadStream({
   bucketName,

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

@@ -0,0 +1,15 @@
+import { connectionMongo, type Model } from '../../mongo';
+const { Schema, model, models } = connectionMongo;
+
+const FileSchema = new Schema({});
+
+try {
+  FileSchema.index({ 'metadata.teamId': 1 });
+  FileSchema.index({ 'metadata.uploadDate': -1 });
+} catch (error) {
+  console.log(error);
+}
+
+export const MongoFileSchema = models['dataset.files'] || model('dataset.files', FileSchema);
+
+MongoFileSchema.syncIndexes();

packages/service/common/file/image/constant.ts

@@ -1 +0,0 @@
-export const imageBaseUrl = '/api/system/img/';

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

@@ -1,5 +1,5 @@
 import { UploadImgProps } from '@fastgpt/global/common/file/api';
-import { imageBaseUrl } from './constant';
+import { imageBaseUrl } from '@fastgpt/global/common/file/image/constants';
 import { MongoImage } from './schema';
 
 export function getMongoImgUrl(id: string) {
@@ -8,10 +8,13 @@ export function getMongoImgUrl(id: string) {
 
 export const maxImgSize = 1024 * 1024 * 12;
 export async function uploadMongoImg({
+  type,
   base64Img,
   teamId,
   expiredTime,
-  metadata
+  metadata,
+
+  shareId
 }: UploadImgProps & {
   teamId: string;
 }) {
@@ -20,12 +23,16 @@ export async function uploadMongoImg({
   }
 
   const base64Data = base64Img.split(',')[1];
+  const binary = Buffer.from(base64Data, 'base64');
 
   const { _id } = await MongoImage.create({
+    type,
     teamId,
-    binary: Buffer.from(base64Data, 'base64'),
+    binary,
     expiredTime: expiredTime,
-    metadata
+    metadata,
+
+    shareId
   });
 
   return getMongoImgUrl(String(_id));
@@ -39,8 +46,17 @@ export async function readMongoImg({ id }: { id: string }) {
   return data?.binary;
 }
 
-export async function delImgByFileIdList(fileIds: string[]) {
+export async function delImgByRelatedId({
+  teamId,
+  relateIds
+}: {
+  teamId: string;
+  relateIds: string[];
+}) {
+  if (relateIds.length === 0) return;
+
   return MongoImage.deleteMany({
-    'metadata.fileId': { $in: fileIds.map((item) => String(item)) }
+    teamId,
+    'metadata.relatedId': { $in: relateIds.map((id) => String(id)) }
   });
 }

packages/service/common/file/image/schema.ts

@@ -1,5 +1,7 @@
 import { TeamCollectionName } from '@fastgpt/global/support/user/team/constant';
 import { connectionMongo, type Model } from '../../mongo';
+import { MongoImageSchemaType } from '@fastgpt/global/common/file/image/type.d';
+import { mongoImageTypeMap } from '@fastgpt/global/common/file/image/constants';
 const { Schema, model, models } = connectionMongo;
 
 const ImageSchema = new Schema({
@@ -12,12 +14,18 @@ const ImageSchema = new Schema({
     type: Date,
     default: () => new Date()
   },
-  binary: {
-    type: Buffer
-  },
   expiredTime: {
     type: Date
   },
+  binary: {
+    type: Buffer
+  },
+  type: {
+    type: String,
+    enum: Object.keys(mongoImageTypeMap),
+    required: true
+  },
+
   metadata: {
     type: Object
   }
@@ -25,14 +33,14 @@ const ImageSchema = new Schema({
 
 try {
   ImageSchema.index({ expiredTime: 1 }, { expireAfterSeconds: 60 });
+  ImageSchema.index({ type: 1 });
+  ImageSchema.index({ createTime: 1 });
+  ImageSchema.index({ teamId: 1, 'metadata.relatedId': 1 });
 } catch (error) {
   console.log(error);
 }
 
-export const MongoImage: Model<{
-  teamId: string;
-  binary: Buffer;
-  metadata?: { fileId?: string };
-}> = models['image'] || model('image', ImageSchema);
+export const MongoImage: Model<MongoImageSchemaType> =
+  models['image'] || model('image', ImageSchema);
 
 MongoImage.syncIndexes();

packages/service/common/file/multer.ts

@@ -1,11 +1,8 @@
 import type { NextApiRequest, NextApiResponse } from 'next';
-import { customAlphabet } from 'nanoid';
 import multer from 'multer';
 import path from 'path';
 import { BucketNameEnum, bucketNameMap } from '@fastgpt/global/common/file/constants';
-import fs from 'fs';
-
-const nanoid = customAlphabet('1234567890abcdef', 12);
+import { getNanoid } from '@fastgpt/global/common/string/tools';
 
 type FileType = {
   fieldname: string;
@@ -17,7 +14,7 @@ type FileType = {
   size: number;
 };
 
-export function getUploadModel({ maxSize = 500 }: { maxSize?: number }) {
+export const getUploadModel = ({ maxSize = 500 }: { maxSize?: number }) => {
   maxSize *= 1024 * 1024;
   class UploadModel {
     uploader = multer({
@@ -26,17 +23,25 @@ export function getUploadModel({ maxSize = 500 }: { maxSize?: number }) {
       },
       preservePath: true,
       storage: multer.diskStorage({
-        filename: (_req, file, cb) => {
+        // destination: (_req, _file, cb) => {
+        //   cb(null, tmpFileDirPath);
+        // },
+        filename: async (req, file, cb) => {
           const { ext } = path.parse(decodeURIComponent(file.originalname));
-          cb(null, nanoid() + ext);
+          cb(null, `${getNanoid()}${ext}`);
         }
       })
-    }).any();
+    }).single('file');
 
-    async doUpload<T = Record<string, any>>(req: NextApiRequest, res: NextApiResponse) {
+    async doUpload<T = Record<string, any>>(
+      req: NextApiRequest,
+      res: NextApiResponse,
+      originBuckerName?: `${BucketNameEnum}`
+    ) {
       return new Promise<{
-        files: FileType[];
-        metadata: T;
+        file: FileType;
+        metadata: Record<string, any>;
+        data: T;
         bucketName?: `${BucketNameEnum}`;
       }>((resolve, reject) => {
         // @ts-ignore
@@ -46,25 +51,33 @@ export function getUploadModel({ maxSize = 500 }: { maxSize?: number }) {
           }
 
           // check bucket name
-          const bucketName = req.body?.bucketName as `${BucketNameEnum}`;
+          const bucketName = (req.body?.bucketName || originBuckerName) as `${BucketNameEnum}`;
           if (bucketName && !bucketNameMap[bucketName]) {
             return reject('BucketName is invalid');
           }
 
+          // @ts-ignore
+          const file = req.file as FileType;
+
           resolve({
-            ...req.body,
-            files:
-              // @ts-ignore
-              req.files?.map((file) => ({
-                ...file,
-                originalname: decodeURIComponent(file.originalname)
-              })) || [],
+            file: {
+              ...file,
+              originalname: decodeURIComponent(file.originalname)
+            },
+            bucketName,
             metadata: (() => {
               if (!req.body?.metadata) return {};
               try {
                 return JSON.parse(req.body.metadata);
               } catch (error) {
-                console.log(error);
+                return {};
+              }
+            })(),
+            data: (() => {
+              if (!req.body?.data) return {};
+              try {
+                return JSON.parse(req.body.data);
+              } catch (error) {
                 return {};
               }
             })()
@@ -75,14 +88,4 @@ export function getUploadModel({ maxSize = 500 }: { maxSize?: number }) {
   }
 
   return new UploadModel();
-}
-
-export const removeFilesByPaths = (paths: string[]) => {
-  paths.forEach((path) => {
-    fs.unlink(path, (err) => {
-      if (err) {
-        console.error(err);
-      }
-    });
-  });
 };

packages/service/common/file/utils.ts

@@ -0,0 +1,11 @@
+import fs from 'fs';
+
+export const removeFilesByPaths = (paths: string[]) => {
+  paths.forEach((path) => {
+    fs.unlink(path, (err) => {
+      if (err) {
+        console.error(err);
+      }
+    });
+  });
+};

packages/service/common/string/cheerio.ts

@@ -50,8 +50,11 @@ export const cheerioToHtml = ({
     .get()
     .join('\n');
 
+  const title = $('head title').text() || $('h1:first').text() || fetchUrl;
+
   return {
     html,
+    title,
     usedSelector
   };
 };
@@ -61,39 +64,39 @@ export const urlsFetch = async ({
 }: UrlFetchParams): Promise<UrlFetchResponse> => {
   urlList = urlList.filter((url) => /^(http|https):\/\/[^ "]+$/.test(url));
 
-  const response = (
-    await Promise.all(
-      urlList.map(async (url) => {
-        try {
-          const fetchRes = await axios.get(url, {
-            timeout: 30000
-          });
+  const response = await Promise.all(
+    urlList.map(async (url) => {
+      try {
+        const fetchRes = await axios.get(url, {
+          timeout: 30000
+        });
 
-          const $ = cheerio.load(fetchRes.data);
-          const { html, usedSelector } = cheerioToHtml({
-            fetchUrl: url,
-            $,
-            selector
-          });
-          const md = await htmlToMarkdown(html);
+        const $ = cheerio.load(fetchRes.data);
+        const { title, html, usedSelector } = cheerioToHtml({
+          fetchUrl: url,
+          $,
+          selector
+        });
+        const md = await htmlToMarkdown(html);
 
-          return {
-            url,
-            content: md,
-            selector: usedSelector
-          };
-        } catch (error) {
-          console.log(error, 'fetch error');
+        return {
+          url,
+          title,
+          content: md,
+          selector: usedSelector
+        };
+      } catch (error) {
+        console.log(error, 'fetch error');
 
-          return {
-            url,
-            content: '',
-            selector: ''
-          };
-        }
-      })
-    )
-  ).filter((item) => item.content);
+        return {
+          url,
+          title: '',
+          content: '',
+          selector: ''
+        };
+      }
+    })
+  );
 
   return response;
 };

packages/service/common/string/markdown.ts

@@ -15,7 +15,9 @@ export const htmlToMarkdown = (html?: string | null) =>
     worker.on('message', (md: string) => {
       worker.terminate();
 
-      resolve(simpleMarkdownText(md));
+      let rawText = simpleMarkdownText(md);
+
+      resolve(rawText);
     });
     worker.on('error', (err) => {
       worker.terminate();

packages/service/common/system/cron.ts

@@ -0,0 +1,6 @@
+import nodeCron from 'node-cron';
+
+export const setCron = (time: string, cb: () => void) => {
+  // second minute hour day month week
+  return nodeCron.schedule(time, cb);
+};

packages/service/common/system/log.ts

@@ -49,6 +49,7 @@ export const addLog = {
   },
   error(msg: string, error?: any) {
     this.log('error', msg, {
+      message: error?.message,
       stack: error?.stack,
       ...(error?.config && {
         config: {

packages/service/common/vectorStore/controller.d.ts

@@ -1,19 +1,19 @@
 export type DeleteDatasetVectorProps = {
+  teamId: string;
+
   id?: string;
   datasetIds?: string[];
   collectionIds?: string[];
-  dataIds?: string[];
+  idList?: string[];
 };
 
 export type InsertVectorProps = {
   teamId: string;
-  tmbId: string;
   datasetId: string;
   collectionId: string;
-  dataId: string;
 };
 
 export type EmbeddingRecallProps = {
-  similarity?: number;
   datasetIds: string[];
+  similarity?: number;
 };

packages/service/common/vectorStore/controller.ts

@@ -10,6 +10,7 @@ const getVectorObj = () => {
 export const initVectorStore = getVectorObj().init;
 export const deleteDatasetDataVector = getVectorObj().delete;
 export const recallFromVectorStore = getVectorObj().recall;
+export const checkVectorDataExist = getVectorObj().checkDataExist;
 export const getVectorDataByTime = getVectorObj().getVectorDataByTime;
 export const getVectorCountByTeamId = getVectorObj().getVectorCountByTeamId;
 
@@ -21,7 +22,7 @@ export const insertDatasetDataVector = async ({
   query: string;
   model: string;
 }) => {
-  const { vectors, tokens } = await getVectorsByText({
+  const { vectors, charsLength } = await getVectorsByText({
     model,
     input: query
   });
@@ -31,32 +32,27 @@ export const insertDatasetDataVector = async ({
   });
 
   return {
-    tokens,
+    charsLength,
     insertId
   };
 };
 
 export const updateDatasetDataVector = async ({
   id,
-  query,
-  model
-}: {
+  ...props
+}: InsertVectorProps & {
   id: string;
   query: string;
   model: string;
 }) => {
-  // get vector
-  const { vectors, tokens } = await getVectorsByText({
-    model,
-    input: query
+  // insert new vector
+  const { charsLength, insertId } = await insertDatasetDataVector(props);
+
+  // delete old vector
+  await deleteDatasetDataVector({
+    teamId: props.teamId,
+    id
   });
 
-  await getVectorObj().update({
-    id,
-    vectors
-  });
-
-  return {
-    tokens
-  };
+  return { charsLength, insertId };
 };

packages/service/common/vectorStore/pg/class.ts

@@ -1,20 +1,20 @@
 import {
   initPg,
   insertDatasetDataVector,
-  updateDatasetDataVector,
   deleteDatasetDataVector,
   embeddingRecall,
   getVectorDataByTime,
-  getVectorCountByTeamId
+  getVectorCountByTeamId,
+  checkDataExist
 } from './controller';
 
 export class PgVector {
   constructor() {}
   init = initPg;
   insert = insertDatasetDataVector;
-  update = updateDatasetDataVector;
   delete = deleteDatasetDataVector;
   recall = embeddingRecall;
+  checkDataExist = checkDataExist;
   getVectorCountByTeamId = getVectorCountByTeamId;
   getVectorDataByTime = getVectorDataByTime;
 }

packages/service/common/vectorStore/pg/controller.ts

@@ -4,7 +4,7 @@ import { delay } from '@fastgpt/global/common/system/utils';
 import { PgClient, connectPg } from './index';
 import { PgSearchRawType } from '@fastgpt/global/core/dataset/api';
 import { EmbeddingRecallItemType } from '../type';
-import { DeleteDatasetVectorProps, EmbeddingRecallProps } from '../controller.d';
+import { DeleteDatasetVectorProps, EmbeddingRecallProps, InsertVectorProps } from '../controller.d';
 import dayjs from 'dayjs';
 
 export async function initPg() {
@@ -16,11 +16,9 @@ export async function initPg() {
           id BIGSERIAL PRIMARY KEY,
           vector VECTOR(1536) NOT NULL,
           team_id VARCHAR(50) NOT NULL,
-          tmb_id VARCHAR(50) NOT NULL,
           dataset_id VARCHAR(50) NOT NULL,
           collection_id VARCHAR(50) NOT NULL,
-          data_id VARCHAR(50) NOT NULL,
-          createTime TIMESTAMP DEFAULT CURRENT_TIMESTAMP
+          createtime TIMESTAMP DEFAULT CURRENT_TIMESTAMP
       );
     `);
 
@@ -34,26 +32,22 @@ export async function initPg() {
   }
 }
 
-export const insertDatasetDataVector = async (props: {
-  teamId: string;
-  tmbId: string;
-  datasetId: string;
-  collectionId: string;
-  dataId: string;
-  vectors: number[][];
-  retry?: number;
-}): Promise<{ insertId: string }> => {
-  const { dataId, teamId, tmbId, datasetId, collectionId, vectors, retry = 3 } = props;
+export const insertDatasetDataVector = async (
+  props: InsertVectorProps & {
+    vectors: number[][];
+    retry?: number;
+  }
+): Promise<{ insertId: string }> => {
+  const { teamId, datasetId, collectionId, vectors, retry = 3 } = props;
+
   try {
     const { rows } = await PgClient.insert(PgDatasetTableName, {
       values: [
         [
           { key: 'vector', value: `[${vectors[0]}]` },
           { key: 'team_id', value: String(teamId) },
-          { key: 'tmb_id', value: String(tmbId) },
-          { key: 'dataset_id', value: datasetId },
-          { key: 'collection_id', value: collectionId },
-          { key: 'data_id', value: String(dataId) }
+          { key: 'dataset_id', value: String(datasetId) },
+          { key: 'collection_id', value: String(collectionId) }
         ]
       ]
     });
@@ -72,43 +66,33 @@ export const insertDatasetDataVector = async (props: {
   }
 };
 
-export const updateDatasetDataVector = async (props: {
-  id: string;
-  vectors: number[][];
-  retry?: number;
-}): Promise<void> => {
-  const { id, vectors, retry = 2 } = props;
-  try {
-    // update pg
-    await PgClient.update(PgDatasetTableName, {
-      where: [['id', id]],
-      values: [{ key: 'vector', value: `[${vectors[0]}]` }]
-    });
-  } catch (error) {
-    if (retry <= 0) {
-      return Promise.reject(error);
-    }
-    await delay(500);
-    return updateDatasetDataVector({
-      ...props,
-      retry: retry - 1
-    });
-  }
-};
-
 export const deleteDatasetDataVector = async (
   props: DeleteDatasetVectorProps & {
     retry?: number;
   }
 ): Promise<any> => {
-  const { id, datasetIds, collectionIds, dataIds, retry = 2 } = props;
+  const { teamId, id, datasetIds, collectionIds, idList, retry = 2 } = props;
+
+  const teamIdWhere = `team_id='${String(teamId)}' AND`;
 
   const where = await (() => {
-    if (id) return `id=${id}`;
-    if (datasetIds) return `dataset_id IN (${datasetIds.map((id) => `'${String(id)}'`).join(',')})`;
-    if (collectionIds)
-      return `collection_id IN (${collectionIds.map((id) => `'${String(id)}'`).join(',')})`;
-    if (dataIds) return `data_id IN (${dataIds.map((id) => `'${String(id)}'`).join(',')})`;
+    if (id) return `${teamIdWhere} id=${id}`;
+
+    if (datasetIds) {
+      return `${teamIdWhere} dataset_id IN (${datasetIds
+        .map((id) => `'${String(id)}'`)
+        .join(',')})`;
+    }
+
+    if (collectionIds) {
+      return `${teamIdWhere} collection_id IN (${collectionIds
+        .map((id) => `'${String(id)}'`)
+        .join(',')})`;
+    }
+
+    if (idList) {
+      return `${teamIdWhere} id IN (${idList.map((id) => `'${String(id)}'`).join(',')})`;
+    }
     return Promise.reject('deleteDatasetData: no where');
   })();
 
@@ -137,13 +121,13 @@ export const embeddingRecall = async (
 ): Promise<{
   results: EmbeddingRecallItemType[];
 }> => {
-  const { vectors, limit, similarity = 0, datasetIds, retry = 2 } = props;
+  const { datasetIds, vectors, limit, similarity = 0, retry = 2 } = props;
 
   try {
     const results: any = await PgClient.query(
       `BEGIN;
         SET LOCAL hnsw.ef_search = ${global.systemEnv.pgHNSWEfSearch || 100};
-        select id, collection_id, data_id, (vector <#> '[${vectors[0]}]') * -1 AS score 
+        select id, collection_id, (vector <#> '[${vectors[0]}]') * -1 AS score 
           from ${PgDatasetTableName} 
           where dataset_id IN (${datasetIds.map((id) => `'${String(id)}'`).join(',')})
               AND vector <#> '[${vectors[0]}]' < -${similarity}
@@ -153,21 +137,10 @@ export const embeddingRecall = async (
 
     const rows = results?.[2]?.rows as PgSearchRawType[];
 
-    // concat same data_id
-    const filterRows: PgSearchRawType[] = [];
-    let set = new Set<string>();
-    for (const row of rows) {
-      if (!set.has(row.data_id)) {
-        filterRows.push(row);
-        set.add(row.data_id);
-      }
-    }
-
     return {
-      results: filterRows.map((item) => ({
+      results: rows.map((item) => ({
         id: item.id,
         collectionId: item.collection_id,
-        dataId: item.data_id,
         score: item.score
       }))
     };
@@ -179,7 +152,11 @@ export const embeddingRecall = async (
   }
 };
 
-// bill
+export const checkDataExist = async (id: string) => {
+  const { rows } = await PgClient.query(`SELECT id FROM ${PgDatasetTableName} WHERE id=${id};`);
+
+  return rows.length > 0;
+};
 export const getVectorCountByTeamId = async (teamId: string) => {
   const total = await PgClient.count(PgDatasetTableName, {
     where: [['team_id', String(teamId)]]
@@ -188,15 +165,20 @@ export const getVectorCountByTeamId = async (teamId: string) => {
   return total;
 };
 export const getVectorDataByTime = async (start: Date, end: Date) => {
-  const { rows } = await PgClient.query<{ id: string; data_id: string }>(`SELECT id, data_id
+  const { rows } = await PgClient.query<{
+    id: string;
+    team_id: string;
+    dataset_id: string;
+  }>(`SELECT id, team_id, dataset_id
   FROM ${PgDatasetTableName}
-  WHERE createTime BETWEEN '${dayjs(start).format('YYYY-MM-DD')}' AND '${dayjs(end).format(
-    'YYYY-MM-DD 23:59:59'
+  WHERE createtime BETWEEN '${dayjs(start).format('YYYY-MM-DD HH:mm:ss')}' AND '${dayjs(end).format(
+    'YYYY-MM-DD HH:mm:ss'
   )}';
   `);
 
   return rows.map((item) => ({
-    id: item.id,
-    dataId: item.data_id
+    id: String(item.id),
+    teamId: item.team_id,
+    datasetId: item.dataset_id
   }));
 };

packages/service/common/vectorStore/type.d.ts

@@ -7,6 +7,5 @@ declare global {
 export type EmbeddingRecallItemType = {
   id: string;
   collectionId: string;
-  dataId: string;
   score: number;
 };

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

@@ -18,10 +18,9 @@ export async function getVectorsByText({
   }
 
   try {
-    // 获取 chatAPI
     const ai = getAIApi();
 
-    // 把输入的内容转成向量
+    // input text to vector
     const result = await ai.embeddings
       .create({
         model,
@@ -32,13 +31,13 @@ export async function getVectorsByText({
           return Promise.reject('Embedding API 404');
         }
         if (!res?.data?.[0]?.embedding) {
-          console.log(res?.data);
+          console.log(res);
           // @ts-ignore
           return Promise.reject(res.data?.err?.message || 'Embedding API Error');
         }
 
         return {
-          tokens: res.usage.total_tokens || 0,
+          charsLength: input.length,
           vectors: await Promise.all(res.data.map((item) => unityDimensional(item.embedding)))
         };
       });
@@ -53,7 +52,9 @@ export async function getVectorsByText({
 
 function unityDimensional(vector: number[]) {
   if (vector.length > 1536) {
-    console.log(`当前向量维度为: ${vector.length}, 向量维度不能超过 1536, 已自动截取前 1536 维度`);
+    console.log(
+      `The current vector dimension is ${vector.length}, and the vector dimension cannot exceed 1536. The first 1536 dimensions are automatically captured`
+    );
     return vector.slice(0, 1536);
   }
   let resultVector = vector;

packages/service/core/chat/chatItemSchema.ts

@@ -2,8 +2,7 @@ import { connectionMongo, type Model } from '../../common/mongo';
 const { Schema, model, models } = connectionMongo;
 import { ChatItemSchema as ChatItemType } from '@fastgpt/global/core/chat/type';
 import { ChatRoleMap } from '@fastgpt/global/core/chat/constants';
-import { customAlphabet } from 'nanoid';
-const nanoid = customAlphabet('abcdefghijklmnopqrstuvwxyz1234567890', 24);
+import { getNanoid } from '@fastgpt/global/common/string/tools';
 import {
   TeamCollectionName,
   TeamMemberCollectionName
@@ -12,25 +11,9 @@ import { appCollectionName } from '../app/schema';
 import { userCollectionName } from '../../support/user/schema';
 import { ModuleOutputKeyEnum } from '@fastgpt/global/core/module/constants';
 
+export const ChatItemCollectionName = 'chatitems';
+
 const ChatItemSchema = new Schema({
-  dataId: {
-    type: String,
-    require: true,
-    default: () => nanoid()
-  },
-  appId: {
-    type: Schema.Types.ObjectId,
-    ref: appCollectionName,
-    required: true
-  },
-  chatId: {
-    type: String,
-    require: true
-  },
-  userId: {
-    type: Schema.Types.ObjectId,
-    ref: userCollectionName
-  },
   teamId: {
     type: Schema.Types.ObjectId,
     ref: TeamCollectionName,
@@ -41,6 +24,24 @@ const ChatItemSchema = new Schema({
     ref: TeamMemberCollectionName,
     required: true
   },
+  userId: {
+    type: Schema.Types.ObjectId,
+    ref: userCollectionName
+  },
+  chatId: {
+    type: String,
+    require: true
+  },
+  dataId: {
+    type: String,
+    require: true,
+    default: () => getNanoid(22)
+  },
+  appId: {
+    type: Schema.Types.ObjectId,
+    ref: appCollectionName,
+    required: true
+  },
   time: {
     type: Date,
     default: () => new Date()
@@ -80,19 +81,24 @@ const ChatItemSchema = new Schema({
 });
 
 try {
-  ChatItemSchema.index({ dataId: -1 });
-  ChatItemSchema.index({ time: -1 });
-  ChatItemSchema.index({ appId: 1 });
-  ChatItemSchema.index({ chatId: 1 });
-  ChatItemSchema.index({ userGoodFeedback: 1 });
-  ChatItemSchema.index({ userBadFeedback: 1 });
-  ChatItemSchema.index({ customFeedbacks: 1 });
-  ChatItemSchema.index({ adminFeedback: 1 });
+  ChatItemSchema.index({ dataId: 1 }, { background: true });
+  /* delete by app; 
+     delete by chat id;
+     get chat list; 
+     get chat logs; 
+     close custom feedback; 
+  */
+  ChatItemSchema.index({ appId: 1, chatId: 1, dataId: 1 }, { background: true });
+  ChatItemSchema.index({ time: -1 }, { background: true });
+  ChatItemSchema.index({ userGoodFeedback: 1 }, { background: true });
+  ChatItemSchema.index({ userBadFeedback: 1 }, { background: true });
+  ChatItemSchema.index({ customFeedbacks: 1 }, { background: true });
+  ChatItemSchema.index({ adminFeedback: 1 }, { background: true });
 } catch (error) {
   console.log(error);
 }
 
 export const MongoChatItem: Model<ChatItemType> =
-  models['chatItem'] || model('chatItem', ChatItemSchema);
+  models[ChatItemCollectionName] || model(ChatItemCollectionName, ChatItemSchema);
 
 MongoChatItem.syncIndexes();

packages/service/core/chat/chatSchema.ts

@@ -1,13 +1,12 @@
 import { connectionMongo, type Model } from '../../common/mongo';
 const { Schema, model, models } = connectionMongo;
 import { ChatSchema as ChatType } from '@fastgpt/global/core/chat/type.d';
-import { ChatRoleMap, ChatSourceMap } from '@fastgpt/global/core/chat/constants';
+import { ChatSourceMap } from '@fastgpt/global/core/chat/constants';
 import {
   TeamCollectionName,
   TeamMemberCollectionName
 } from '@fastgpt/global/support/user/team/constant';
 import { appCollectionName } from '../app/schema';
-import { ModuleOutputKeyEnum } from '@fastgpt/global/core/module/constants';
 
 export const chatCollectionName = 'chat';
 
@@ -48,7 +47,8 @@ const ChatSchema = new Schema({
     default: ''
   },
   top: {
-    type: Boolean
+    type: Boolean,
+    default: false
   },
   source: {
     type: String,
@@ -69,34 +69,20 @@ const ChatSchema = new Schema({
     //For special storage
     type: Object,
     default: {}
-  },
-  content: {
-    type: [
-      {
-        obj: {
-          type: String,
-          required: true,
-          enum: Object.keys(ChatRoleMap)
-        },
-        value: {
-          type: String,
-          default: ''
-        },
-        [ModuleOutputKeyEnum.responseData]: {
-          type: Array,
-          default: []
-        }
-      }
-    ],
-    default: []
   }
 });
 
 try {
-  ChatSchema.index({ appId: 1 });
-  ChatSchema.index({ tmbId: 1 });
-  ChatSchema.index({ shareId: 1 });
-  ChatSchema.index({ updateTime: -1 });
+  ChatSchema.index({ chatId: 1 }, { background: true });
+  // get user history
+  ChatSchema.index({ tmbId: 1, appId: 1, top: -1, updateTime: -1 }, { background: true });
+  // delete by appid; clear history; init chat; update chat; auth chat;
+  ChatSchema.index({ appId: 1, chatId: 1 }, { background: true });
+
+  // get chat logs;
+  ChatSchema.index({ teamId: 1, appId: 1, updateTime: -1 }, { background: true });
+  // get share chat history
+  ChatSchema.index({ shareId: 1, outLinkUid: 1 }, { background: true });
 } catch (error) {
   console.log(error);
 }

packages/service/core/chat/controller.ts

@@ -3,10 +3,12 @@ import { MongoChatItem } from './chatItemSchema';
 import { addLog } from '../../common/system/log';
 
 export async function getChatItems({
+  appId,
   chatId,
   limit = 30,
   field
 }: {
+  appId: string;
   chatId?: string;
   limit?: number;
   field: string;
@@ -15,7 +17,10 @@ export async function getChatItems({
     return { history: [] };
   }
 
-  const history = await MongoChatItem.find({ chatId }, field).sort({ _id: -1 }).limit(limit).lean();
+  const history = await MongoChatItem.find({ appId, chatId }, field)
+    .sort({ _id: -1 })
+    .limit(limit)
+    .lean();
 
   history.reverse();
 
@@ -23,10 +28,12 @@ export async function getChatItems({
 }
 
 export const addCustomFeedbacks = async ({
+  appId,
   chatId,
   chatItemId,
   feedbacks
 }: {
+  appId: string;
   chatId?: string;
   chatItemId?: string;
   feedbacks: string[];

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

@@ -1,9 +1,20 @@
 import {
-  DatasetCollectionTrainingModeEnum,
+  TrainingModeEnum,
   DatasetCollectionTypeEnum
-} from '@fastgpt/global/core/dataset/constant';
+} from '@fastgpt/global/core/dataset/constants';
 import type { CreateDatasetCollectionParams } from '@fastgpt/global/core/dataset/api.d';
 import { MongoDatasetCollection } from './schema';
+import {
+  CollectionWithDatasetType,
+  DatasetCollectionSchemaType
+} from '@fastgpt/global/core/dataset/type';
+import { MongoDatasetTraining } from '../training/schema';
+import { delay } from '@fastgpt/global/common/system/utils';
+import { MongoDatasetData } from '../data/schema';
+import { delImgByRelatedId } from '../../../common/file/image/controller';
+import { deleteDatasetDataVector } from '../../../common/vectorStore/controller';
+import { delFileByFileIdList } from '../../../common/file/gridfs/controller';
+import { BucketNameEnum } from '@fastgpt/global/common/file/constants';
 
 export async function createOneCollection({
   teamId,
@@ -12,11 +23,15 @@ export async function createOneCollection({
   parentId,
   datasetId,
   type,
-  trainingType = DatasetCollectionTrainingModeEnum.manual,
-  chunkSize = 0,
+
+  trainingType = TrainingModeEnum.chunk,
+  chunkSize = 512,
+  chunkSplitter,
+  qaPrompt,
+
   fileId,
   rawLink,
-  qaPrompt,
+
   hashRawText,
   rawTextLength,
   metadata = {},
@@ -30,11 +45,15 @@ export async function createOneCollection({
     datasetId,
     name,
     type,
+
     trainingType,
     chunkSize,
+    chunkSplitter,
+    qaPrompt,
+
     fileId,
     rawLink,
-    qaPrompt,
+
     rawTextLength,
     hashRawText,
     metadata
@@ -74,26 +93,59 @@ export function createDefaultCollection({
     datasetId,
     parentId,
     type: DatasetCollectionTypeEnum.virtual,
-    trainingType: DatasetCollectionTrainingModeEnum.manual,
+    trainingType: TrainingModeEnum.chunk,
     chunkSize: 0,
     updateTime: new Date('2099')
   });
 }
 
-// check same collection
-export const getSameRawTextCollection = async ({
-  datasetId,
-  hashRawText
+/**
+ * delete collection and it related data
+ */
+export async function delCollectionAndRelatedSources({
+  collections
 }: {
-  datasetId: string;
-  hashRawText?: string;
-}) => {
-  if (!hashRawText) return undefined;
+  collections: (CollectionWithDatasetType | DatasetCollectionSchemaType)[];
+}) {
+  if (collections.length === 0) return;
 
-  const collection = await MongoDatasetCollection.findOne({
-    datasetId,
-    hashRawText
+  const teamId = collections[0].teamId;
+
+  if (!teamId) return Promise.reject('teamId is not exist');
+
+  const collectionIds = collections.map((item) => String(item._id));
+  const fileIdList = collections.map((item) => item?.fileId || '').filter(Boolean);
+  const relatedImageIds = collections
+    .map((item) => item?.metadata?.relatedImgId || '')
+    .filter(Boolean);
+
+  // delete training data
+  await MongoDatasetTraining.deleteMany({
+    teamId,
+    collectionId: { $in: collectionIds }
   });
 
-  return collection;
-};
+  await delay(2000);
+
+  // delete dataset.datas
+  await MongoDatasetData.deleteMany({ teamId, collectionId: { $in: collectionIds } });
+  // delete pg data
+  await deleteDatasetDataVector({ teamId, collectionIds });
+
+  // delete file and imgs
+  await Promise.all([
+    delImgByRelatedId({
+      teamId,
+      relateIds: relatedImageIds
+    }),
+    delFileByFileIdList({
+      bucketName: BucketNameEnum.dataset,
+      fileIdList
+    })
+  ]);
+
+  // delete collections
+  await MongoDatasetCollection.deleteMany({
+    _id: { $in: collectionIds }
+  });
+}

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

@@ -1,10 +1,7 @@
 import { connectionMongo, type Model } from '../../../common/mongo';
 const { Schema, model, models } = connectionMongo;
 import { DatasetCollectionSchemaType } from '@fastgpt/global/core/dataset/type.d';
-import {
-  DatasetCollectionTrainingTypeMap,
-  DatasetCollectionTypeMap
-} from '@fastgpt/global/core/dataset/constant';
+import { TrainingTypeMap, DatasetCollectionTypeMap } from '@fastgpt/global/core/dataset/constants';
 import { DatasetCollectionName } from '../schema';
 import {
   TeamCollectionName,
@@ -56,15 +53,23 @@ const DatasetCollectionSchema = new Schema({
     type: Date,
     default: () => new Date()
   },
+
   trainingType: {
     type: String,
-    enum: Object.keys(DatasetCollectionTrainingTypeMap),
+    enum: Object.keys(TrainingTypeMap),
     required: true
   },
   chunkSize: {
     type: Number,
     required: true
   },
+  chunkSplitter: {
+    type: String
+  },
+  qaPrompt: {
+    type: String
+  },
+
   fileId: {
     type: Schema.Types.ObjectId,
     ref: 'dataset.files'
@@ -72,9 +77,6 @@ const DatasetCollectionSchema = new Schema({
   rawLink: {
     type: String
   },
-  qaPrompt: {
-    type: String
-  },
 
   rawTextLength: {
     type: Number
@@ -89,10 +91,19 @@ const DatasetCollectionSchema = new Schema({
 });
 
 try {
-  DatasetCollectionSchema.index({ datasetId: 1 });
-  DatasetCollectionSchema.index({ datasetId: 1, parentId: 1 });
-  DatasetCollectionSchema.index({ updateTime: -1 });
-  DatasetCollectionSchema.index({ hashRawText: -1 });
+  // auth file
+  DatasetCollectionSchema.index({ teamId: 1, fileId: 1 }, { background: true });
+
+  // list collection; deep find collections
+  DatasetCollectionSchema.index(
+    {
+      teamId: 1,
+      datasetId: 1,
+      parentId: 1,
+      updateTime: -1
+    },
+    { background: true }
+  );
 } catch (error) {
   console.log(error);
 }

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

@@ -4,16 +4,32 @@ import type { ParentTreePathItemType } from '@fastgpt/global/common/parentFolder
 import { splitText2Chunks } from '@fastgpt/global/common/string/textSplitter';
 import { MongoDatasetTraining } from '../training/schema';
 import { urlsFetch } from '../../../common/string/cheerio';
-import { DatasetCollectionTypeEnum } from '@fastgpt/global/core/dataset/constant';
+import {
+  DatasetCollectionTypeEnum,
+  TrainingModeEnum
+} from '@fastgpt/global/core/dataset/constants';
 import { hashStr } from '@fastgpt/global/common/string/tools';
 
 /**
  * get all collection by top collectionId
  */
-export async function findCollectionAndChild(id: string, fields = '_id parentId name metadata') {
+export async function findCollectionAndChild({
+  teamId,
+  datasetId,
+  collectionId,
+  fields = '_id parentId name metadata'
+}: {
+  teamId: string;
+  datasetId: string;
+  collectionId: string;
+  fields?: string;
+}) {
   async function find(id: string) {
     // find children
-    const children = await MongoDatasetCollection.find({ parentId: id }, fields);
+    const children = await MongoDatasetCollection.find(
+      { teamId, datasetId, parentId: id },
+      fields
+    ).lean();
 
     let collections = children;
 
@@ -25,8 +41,8 @@ export async function findCollectionAndChild(id: string, fields = '_id parentId
     return collections;
   }
   const [collection, childCollections] = await Promise.all([
-    MongoDatasetCollection.findById(id, fields),
-    find(id)
+    MongoDatasetCollection.findById(collectionId, fields),
+    find(collectionId)
   ]);
 
   if (!collection) {
@@ -92,8 +108,12 @@ export const getCollectionAndRawText = async ({
     return Promise.reject('Collection not found');
   }
 
-  const rawText = await (async () => {
-    if (newRawText) return newRawText;
+  const { title, rawText } = await (async () => {
+    if (newRawText)
+      return {
+        title: '',
+        rawText: newRawText
+      };
     // link
     if (col.type === DatasetCollectionTypeEnum.link && col.rawLink) {
       // crawl new data
@@ -102,19 +122,26 @@ export const getCollectionAndRawText = async ({
         selector: col.datasetId?.websiteConfig?.selector || col?.metadata?.webPageSelector
       });
 
-      return result[0].content;
+      return {
+        title: result[0]?.title,
+        rawText: result[0]?.content
+      };
     }
 
     // file
 
-    return '';
+    return {
+      title: '',
+      rawText: ''
+    };
   })();
 
   const hashRawText = hashStr(rawText);
-  const isSameRawText = col.hashRawText === hashRawText;
+  const isSameRawText = rawText && col.hashRawText === hashRawText;
 
   return {
     collection: col,
+    title,
     rawText,
     isSameRawText
   };
@@ -135,6 +162,7 @@ export const reloadCollectionChunks = async ({
   rawText?: string;
 }) => {
   const {
+    title,
     rawText: newRawText,
     collection: col,
     isSameRawText
@@ -149,11 +177,15 @@ export const reloadCollectionChunks = async ({
   // split data
   const { chunks } = splitText2Chunks({
     text: newRawText,
-    chunkLen: col.chunkSize || 512,
-    countTokens: false
+    chunkLen: col.chunkSize || 512
   });
 
   // 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');
+  })();
   await MongoDatasetTraining.insertMany(
     chunks.map((item, i) => ({
       teamId: col.teamId,
@@ -163,7 +195,7 @@ export const reloadCollectionChunks = async ({
       billId,
       mode: col.trainingType,
       prompt: '',
-      model: col.datasetId.vectorModel,
+      model,
       q: item,
       a: '',
       chunkIndex: i
@@ -172,6 +204,7 @@ export const reloadCollectionChunks = async ({
 
   // update raw text
   await MongoDatasetCollection.findByIdAndUpdate(col._id, {
+    ...(title && { name: title }),
     rawTextLength: newRawText.length,
     hashRawText: hashStr(newRawText)
   });

packages/service/core/dataset/controller.ts

@@ -1,24 +1,47 @@
-import { CollectionWithDatasetType } from '@fastgpt/global/core/dataset/type';
+import { CollectionWithDatasetType, DatasetSchemaType } from '@fastgpt/global/core/dataset/type';
 import { MongoDatasetCollection } from './collection/schema';
 import { MongoDataset } from './schema';
+import { delCollectionAndRelatedSources } from './collection/controller';
 
 /* ============= dataset ========== */
 /* find all datasetId by top datasetId */
-export async function findDatasetIdTreeByTopDatasetId(
-  id: string,
-  result: string[] = []
-): Promise<string[]> {
-  let allChildrenIds = [...result];
+export async function findDatasetAndAllChildren({
+  teamId,
+  datasetId,
+  fields
+}: {
+  teamId: string;
+  datasetId: string;
+  fields?: string;
+}): Promise<DatasetSchemaType[]> {
+  const find = async (id: string) => {
+    const children = await MongoDataset.find(
+      {
+        teamId,
+        parentId: id
+      },
+      fields
+    ).lean();
 
-  // find children
-  const children = await MongoDataset.find({ parentId: id });
+    let datasets = children;
 
-  for (const child of children) {
-    const grandChildrenIds = await findDatasetIdTreeByTopDatasetId(child._id, result);
-    allChildrenIds = allChildrenIds.concat(grandChildrenIds);
+    for (const child of children) {
+      const grandChildrenIds = await find(child._id);
+      datasets = datasets.concat(grandChildrenIds);
+    }
+
+    return datasets;
+  };
+  const [dataset, childDatasets] = await Promise.all([
+    MongoDataset.findById(datasetId),
+    find(datasetId)
+  ]);
+
+  if (!dataset) {
+    return Promise.reject('Dataset not found');
   }
 
-  return [String(id), ...allChildrenIds];
+  return [dataset, ...childDatasets];
 }
 
 export async function getCollectionWithDataset(collectionId: string) {
@@ -30,3 +53,22 @@ export async function getCollectionWithDataset(collectionId: string) {
   }
   return data;
 }
+
+/* delete all data by datasetIds */
+export async function delDatasetRelevantData({ datasets }: { datasets: DatasetSchemaType[] }) {
+  if (!datasets.length) return;
+
+  const teamId = datasets[0].teamId;
+  const datasetIds = datasets.map((item) => String(item._id));
+
+  // Get _id, teamId, fileId, metadata.relatedImgId for all collections
+  const collections = await MongoDatasetCollection.find(
+    {
+      teamId,
+      datasetId: { $in: datasetIds }
+    },
+    '_id teamId fileId metadata'
+  ).lean();
+
+  await delCollectionAndRelatedSources({ collections });
+}

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

@@ -1,81 +1,2 @@
 import { MongoDatasetData } from './schema';
-import { MongoDatasetTraining } from '../training/schema';
-import { delFileByFileIdList, delFileByMetadata } from '../../../common/file/gridfs/controller';
-import { BucketNameEnum } from '@fastgpt/global/common/file/constants';
-import { MongoDatasetCollection } from '../collection/schema';
-import { delay } from '@fastgpt/global/common/system/utils';
-import { delImgByFileIdList } from '../../../common/file/image/controller';
 import { deleteDatasetDataVector } from '../../../common/vectorStore/controller';
-
-/* delete all data by datasetIds */
-export async function delDatasetRelevantData({ datasetIds }: { datasetIds: string[] }) {
-  datasetIds = datasetIds.map((item) => String(item));
-
-  // delete training data(There could be a training mission)
-  await MongoDatasetTraining.deleteMany({
-    datasetId: { $in: datasetIds }
-  });
-
-  await delay(2000);
-
-  // delete dataset.datas
-  await MongoDatasetData.deleteMany({ datasetId: { $in: datasetIds } });
-  // delete pg data
-  await deleteDatasetDataVector({ datasetIds });
-
-  // delete collections
-  await MongoDatasetCollection.deleteMany({
-    datasetId: { $in: datasetIds }
-  });
-
-  // delete related files
-  await Promise.all(
-    datasetIds.map((id) => delFileByMetadata({ bucketName: BucketNameEnum.dataset, datasetId: id }))
-  );
-}
-/**
- * delete all data by collectionIds
- */
-export async function delCollectionRelevantData({
-  collectionIds,
-  fileIds
-}: {
-  collectionIds: string[];
-  fileIds: string[];
-}) {
-  collectionIds = collectionIds.filter(Boolean).map((item) => String(item));
-  const filterFileIds = fileIds.filter(Boolean).map((item) => String(item));
-
-  // delete training data
-  await MongoDatasetTraining.deleteMany({
-    collectionId: { $in: collectionIds }
-  });
-
-  await delay(2000);
-
-  // delete dataset.datas
-  await MongoDatasetData.deleteMany({ collectionId: { $in: collectionIds } });
-  // delete pg data
-  await deleteDatasetDataVector({ collectionIds });
-
-  // delete collections
-  await MongoDatasetCollection.deleteMany({
-    _id: { $in: collectionIds }
-  });
-
-  // delete file and imgs
-  await Promise.all([
-    delImgByFileIdList(filterFileIds),
-    delFileByFileIdList({
-      bucketName: BucketNameEnum.dataset,
-      fileIdList: filterFileIds
-    })
-  ]);
-}
-/**
- * delete one data by mongoDataId
- */
-export async function delDatasetDataByDataId(mongoDataId: string) {
-  await deleteDatasetDataVector({ dataIds: [mongoDataId] });
-  await MongoDatasetData.findByIdAndDelete(mongoDataId);
-}

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

@@ -10,7 +10,7 @@ import { DatasetColCollectionName } from '../collection/schema';
 import {
   DatasetDataIndexTypeEnum,
   DatasetDataIndexTypeMap
-} from '@fastgpt/global/core/dataset/constant';
+} from '@fastgpt/global/core/dataset/constants';
 
 export const DatasetDataCollectionName = 'dataset.datas';
 
@@ -71,6 +71,7 @@ const DatasetDataSchema = new Schema({
     ],
     default: []
   },
+
   updateTime: {
     type: Date,
     default: () => new Date()
@@ -85,12 +86,18 @@ const DatasetDataSchema = new Schema({
 });
 
 try {
-  DatasetDataSchema.index({ datasetId: 1 });
-  DatasetDataSchema.index({ collectionId: 1 });
-  DatasetDataSchema.index({ updateTime: -1 });
+  // same data check
+  DatasetDataSchema.index({ teamId: 1, collectionId: 1, q: 1, a: 1 }, { background: true });
+  // list collection and count data; list data
+  DatasetDataSchema.index(
+    { teamId: 1, datasetId: 1, collectionId: 1, chunkIndex: 1, updateTime: -1 },
+    { background: true }
+  );
   // full text index
-  DatasetDataSchema.index({ datasetId: 1, fullTextToken: 'text' });
-  DatasetDataSchema.index({ inited: 1 });
+  DatasetDataSchema.index({ teamId: 1, datasetId: 1, fullTextToken: 'text' }, { background: true });
+  // Recall vectors after data matching
+  DatasetDataSchema.index({ teamId: 1, datasetId: 1, 'indexes.dataId': 1 }, { background: true });
+  DatasetDataSchema.index({ updateTime: 1 }, { background: true });
 } catch (error) {
   console.log(error);
 }

packages/service/core/dataset/schema.ts

@@ -5,7 +5,7 @@ import {
   DatasetStatusEnum,
   DatasetStatusMap,
   DatasetTypeMap
-} from '@fastgpt/global/core/dataset/constant';
+} from '@fastgpt/global/core/dataset/constants';
 import {
   TeamCollectionName,
   TeamMemberCollectionName
@@ -92,7 +92,7 @@ const DatasetSchema = new Schema({
 });
 
 try {
-  DatasetSchema.index({ userId: 1 });
+  DatasetSchema.index({ teamId: 1 });
 } catch (error) {
   console.log(error);
 }

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

@@ -1,5 +1,15 @@
 import { delay } from '@fastgpt/global/common/system/utils';
 import { MongoDatasetTraining } from './schema';
+import type {
+  PushDatasetDataChunkProps,
+  PushDatasetDataProps,
+  PushDatasetDataResponse
+} from '@fastgpt/global/core/dataset/api.d';
+import { getCollectionWithDataset } from '../controller';
+import { TrainingModeEnum } from '@fastgpt/global/core/dataset/constants';
+import { simpleText } from '@fastgpt/global/common/string/tools';
+import { countPromptTokens } from '@fastgpt/global/common/string/tiktoken';
+import type { VectorModelItemType, LLMModelItemType } from '@fastgpt/global/core/ai/model.d';
 
 export const lockTrainingDataByTeamId = async (teamId: string, retry = 3): Promise<any> => {
   try {
@@ -19,3 +29,165 @@ export const lockTrainingDataByTeamId = async (teamId: string, retry = 3): Promi
     return Promise.reject(error);
   }
 };
+
+export async function pushDataListToTrainingQueue({
+  teamId,
+  tmbId,
+  collectionId,
+  data,
+  prompt,
+  billId,
+  trainingMode = TrainingModeEnum.chunk,
+
+  vectorModelList = [],
+  qaModelList = []
+}: {
+  teamId: string;
+  tmbId: string;
+  vectorModelList: VectorModelItemType[];
+  qaModelList: LLMModelItemType[];
+} & PushDatasetDataProps): Promise<PushDatasetDataResponse> {
+  const {
+    datasetId: { _id: datasetId, vectorModel, agentModel }
+  } = await getCollectionWithDataset(collectionId);
+
+  const checkModelValid = async ({ collectionId }: { collectionId: string }) => {
+    if (!collectionId) return Promise.reject(`CollectionId is empty`);
+
+    if (trainingMode === TrainingModeEnum.chunk) {
+      const vectorModelData = vectorModelList?.find((item) => item.model === vectorModel);
+      if (!vectorModelData) {
+        return Promise.reject(`Model ${vectorModel} is inValid`);
+      }
+
+      return {
+        maxToken: vectorModelData.maxToken * 1.5,
+        model: vectorModelData.model,
+        weight: vectorModelData.weight
+      };
+    }
+
+    if (trainingMode === TrainingModeEnum.qa) {
+      const qaModelData = qaModelList?.find((item) => item.model === agentModel);
+      if (!qaModelData) {
+        return Promise.reject(`Model ${agentModel} is inValid`);
+      }
+      return {
+        maxToken: qaModelData.maxContext * 0.8,
+        model: qaModelData.model,
+        weight: 0
+      };
+    }
+    return Promise.reject(`Training mode "${trainingMode}" is inValid`);
+  };
+
+  const { model, maxToken, weight } = await checkModelValid({
+    collectionId
+  });
+
+  // format q and a, remove empty char
+  data.forEach((item) => {
+    item.q = simpleText(item.q);
+    item.a = simpleText(item.a);
+
+    item.indexes = item.indexes
+      ?.map((index) => {
+        return {
+          ...index,
+          text: simpleText(index.text)
+        };
+      })
+      .filter(Boolean);
+  });
+
+  // filter repeat or equal content
+  const set = new Set();
+  const filterResult: Record<string, PushDatasetDataChunkProps[]> = {
+    success: [],
+    overToken: [],
+    repeat: [],
+    error: []
+  };
+
+  // filter repeat content
+  data.forEach((item) => {
+    if (!item.q) {
+      filterResult.error.push(item);
+      return;
+    }
+
+    const text = item.q + item.a;
+
+    // count q token
+    const token = countPromptTokens(item.q);
+
+    if (token > maxToken) {
+      filterResult.overToken.push(item);
+      return;
+    }
+
+    if (set.has(text)) {
+      console.log('repeat', item);
+      filterResult.repeat.push(item);
+    } else {
+      filterResult.success.push(item);
+      set.add(text);
+    }
+  });
+
+  // insert data to db
+  const insertData = async (dataList: PushDatasetDataChunkProps[], retry = 3): Promise<number> => {
+    try {
+      const results = await MongoDatasetTraining.insertMany(
+        dataList.map((item, i) => ({
+          teamId,
+          tmbId,
+          datasetId,
+          collectionId,
+          billId,
+          mode: trainingMode,
+          prompt,
+          model,
+          q: item.q,
+          a: item.a,
+          chunkIndex: item.chunkIndex ?? i,
+          weight: weight ?? 0,
+          indexes: item.indexes
+        }))
+      );
+      await delay(500);
+      return results.length;
+    } catch (error) {
+      if (retry > 0) {
+        await delay(500);
+        return insertData(dataList, retry - 1);
+      }
+      return Promise.reject(error);
+    }
+  };
+
+  let insertLen = 0;
+  const chunkSize = 50;
+  const chunkList = filterResult.success.reduce(
+    (acc, cur) => {
+      const lastChunk = acc[acc.length - 1];
+      if (lastChunk.length < chunkSize) {
+        lastChunk.push(cur);
+      } else {
+        acc.push([cur]);
+      }
+      return acc;
+    },
+    [[]] as PushDatasetDataChunkProps[][]
+  );
+  for await (const chunks of chunkList) {
+    insertLen += await insertData(chunks);
+  }
+
+  delete filterResult.success;
+
+  return {
+    insertLen,
+    ...filterResult
+  };
+}

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

@@ -2,7 +2,7 @@
 import { connectionMongo, type Model } from '../../../common/mongo';
 const { Schema, model, models } = connectionMongo;
 import { DatasetTrainingSchemaType } from '@fastgpt/global/core/dataset/type';
-import { DatasetDataIndexTypeMap, TrainingTypeMap } from '@fastgpt/global/core/dataset/constant';
+import { DatasetDataIndexTypeMap, TrainingTypeMap } from '@fastgpt/global/core/dataset/constants';
 import { DatasetColCollectionName } from '../collection/schema';
 import { DatasetCollectionName } from '../schema';
 import {
@@ -102,10 +102,11 @@ const TrainingDataSchema = new Schema({
 });
 
 try {
+  // lock training data; delete training data
+  TrainingDataSchema.index({ teamId: 1, collectionId: 1 });
+  // get training data and sort
   TrainingDataSchema.index({ weight: -1 });
   TrainingDataSchema.index({ lockTime: 1 });
-  TrainingDataSchema.index({ datasetId: 1 });
-  TrainingDataSchema.index({ collectionId: 1 });
   TrainingDataSchema.index({ expireAt: 1 }, { expireAfterSeconds: 7 * 24 * 60 });
 } catch (error) {
   console.log(error);

packages/service/package.json

@@ -3,17 +3,17 @@
   "version": "1.0.0",
   "dependencies": {
     "@fastgpt/global": "workspace:*",
+    "axios": "^1.5.1",
+    "cheerio": "1.0.0-rc.12",
     "cookie": "^0.5.0",
+    "dayjs": "^1.11.7",
     "encoding": "^0.1.13",
     "jsonwebtoken": "^9.0.2",
     "mongoose": "^7.0.2",
-    "nanoid": "^4.0.1",
-    "dayjs": "^1.11.7",
-    "next": "13.5.2",
     "multer": "1.4.5-lts.1",
-    "axios": "^1.5.1",
-    "cheerio": "1.0.0-rc.12",
+    "next": "13.5.2",
     "nextjs-cors": "^2.1.2",
+    "node-cron": "^3.0.3",
     "pg": "^8.10.0",
     "tunnel": "^0.0.6"
   },
@@ -21,6 +21,7 @@
     "@types/cookie": "^0.5.2",
     "@types/jsonwebtoken": "^9.0.3",
     "@types/multer": "^1.4.10",
+    "@types/node-cron": "^3.0.11",
     "@types/pg": "^8.6.6",
     "@types/tunnel": "^0.0.4"
   }

packages/service/support/openapi/tools.ts

@@ -1,18 +1,22 @@
 import { MongoOpenApi } from './schema';
 
-export async function updateApiKeyUsedTime(id: string) {
-  await MongoOpenApi.findByIdAndUpdate(id, {
+export function updateApiKeyUsedTime(id: string) {
+  MongoOpenApi.findByIdAndUpdate(id, {
     lastUsedTime: new Date()
+  }).catch((err) => {
+    console.log('update apiKey used time error', err);
   });
 }
 
-export async function updateApiKeyUsage({ apikey, usage }: { apikey: string; usage: number }) {
-  await MongoOpenApi.findOneAndUpdate(
+export function updateApiKeyUsage({ apikey, usage }: { apikey: string; usage: number }) {
+  MongoOpenApi.findOneAndUpdate(
     { apiKey: apikey },
     {
       $inc: {
         usage
       }
     }
-  );
+  ).catch((err) => {
+    console.log('update apiKey usage error', err);
+  });
 }

packages/service/support/outLink/tools.ts

@@ -9,17 +9,15 @@ export const updateOutLinkUsage = async ({
   shareId: string;
   total: number;
 }) => {
-  try {
-    await MongoOutLink.findOneAndUpdate(
-      { shareId },
-      {
-        $inc: { total },
-        lastTime: new Date()
-      }
-    );
-  } catch (err) {
+  MongoOutLink.findOneAndUpdate(
+    { shareId },
+    {
+      $inc: { total },
+      lastTime: new Date()
+    }
+  ).catch((err) => {
     console.log('update shareChat error', err);
-  }
+  });
 };
 
 export const pushResult2Remote = async ({

packages/service/support/permission/auth/app.ts

@@ -6,7 +6,7 @@ import { TeamMemberRoleEnum } from '@fastgpt/global/support/user/team/constant';
 import { parseHeaderCert } from '../controller';
 import { PermissionTypeEnum } from '@fastgpt/global/support/permission/constant';
 import { AppErrEnum } from '@fastgpt/global/common/error/code/app';
-import { getTeamInfoByTmbId } from '../../user/team/controller';
+import { getTmbInfoByTmbId } from '../../user/team/controller';
 
 // 模型使用权校验
 export async function authApp({
@@ -24,7 +24,7 @@ export async function authApp({
 > {
   const result = await parseHeaderCert(props);
   const { teamId, tmbId } = result;
-  const { role } = await getTeamInfoByTmbId({ tmbId });
+  const { role } = await getTmbInfoByTmbId({ tmbId });
 
   const { app, isOwner, canWrite } = await (async () => {
     // get app

packages/service/support/permission/auth/dataset.ts

@@ -13,8 +13,9 @@ import {
 } from '@fastgpt/global/core/dataset/type';
 import { getFileById } from '../../../common/file/gridfs/controller';
 import { BucketNameEnum } from '@fastgpt/global/common/file/constants';
-import { getTeamInfoByTmbId } from '../../user/team/controller';
+import { getTmbInfoByTmbId } from '../../user/team/controller';
 import { CommonErrEnum } from '@fastgpt/global/common/error/code/common';
+import { MongoDatasetCollection } from '../../../core/dataset/collection/schema';
 
 export async function authDatasetByTmbId({
   teamId,
@@ -27,7 +28,7 @@ export async function authDatasetByTmbId({
   datasetId: string;
   per: AuthModeType['per'];
 }) {
-  const { role } = await getTeamInfoByTmbId({ tmbId });
+  const { role } = await getTmbInfoByTmbId({ tmbId });
 
   const { dataset, isOwner, canWrite } = await (async () => {
     const dataset = await MongoDataset.findOne({ _id: datasetId, teamId }).lean();
@@ -107,7 +108,7 @@ export async function authDatasetCollection({
   }
 > {
   const { userId, teamId, tmbId } = await parseHeaderCert(props);
-  const { role } = await getTeamInfoByTmbId({ tmbId });
+  const { role } = await getTmbInfoByTmbId({ tmbId });
 
   const { collection, isOwner, canWrite } = await (async () => {
     const collection = await getCollectionWithDataset(collectionId);
@@ -163,47 +164,40 @@ export async function authDatasetFile({
   }
 > {
   const { userId, teamId, tmbId } = await parseHeaderCert(props);
-  const { role } = await getTeamInfoByTmbId({ tmbId });
 
-  const file = await getFileById({ bucketName: BucketNameEnum.dataset, fileId });
+  const [file, collection] = await Promise.all([
+    getFileById({ bucketName: BucketNameEnum.dataset, fileId }),
+    MongoDatasetCollection.findOne({
+      teamId,
+      fileId
+    })
+  ]);
 
   if (!file) {
     return Promise.reject(CommonErrEnum.fileNotFound);
   }
 
-  if (file.metadata.teamId !== teamId) {
+  if (!collection) {
     return Promise.reject(DatasetErrEnum.unAuthDatasetFile);
   }
 
-  const { dataset } = await authDataset({
-    ...props,
-    datasetId: file.metadata.datasetId,
-    per
-  });
-  const isOwner =
-    role !== TeamMemberRoleEnum.visitor &&
-    (String(dataset.tmbId) === tmbId || role === TeamMemberRoleEnum.owner);
+  // file role = collection role
+  try {
+    const { isOwner, canWrite } = await authDatasetCollection({
+      ...props,
+      collectionId: collection._id,
+      per
+    });
 
-  const canWrite =
-    isOwner ||
-    (role !== TeamMemberRoleEnum.visitor && dataset.permission === PermissionTypeEnum.public);
-
-  if (per === 'r' && !isOwner && dataset.permission !== PermissionTypeEnum.public) {
+    return {
+      userId,
+      teamId,
+      tmbId,
+      file,
+      isOwner,
+      canWrite
+    };
+  } catch (error) {
     return Promise.reject(DatasetErrEnum.unAuthDatasetFile);
   }
-  if (per === 'w' && !canWrite) {
-    return Promise.reject(DatasetErrEnum.unAuthDatasetFile);
-  }
-  if (per === 'owner' && !isOwner) {
-    return Promise.reject(DatasetErrEnum.unAuthDatasetFile);
-  }
-
-  return {
-    userId,
-    teamId,
-    tmbId,
-    file,
-    isOwner,
-    canWrite
-  };
 }

packages/service/support/permission/auth/openapi.ts

@@ -2,7 +2,7 @@ import { AuthResponseType } from '@fastgpt/global/support/permission/type';
 import { AuthModeType } from '../type';
 import { OpenApiSchema } from '@fastgpt/global/support/openapi/type';
 import { parseHeaderCert } from '../controller';
-import { getTeamInfoByTmbId } from '../../user/team/controller';
+import { getTmbInfoByTmbId } from '../../user/team/controller';
 import { MongoOpenApi } from '../../openapi/schema';
 import { OpenApiErrEnum } from '@fastgpt/global/common/error/code/openapi';
 import { TeamMemberRoleEnum } from '@fastgpt/global/support/user/team/constant';
@@ -21,7 +21,7 @@ export async function authOpenApiKeyCrud({
   const result = await parseHeaderCert(props);
   const { tmbId, teamId } = result;
 
-  const { role } = await getTeamInfoByTmbId({ tmbId });
+  const { role } = await getTmbInfoByTmbId({ tmbId });
 
   const { openapi, isOwner, canWrite } = await (async () => {
     const openapi = await MongoOpenApi.findOne({ _id: id, teamId });

packages/service/support/permission/auth/outLink.ts

@@ -9,7 +9,7 @@ import { MongoApp } from '../../../core/app/schema';
 import { OutLinkErrEnum } from '@fastgpt/global/common/error/code/outLink';
 import { PermissionTypeEnum } from '@fastgpt/global/support/permission/constant';
 import { AppErrEnum } from '@fastgpt/global/common/error/code/app';
-import { getTeamInfoByTmbId } from '../../user/team/controller';
+import { getTmbInfoByTmbId } from '../../user/team/controller';
 
 /* crud outlink permission */
 export async function authOutLinkCrud({
@@ -27,7 +27,7 @@ export async function authOutLinkCrud({
   const result = await parseHeaderCert(props);
   const { tmbId, teamId } = result;
 
-  const { role } = await getTeamInfoByTmbId({ tmbId });
+  const { role } = await getTmbInfoByTmbId({ tmbId });
 
   const { app, outLink, isOwner, canWrite } = await (async () => {
     const outLink = await MongoOutLink.findOne({ _id: outLinkId, teamId });

packages/service/support/permission/auth/plugin.ts

@@ -1,7 +1,7 @@
 import { AuthResponseType } from '@fastgpt/global/support/permission/type';
 import { AuthModeType } from '../type';
 import { parseHeaderCert } from '../controller';
-import { getTeamInfoByTmbId } from '../../user/team/controller';
+import { getTmbInfoByTmbId } from '../../user/team/controller';
 import { TeamMemberRoleEnum } from '@fastgpt/global/support/user/team/constant';
 import { MongoPlugin } from '../../../core/plugin/schema';
 import { PluginErrEnum } from '@fastgpt/global/common/error/code/plugin';
@@ -23,7 +23,7 @@ export async function authPluginCrud({
   const result = await parseHeaderCert(props);
   const { tmbId, teamId } = result;
 
-  const { role } = await getTeamInfoByTmbId({ tmbId });
+  const { role } = await getTmbInfoByTmbId({ tmbId });
 
   const { plugin, isOwner, canWrite } = await (async () => {
     const plugin = await MongoPlugin.findOne({ _id: id, teamId });
@@ -73,7 +73,7 @@ export async function authPluginCanUse({
   }
 
   if (source === PluginSourceEnum.personal) {
-    const { role } = await getTeamInfoByTmbId({ tmbId });
+    const { role } = await getTmbInfoByTmbId({ tmbId });
     const plugin = await MongoPlugin.findOne({ _id: pluginId, teamId });
     if (!plugin) {
       return Promise.reject(PluginErrEnum.unExist);

packages/service/support/permission/auth/user.ts

@@ -3,7 +3,7 @@ import { AuthModeType } from '../type';
 import { TeamItemType } from '@fastgpt/global/support/user/team/type';
 import { TeamMemberRoleEnum } from '@fastgpt/global/support/user/team/constant';
 import { parseHeaderCert } from '../controller';
-import { getTeamInfoByTmbId } from '../../user/team/controller';
+import { getTmbInfoByTmbId } from '../../user/team/controller';
 import { UserErrEnum } from '../../../../global/common/error/code/user';
 
 export async function authUserNotVisitor(props: AuthModeType): Promise<
@@ -13,7 +13,7 @@ export async function authUserNotVisitor(props: AuthModeType): Promise<
   }
 > {
   const { userId, teamId, tmbId } = await parseHeaderCert(props);
-  const team = await getTeamInfoByTmbId({ tmbId });
+  const team = await getTmbInfoByTmbId({ tmbId });
 
   if (team.role === TeamMemberRoleEnum.visitor) {
     return Promise.reject(UserErrEnum.binVisitor);
@@ -38,7 +38,7 @@ export async function authUserRole(props: AuthModeType): Promise<
   }
 > {
   const result = await parseHeaderCert(props);
-  const { role: userRole, canWrite } = await getTeamInfoByTmbId({ tmbId: result.tmbId });
+  const { role: userRole, canWrite } = await getTmbInfoByTmbId({ tmbId: result.tmbId });
 
   return {
     ...result,