fix: img compress (#546 )

fix: custom chat title (#534 )
* Fix: Update Custom Chat Title Based on chatId * remove `new:true` option * Update update.ts --------- Co-authored-by: Archer <545436317@qq.com>
2023-12-03 23:56:45 +08:00 · 2023-12-03 21:19:22 +08:00 · 2023-12-03 20:45:57 +08:00 · 2023-11-29 20:45:36 +08:00
143 changed files with 4288 additions and 1517 deletions
--- a/docSite/content/docs/custom-models/chatglm2-m3e.md
+++ b/docSite/content/docs/custom-models/chatglm2-m3e.md
@@ -59,7 +59,7 @@ Authorization 为 sk-aaabbbcccdddeeefffggghhhiiijjjkkk。model 为刚刚在 One

 ## 接入 FastGPT

-修改 config.json 配置文件，在 VectorModels 中加入 chatglm2 和 M3E 模型：
+修改 config.json 配置文件，在 ChatModels 中加入 chatglm2, 在 VectorModels 中加入 M3E 模型：

 ```json
 "ChatModels": [
--- a/docSite/content/docs/installation/upgrading/463.md
+++ b/docSite/content/docs/installation/upgrading/463.md
@@ -0,0 +1,33 @@
+---
+title: 'V4.6.3(需要初始化)'
+description: 'FastGPT V4.6.3'
+icon: 'upgrade'
+draft: false
+toc: true
+weight: 833
+---
+
+## 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/initv463
+
+```bash
+curl --location --request POST 'https://{{host}}/api/admin/initv463' \
+--header 'rootkey: {{rootkey}}' \
+--header 'Content-Type: application/json'
+```
+
+初始化说明：
+1. 初始化Mongo 中 dataset，collection 和 data 的部分字段
+
+## V4.6.3 功能介绍
+
+1. 商业版新增 - web站点同步
+2. 新增 - 集合元数据记录
+3. 优化 - url 读取内容
+4. 优化 - 流读取文件，防止内存溢出
+5. 优化 - 4v模型自动将 url 转 base64，本地也可调试
+6. 优化 - 图片压缩等级
+7. 修复 - 图片压缩失败报错，防止文件读取过程卡死。
--- a/packages/global/common/file/api.d.ts
+++ b/packages/global/common/file/api.d.ts
@@ -0,0 +1,8 @@
+export type UrlFetchParams = {
+  urlList: string[];
+  selector?: string;
+};
+export type UrlFetchResponse = {
+  url: string;
+  content: string;
+}[];
--- a/packages/global/common/file/tools.ts
+++ b/packages/global/common/file/tools.ts
@@ -1,3 +1,8 @@
+import axios from 'axios';
+import { UrlFetchParams, UrlFetchResponse } from './api.d';
+import { htmlToMarkdown } from '../string/markdown';
+import * as cheerio from 'cheerio';
+
 export const formatFileSize = (bytes: number): string => {
  if (bytes === 0) return '0 B';

@@ -7,3 +12,84 @@ export const formatFileSize = (bytes: number): string => {

  return parseFloat((bytes / Math.pow(k, i)).toFixed(2)) + ' ' + sizes[i];
 };
+
+export const cheerioToHtml = ({
+  fetchUrl,
+  $,
+  selector
+}: {
+  fetchUrl: string;
+  $: cheerio.CheerioAPI;
+  selector?: string;
+}) => {
+  // get origin url
+  const originUrl = new URL(fetchUrl).origin;
+
+  // remove i element
+  $('i,script').remove();
+
+  // remove empty a element
+  $('a')
+    .filter((i, el) => {
+      return $(el).text().trim() === '' && $(el).children().length === 0;
+    })
+    .remove();
+
+  // if link,img startWith /, add origin url
+  $('a').each((i, el) => {
+    const href = $(el).attr('href');
+    if (href && href.startsWith('/')) {
+      $(el).attr('href', originUrl + href);
+    }
+  });
+  $('img').each((i, el) => {
+    const src = $(el).attr('src');
+    if (src && src.startsWith('/')) {
+      $(el).attr('src', originUrl + src);
+    }
+  });
+
+  return $(selector || 'body').html();
+};
+export const urlsFetch = async ({
+  urlList,
+  selector
+}: UrlFetchParams): Promise<UrlFetchResponse> => {
+  urlList = urlList.filter((url) => /^(http|https):\/\/[^ "]+$/.test(url));
+
+  const response = (
+    await Promise.all(
+      urlList.map(async (url) => {
+        try {
+          const fetchRes = await axios.get(url, {
+            timeout: 30000
+          });
+
+          const $ = cheerio.load(fetchRes.data);
+
+          const md = htmlToMarkdown(
+            cheerioToHtml({
+              fetchUrl: url,
+              $,
+              selector
+            })
+          );
+
+          return {
+            url,
+            content: md
+          };
+        } catch (error) {
+          console.log(error, 'fetch error');
+
+          return {
+            url,
+            content: ''
+          };
+        }
+      })
+    )
+  ).filter((item) => item.content);
+
+  return response;
+};
--- a/packages/global/common/plugin/types/pluginRes.d.ts
+++ b/packages/global/common/plugin/types/pluginRes.d.ts
@@ -1,4 +0,0 @@
-export type FetchResultItem = {
-  url: string;
-  content: string;
-};
--- a/packages/global/common/string/jieba.ts
+++ b/packages/global/common/string/jieba.ts
--- a/packages/global/common/string/markdown.ts
+++ b/packages/global/common/string/markdown.ts
@@ -0,0 +1,97 @@
+import { simpleText } from './tools';
+import { NodeHtmlMarkdown } from 'node-html-markdown';
+
+/* Delete redundant text in markdown */
+export const simpleMarkdownText = (rawText: string) => {
+  rawText = simpleText(rawText);
+
+  // Remove a line feed from a hyperlink or picture
+  rawText = rawText.replace(/\[([^\]]+)\]\((.+?)\)/g, (match, linkText, url) => {
+    const cleanedLinkText = linkText.replace(/\n/g, ' ').trim();
+
+    if (!url) {
+      return '';
+    }
+
+    return `[${cleanedLinkText}](${url})`;
+  });
+
+  // replace special \.* ……
+  const reg1 = /\\([-.!`_(){}\[\]])/g;
+  if (reg1.test(rawText)) {
+    rawText = rawText.replace(/\\([`!*()+-_\[\]{}\\.])/g, '$1');
+  }
+
+  // replace \\n
+  rawText = rawText.replace(/\\\\n/g, '\\n');
+
+  // Remove headings and code blocks front spaces
+  ['####', '###', '##', '#', '```', '~~~'].forEach((item) => {
+    const reg = new RegExp(`\\n\\s*${item}`, 'g');
+    if (reg.test(rawText)) {
+      rawText = rawText.replace(new RegExp(`\\n\\s*(${item})`, 'g'), '\n$1');
+    }
+  });
+
+  return rawText.trim();
+};
+
+/* html string to markdown */
+export const htmlToMarkdown = (html?: string | null) => {
+  if (!html) return '';
+
+  const surround = (source: string, surroundStr: string) => `${surroundStr}${source}${surroundStr}`;
+
+  const nhm = new NodeHtmlMarkdown(
+    {
+      codeFence: '```',
+      codeBlockStyle: 'fenced',
+      ignore: ['i', 'script']
+    },
+    {
+      code: ({ node, parent, options: { codeFence, codeBlockStyle }, visitor }) => {
+        const isCodeBlock = ['PRE', 'WRAPPED-PRE'].includes(parent?.tagName!);
+
+        if (!isCodeBlock) {
+          return {
+            spaceIfRepeatingChar: true,
+            noEscape: true,
+            postprocess: ({ content }) => {
+              // Find longest occurring sequence of running backticks and add one more (so content is escaped)
+              const delimiter =
+                '`' + (content.match(/`+/g)?.sort((a, b) => b.length - a.length)?.[0] || '');
+              const padding = delimiter.length > 1 ? ' ' : '';
+
+              return surround(surround(content, padding), delimiter);
+            }
+          };
+        }
+
+        /* Handle code block */
+        if (codeBlockStyle === 'fenced') {
+          const language =
+            node.getAttribute('class')?.match(/language-(\S+)/)?.[1] ||
+            parent?.getAttribute('class')?.match(/language-(\S+)/)?.[1] ||
+            '';
+
+          return {
+            noEscape: true,
+            prefix: `${codeFence}${language}\n`,
+            postfix: `\n${codeFence}\n`,
+            childTranslators: visitor.instance.codeBlockTranslators
+          };
+        }
+
+        return {
+          noEscape: true,
+          postprocess: ({ content }) => content.replace(/^/gm, '    '),
+          childTranslators: visitor.instance.codeBlockTranslators
+        };
+      }
+    }
+  );
+
+  const markdown = nhm.translate(html).trim();
+
+  return simpleMarkdownText(markdown);
+};
--- a/packages/global/common/string/textSplitter.ts
+++ b/packages/global/common/string/textSplitter.ts
@@ -15,11 +15,18 @@ export const splitText2Chunks = (props: {
 }): {
  chunks: string[];
  tokens: number;
+  overlapRatio?: number;
 } => {
-  const { text = '', chunkLen, overlapRatio = 0.2 } = props;
+  let { text = '', chunkLen, overlapRatio = 0.2 } = props;
  const splitMarker = 'SPLIT_HERE_SPLIT_HERE';
+  const codeBlockMarker = 'CODE_BLOCK_LINE_MARKER';
  const overlapLen = Math.round(chunkLen * overlapRatio);

+  // replace code block all \n to codeBlockMarker
+  text = text.replace(/(```[\s\S]*?```|~~~[\s\S]*?~~~)/g, function (match) {
+    return match.replace(/\n/g, codeBlockMarker);
+  });
+
  // The larger maxLen is, the next sentence is less likely to trigger splitting
  const stepReges: { reg: RegExp; maxLen: number }[] = [
    { reg: /^(#\s[^\n]+)\n/gm, maxLen: chunkLen * 1.4 },
@@ -27,8 +34,8 @@ export const splitText2Chunks = (props: {
    { reg: /^(###\s[^\n]+)\n/gm, maxLen: chunkLen * 1.4 },
    { reg: /^(####\s[^\n]+)\n/gm, maxLen: chunkLen * 1.4 },

-    { reg: /([\n]{2})/g, maxLen: chunkLen * 1.4 },
-    { reg: /([\n](?![\*\-|>`0-9]))/g, maxLen: chunkLen * 1.8 }, // (?![\*\-|>`0-9]): markdown special char
+    { reg: /([\n](`))/g, maxLen: chunkLen * 4 }, // code block
+    { reg: /([\n](?![\*\-|>0-9]))/g, maxLen: chunkLen * 1.8 }, // (?![\*\-|>`0-9]): markdown special char
    { reg: /([\n])/g, maxLen: chunkLen * 1.4 },

    { reg: /([。]|([a-zA-Z])\.\s)/g, maxLen: chunkLen * 1.4 },
@@ -38,9 +45,15 @@ export const splitText2Chunks = (props: {
    { reg: /([，]|,\s)/g, maxLen: chunkLen * 2 }
  ];

+  // if use markdown title split, Separate record title title
  const getSplitTexts = ({ text, step }: { text: string; step: number }) => {
    if (step >= stepReges.length) {
-      return [text];
+      return [
+        {
+          text,
+          title: ''
+        }
+      ];
    }
    const isMarkdownSplit = step <= 3;
    const { reg } = stepReges[step];
@@ -49,7 +62,17 @@ export const splitText2Chunks = (props: {
      .replace(reg, isMarkdownSplit ? `${splitMarker}$1` : `$1${splitMarker}`)
      .split(`${splitMarker}`)
      .filter((part) => part.trim());
-    return splitTexts;
+
+    return splitTexts
+      .map((text) => {
+        const matchTitle = isMarkdownSplit ? text.match(reg)?.[0] || '' : '';
+
+        return {
+          text: isMarkdownSplit ? text.replace(matchTitle, '') : text,
+          title: matchTitle
+        };
+      })
+      .filter((item) => item.text.trim());
  };

  const getOneTextOverlapText = ({ text, step }: { text: string; step: number }): string => {
@@ -63,7 +86,7 @@ export const splitText2Chunks = (props: {
    let overlayText = '';

    for (let i = splitTexts.length - 1; i >= 0; i--) {
-      const currentText = splitTexts[i];
+      const currentText = splitTexts[i].text;
      const newText = currentText + overlayText;
      const newTextLen = newText.length;

@@ -83,12 +106,16 @@ export const splitText2Chunks = (props: {
  const splitTextRecursively = ({
    text = '',
    step,
-    lastText
+    lastText,
+    mdTitle = ''
  }: {
    text: string;
    step: number;
    lastText: string;
+    mdTitle: string;
  }): string[] => {
+    const isMarkdownSplit = step <= 3;
+
    // mini text
    if (text.length <= chunkLen) {
      return [text];
@@ -102,7 +129,7 @@ export const splitText2Chunks = (props: {
      // use slice-chunkLen to split text
      const chunks: string[] = [];
      for (let i = 0; i < text.length; i += chunkLen - overlapLen) {
-        chunks.push(text.slice(i, i + chunkLen));
+        chunks.push(`${mdTitle}${text.slice(i, i + chunkLen)}`);
      }
      return chunks;
    }
@@ -115,7 +142,10 @@ export const splitText2Chunks = (props: {

    const chunks: string[] = [];
    for (let i = 0; i < splitTexts.length; i++) {
-      const currentText = splitTexts[i];
+      const item = splitTexts[i];
+      const currentTitle = `${mdTitle}${item.title}`;
+
+      const currentText = item.text;
      const currentTextLen = currentText.length;
      const lastTextLen = lastText.length;
      const newText = lastText + currentText;
@@ -125,9 +155,10 @@ export const splitText2Chunks = (props: {
      if (newTextLen > maxLen) {
        // lastText greater minChunkLen, direct push it to chunks, not add to next chunk. (large lastText)
        if (lastTextLen > minChunkLen) {
-          chunks.push(lastText);
+          chunks.push(`${currentTitle}${lastText}`);
          lastText = getOneTextOverlapText({ text: lastText, step }); // next chunk will start with overlayText
          i--;
+
          continue;
        }

@@ -135,11 +166,12 @@ export const splitText2Chunks = (props: {
        const innerChunks = splitTextRecursively({
          text: newText,
          step: step + 1,
-          lastText: ''
+          lastText: '',
+          mdTitle: currentTitle
        });
        const lastChunk = innerChunks[innerChunks.length - 1];
        // last chunk is too small, concat it to lastText
-        if (lastChunk.length < minChunkLen) {
+        if (!isMarkdownSplit && lastChunk.length < minChunkLen) {
          chunks.push(...innerChunks.slice(0, -1));
          lastText = lastChunk;
        } else {
@@ -156,10 +188,11 @@ export const splitText2Chunks = (props: {
      // size less than chunkLen, push text to last chunk. now, text definitely less than maxLen
      lastText = newText;

-      // If the chunk size reaches, add a chunk
-      if (newTextLen >= chunkLen) {
-        chunks.push(lastText);
-        lastText = getOneTextOverlapText({ text: lastText, step });
+      // markdown paragraph block: Direct addition; If the chunk size reaches, add a chunk
+      if (isMarkdownSplit || newTextLen >= chunkLen) {
+        chunks.push(`${currentTitle}${lastText}`);
+
+        lastText = isMarkdownSplit ? '' : getOneTextOverlapText({ text: lastText, step });
      }
    }

@@ -168,7 +201,7 @@ export const splitText2Chunks = (props: {
      if (lastText.length < chunkLen * 0.4) {
        chunks[chunks.length - 1] = chunks[chunks.length - 1] + lastText;
      } else {
-        chunks.push(lastText);
+        chunks.push(`${mdTitle}${lastText}`);
      }
    }

@@ -179,8 +212,9 @@ export const splitText2Chunks = (props: {
    const chunks = splitTextRecursively({
      text,
      step: 0,
-      lastText: ''
-    });
+      lastText: '',
+      mdTitle: ''
+    }).map((chunk) => chunk.replaceAll(codeBlockMarker, '\n')); // restore code block

    const tokens = chunks.reduce((sum, chunk) => sum + countPromptTokens(chunk, 'system'), 0);

--- a/packages/global/common/string/time.ts
+++ b/packages/global/common/string/time.ts
@@ -0,0 +1,3 @@
+import dayjs from 'dayjs';
+
+export const formatTime2YMDHM = (time: Date) => dayjs(time).format('YYYY-MM-DD HH:mm');
--- a/packages/global/common/system/utils.ts
+++ b/packages/global/common/system/utils.ts
@@ -0,0 +1,6 @@
+export const delay = (ms: number) =>
+  new Promise((resolve) => {
+    setTimeout(() => {
+      resolve('');
+    }, ms);
+  });
--- a/packages/global/core/app/utils.ts
+++ b/packages/global/core/app/utils.ts
@@ -77,7 +77,7 @@ export const appModules2Form = ({
      );
      defaultAppForm.aiSettings.quotePrompt = findInputValueByKey(
        module.inputs,
-        ModuleInputKeyEnum.aiChatQuoteTemplate
+        ModuleInputKeyEnum.aiChatQuotePrompt
      );
    } else if (module.flowType === FlowNodeTypeEnum.datasetSearchNode) {
      defaultAppForm.dataset.datasets = findInputValueByKey(
--- a/packages/global/core/chat/constants.ts
+++ b/packages/global/core/chat/constants.ts
@@ -5,7 +5,6 @@ export enum ChatRoleEnum {
  Function = 'Function',
  Tool = 'Tool'
 }
-
 export const ChatRoleMap = {
  [ChatRoleEnum.System]: {
    name: '系统提示词'
@@ -30,7 +29,6 @@ export enum ChatSourceEnum {
  share = 'share',
  api = 'api'
 }
-
 export const ChatSourceMap = {
  [ChatSourceEnum.test]: {
    name: 'chat.logs.test'
--- a/packages/global/core/chat/type.d.ts
+++ b/packages/global/core/chat/type.d.ts
@@ -4,6 +4,7 @@ import { ChatRoleEnum, ChatSourceEnum } from './constants';
 import { FlowNodeTypeEnum } from '../module/node/constant';
 import { ModuleOutputKeyEnum } from '../module/constants';
 import { AppSchema } from '../app/type';
+import { DatasetSearchModeEnum } from '../dataset/constant';

 export type ChatSchema = {
  _id: string;
@@ -94,6 +95,7 @@ export type moduleDispatchResType = {
  // dataset search
  similarity?: number;
  limit?: number;
+  searchMode?: `${DatasetSearchModeEnum}`;

  // cq
  cqList?: ClassifyQuestionAgentItemType[];
--- a/packages/global/core/dataset/api.d.ts
+++ b/packages/global/core/dataset/api.d.ts
@@ -1,8 +1,32 @@
-import { DatasetDataIndexItemType } from './type';
+import { DatasetDataIndexItemType, DatasetSchemaType } from './type';
+import { DatasetCollectionTrainingModeEnum, DatasetCollectionTypeEnum } from './constant';
+import type { LLMModelItemType } from '../ai/model.d';

 /* ================= dataset ===================== */
+export type DatasetUpdateBody = {
+  id: string;
+  parentId?: string;
+  tags?: string[];
+  name?: string;
+  avatar?: string;
+  permission?: DatasetSchemaType['permission'];
+  agentModel?: LLMModelItemType;
+  websiteConfig?: DatasetSchemaType['websiteConfig'];
+  status?: DatasetSchemaType['status'];
+};

 /* ================= collection ===================== */
+export type CreateDatasetCollectionParams = {
+  datasetId: string;
+  parentId?: string;
+  name: string;
+  type: `${DatasetCollectionTypeEnum}`;
+  trainingType?: `${DatasetCollectionTrainingModeEnum}`;
+  chunkSize?: number;
+  fileId?: string;
+  rawLink?: string;
+  metadata?: Record<string, any>;
+};

 /* ================= data ===================== */
 export type PgSearchRawType = {
@@ -18,3 +42,8 @@ export type PushDatasetDataChunkProps = {
  a?: string; // bonus content
  indexes?: Omit<DatasetDataIndexItemType, 'dataId'>[];
 };
+
+export type PostWebsiteSyncParams = {
+  datasetId: string;
+  billId: string;
+};
--- a/packages/global/core/dataset/constant.ts
+++ b/packages/global/core/dataset/constant.ts
@@ -1,41 +1,81 @@
 export const PgDatasetTableName = 'modeldata';

+/* ------------ dataset -------------- */
 export enum DatasetTypeEnum {
  folder = 'folder',
-  dataset = 'dataset'
+  dataset = 'dataset',
+  websiteDataset = 'websiteDataset' // depp link
 }
-
 export const DatasetTypeMap = {
  [DatasetTypeEnum.folder]: {
-    name: 'folder'
+    icon: 'core/dataset/folderDataset',
+    label: 'core.dataset.Folder Dataset',
+    collectionLabel: 'common.Folder'
  },
  [DatasetTypeEnum.dataset]: {
-    name: 'dataset'
+    icon: 'core/dataset/commonDataset',
+    label: 'core.dataset.Common Dataset',
+    collectionLabel: 'common.File'
+  },
+  [DatasetTypeEnum.websiteDataset]: {
+    icon: 'core/dataset/websiteDataset',
+    label: 'core.dataset.Website Dataset',
+    collectionLabel: 'common.Website'
  }
 };

+export enum DatasetStatusEnum {
+  active = 'active',
+  syncing = 'syncing'
+}
+export const DatasetStatusMap = {
+  [DatasetStatusEnum.active]: {
+    label: 'core.dataset.status.active'
+  },
+  [DatasetStatusEnum.syncing]: {
+    label: 'core.dataset.status.syncing'
+  }
+};
+
+/* ------------ collection -------------- */
 export enum DatasetCollectionTypeEnum {
-  file = 'file',
  folder = 'folder',
-  link = 'link',
+  file = 'file',
+  link = 'link', // one link
  virtual = 'virtual'
 }
-
 export const DatasetCollectionTypeMap = {
-  [DatasetCollectionTypeEnum.file]: {
-    name: 'dataset.file'
-  },
  [DatasetCollectionTypeEnum.folder]: {
-    name: 'dataset.folder'
+    name: 'core.dataset.folder'
+  },
+  [DatasetCollectionTypeEnum.file]: {
+    name: 'core.dataset.file'
  },
  [DatasetCollectionTypeEnum.link]: {
-    name: 'dataset.link'
+    name: 'core.dataset.link'
  },
  [DatasetCollectionTypeEnum.virtual]: {
-    name: 'dataset.Virtual File'
+    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'
  }
 };

+/* ------------ data -------------- */
 export enum DatasetDataIndexTypeEnum {
  chunk = 'chunk',
  qa = 'qa',
@@ -61,31 +101,22 @@ export const DatasetDataIndexTypeMap = {
  }
 };

+/* ------------ training -------------- */
 export enum TrainingModeEnum {
-  'chunk' = 'chunk',
-  'qa' = 'qa'
-  // 'hypothetical' = 'hypothetical',
-  // 'summary' = 'summary',
-  // 'multipleIndex' = 'multipleIndex'
+  chunk = 'chunk',
+  qa = 'qa'
 }
+
 export const TrainingTypeMap = {
  [TrainingModeEnum.chunk]: {
-    name: 'chunk'
+    label: 'core.dataset.training.type chunk'
  },
  [TrainingModeEnum.qa]: {
-    name: 'qa'
+    label: 'core.dataset.training.type qa'
  }
-  // [TrainingModeEnum.hypothetical]: {
-  //   name: 'hypothetical'
-  // },
-  // [TrainingModeEnum.summary]: {
-  //   name: 'summary'
-  // },
-  // [TrainingModeEnum.multipleIndex]: {
-  //   name: 'multipleIndex'
-  // }
 };

+/* ------------ search -------------- */
 export enum DatasetSearchModeEnum {
  embedding = 'embedding',
  embeddingReRank = 'embeddingReRank',
--- a/packages/global/core/dataset/controller.d.ts
+++ b/packages/global/core/dataset/controller.d.ts
@@ -5,6 +5,7 @@ export type CreateDatasetDataProps = {
  tmbId: string;
  datasetId: string;
  collectionId: string;
+  chunkIndex?: number;
  q: string;
  a?: string;
  indexes?: Omit<DatasetDataIndexItemType, 'dataId'>[];
--- a/packages/global/core/dataset/type.d.ts
+++ b/packages/global/core/dataset/type.d.ts
@@ -4,6 +4,7 @@ import { PushDatasetDataChunkProps } from './api';
 import {
  DatasetCollectionTypeEnum,
  DatasetDataIndexTypeEnum,
+  DatasetStatusEnum,
  DatasetTypeEnum,
  TrainingModeEnum
 } from './constant';
@@ -20,26 +21,31 @@ export type DatasetSchemaType = {
  name: string;
  vectorModel: string;
  agentModel: string;
-  tags: string[];
+  intro: string;
  type: `${DatasetTypeEnum}`;
+  status: `${DatasetStatusEnum}`;
  permission: `${PermissionTypeEnum}`;
+  websiteConfig?: {
+    url: string;
+    selector: string;
+  };
 };

 export type DatasetCollectionSchemaType = {
  _id: string;
-  userId: string;
  teamId: string;
  tmbId: string;
  datasetId: string;
  parentId?: string;
  name: string;
  type: `${DatasetCollectionTypeEnum}`;
+  createTime: Date;
  updateTime: Date;
-  metadata: {
-    fileId?: string;
-    rawLink?: string;
-    pgCollectionId?: string;
-  };
+  trainingType: `${TrainingModeEnum}`;
+  chunkSize: number;
+  fileId?: string;
+  rawLink?: string;
+  metadata?: Record<string, any>;
 };

 export type DatasetDataIndexItemType = {
@@ -57,6 +63,8 @@ export type DatasetDataSchemaType = {
  collectionId: string;
  datasetId: string;
  collectionId: string;
+  chunkIndex: number;
+  updateTime: Date;
  q: string; // large chunks or question
  a: string; // answer or custom content
  fullTextToken: string;
@@ -78,6 +86,7 @@ export type DatasetTrainingSchemaType = {
  prompt: string;
  q: string;
  a: string;
+  chunkIndex: number;
  indexes: Omit<DatasetDataIndexItemType, 'dataId'>[];
 };

@@ -89,6 +98,18 @@ export type DatasetDataWithCollectionType = Omit<DatasetDataSchemaType, 'collect
 };

 /* ================= dataset ===================== */
+export type DatasetListItemType = {
+  _id: string;
+  parentId: string;
+  avatar: string;
+  name: string;
+  intro: string;
+  type: `${DatasetTypeEnum}`;
+  isOwner: boolean;
+  canWrite: boolean;
+  permission: `${PermissionTypeEnum}`;
+  vectorModel: VectorModelItemType;
+};
 export type DatasetItemType = Omit<DatasetSchemaType, 'vectorModel' | 'agentModel'> & {
  vectorModel: VectorModelItemType;
  agentModel: LLMModelItemType;
@@ -101,6 +122,7 @@ export type DatasetCollectionItemType = CollectionWithDatasetType & {
  canWrite: boolean;
  sourceName: string;
  sourceId?: string;
+  file?: DatasetFileSchema;
 };

 /* ================= data ===================== */
--- a/packages/global/package.json
+++ b/packages/global/package.json
@@ -3,13 +3,16 @@
  "version": "1.0.0",
  "dependencies": {
    "axios": "^1.5.1",
-    "timezones-list": "^3.0.2",
+    "cheerio": "1.0.0-rc.12",
    "dayjs": "^1.11.7",
    "encoding": "^0.1.13",
+    "js-tiktoken": "^1.0.7",
+    "node-html-markdown": "^1.3.0",
    "openai": "^4.16.1",
-    "js-tiktoken": "^1.0.7"
+    "timezones-list": "^3.0.2"
  },
  "devDependencies": {
-    "@types/node": "^20.8.5"
+    "@types/node": "^20.8.5",
+    "@types/turndown": "^5.0.4"
  }
 }
--- a/packages/global/support/wallet/bill/tools.ts
+++ b/packages/global/support/wallet/bill/tools.ts
@@ -1,6 +1,7 @@
 /* bill common  */
 import { PRICE_SCALE } from './constants';
-import { BillItemType, BillSchema } from './type';
+import { BillSourceEnum } from './constants';
+import { AuthUserTypeEnum } from '../../permission/constant';

 /**
 * dataset price / PRICE_SCALE = real price
@@ -8,3 +9,15 @@ import { BillItemType, BillSchema } from './type';
 export const formatPrice = (val = 0, multiple = 1) => {
  return Number(((val / PRICE_SCALE) * multiple).toFixed(10));
 };
+
+export const getBillSourceByAuthType = ({
+  shareId,
+  authType
+}: {
+  shareId?: string;
+  authType?: `${AuthUserTypeEnum}`;
+}) => {
+  if (shareId) return BillSourceEnum.shareLink;
+  if (authType === AuthUserTypeEnum.apikey) return BillSourceEnum.api;
+  return BillSourceEnum.fastgpt;
+};
--- a/packages/service/common/api/plusRequest.ts
+++ b/packages/service/common/api/plusRequest.ts
@@ -101,18 +101,18 @@ export function request(url: string, data: any, config: ConfigType, method: Meth
 * @param {Object} config
 * @returns
 */
-export function GET<T>(url: string, params = {}, config: ConfigType = {}): Promise<T> {
+export function GET<T = undefined>(url: string, params = {}, config: ConfigType = {}): Promise<T> {
  return request(url, params, config, 'GET');
 }

-export function POST<T>(url: string, data = {}, config: ConfigType = {}): Promise<T> {
+export function POST<T = undefined>(url: string, data = {}, config: ConfigType = {}): Promise<T> {
  return request(url, data, config, 'POST');
 }

-export function PUT<T>(url: string, data = {}, config: ConfigType = {}): Promise<T> {
+export function PUT<T = undefined>(url: string, data = {}, config: ConfigType = {}): Promise<T> {
  return request(url, data, config, 'PUT');
 }

-export function DELETE<T>(url: string, data = {}, config: ConfigType = {}): Promise<T> {
+export function DELETE<T = undefined>(url: string, data = {}, config: ConfigType = {}): Promise<T> {
  return request(url, data, config, 'DELETE');
 }
--- a/packages/service/common/file/gridfs/controller.ts
+++ b/packages/service/common/file/gridfs/controller.ts
@@ -89,7 +89,7 @@ export async function delFileById({
  return true;
 }

-export async function getDownloadBuf({
+export async function getDownloadStream({
  bucketName,
  fileId
 }: {
@@ -98,14 +98,5 @@ export async function getDownloadBuf({
 }) {
  const bucket = getGridBucket(bucketName);

-  const stream = bucket.openDownloadStream(new Types.ObjectId(fileId));
-
-  const buf: Buffer = await new Promise((resolve, reject) => {
-    const buffers: Buffer[] = [];
-    stream.on('data', (data) => buffers.push(data));
-    stream.on('error', reject);
-    stream.on('end', () => resolve(Buffer.concat(buffers)));
-  });
-
-  return buf;
+  return bucket.openDownloadStream(new Types.ObjectId(fileId));
 }
--- a/packages/service/core/chat/utils.ts
+++ b/packages/service/core/chat/utils.ts
@@ -3,6 +3,7 @@ import { ChatRoleEnum, IMG_BLOCK_KEY } from '@fastgpt/global/core/chat/constants
 import { countMessagesTokens, countPromptTokens } from '@fastgpt/global/common/string/tiktoken';
 import { adaptRole_Chat2Message } from '@fastgpt/global/core/chat/adapt';
 import type { ChatCompletionContentPart } from '@fastgpt/global/core/ai/type.d';
+import axios from 'axios';

 /* slice chat context by tokens */
 export function ChatContextFilter({
@@ -81,11 +82,13 @@ export function ChatContextFilter({
            }
        ]
 */
-export function formatStr2ChatContent(str: string) {
+export async function formatStr2ChatContent(str: string) {
  const content: ChatCompletionContentPart[] = [];
  let lastIndex = 0;
  const regex = new RegExp(`\`\`\`(${IMG_BLOCK_KEY})\\n([\\s\\S]*?)\`\`\``, 'g');

+  const imgKey: 'image_url' = 'image_url';
+
  let match;

  while ((match = regex.exec(str)) !== null) {
@@ -115,7 +118,7 @@ export function formatStr2ChatContent(str: string) {

      content.push(
        ...jsonLines.map((item) => ({
-          type: 'image_url' as any,
+          type: imgKey,
          image_url: {
            url: item.src
          }
@@ -148,5 +151,18 @@ export function formatStr2ChatContent(str: string) {
  if (content.length === 1 && content[0].type === 'text') {
    return content[0].text;
  }
+
+  if (!content) return null;
+  // load img to base64
+  for await (const item of content) {
+    if (item.type === imgKey && item[imgKey]?.url) {
+      const response = await axios.get(item[imgKey].url, {
+        responseType: 'arraybuffer'
+      });
+      const base64 = Buffer.from(response.data).toString('base64');
+      item[imgKey].url = `data:${response.headers['content-type']};base64,${base64}`;
+    }
+  }
+
  return content ? content : null;
 }
--- a/packages/service/core/dataset/collection/controller.ts
+++ b/packages/service/core/dataset/collection/controller.ts
@@ -0,0 +1,73 @@
+import {
+  DatasetCollectionTrainingModeEnum,
+  DatasetCollectionTypeEnum
+} from '@fastgpt/global/core/dataset/constant';
+import type { CreateDatasetCollectionParams } from '@fastgpt/global/core/dataset/api.d';
+import { MongoDatasetCollection } from './schema';
+
+export async function createOneCollection({
+  name,
+  parentId,
+  datasetId,
+  type,
+  trainingType = DatasetCollectionTrainingModeEnum.manual,
+  chunkSize = 0,
+  fileId,
+  rawLink,
+  teamId,
+  tmbId,
+  metadata = {}
+}: CreateDatasetCollectionParams & { teamId: string; tmbId: string }) {
+  const { _id } = await MongoDatasetCollection.create({
+    name,
+    teamId,
+    tmbId,
+    datasetId,
+    parentId: parentId || null,
+    type,
+    trainingType,
+    chunkSize,
+    fileId,
+    rawLink,
+    metadata
+  });
+
+  // create default collection
+  if (type === DatasetCollectionTypeEnum.folder) {
+    await createDefaultCollection({
+      datasetId,
+      parentId: _id,
+      teamId,
+      tmbId
+    });
+  }
+
+  return _id;
+}
+
+// create default collection
+export function createDefaultCollection({
+  name = '手动录入',
+  datasetId,
+  parentId,
+  teamId,
+  tmbId
+}: {
+  name?: '手动录入' | '手动标注';
+  datasetId: string;
+  parentId?: string;
+  teamId: string;
+  tmbId: string;
+}) {
+  return MongoDatasetCollection.create({
+    name,
+    teamId,
+    tmbId,
+    datasetId,
+    parentId,
+    type: DatasetCollectionTypeEnum.virtual,
+    trainingType: DatasetCollectionTrainingModeEnum.manual,
+    chunkSize: 0,
+    updateTime: new Date('2099')
+  });
+}
--- a/packages/service/core/dataset/collection/schema.ts
+++ b/packages/service/core/dataset/collection/schema.ts
@@ -1,7 +1,10 @@
 import { connectionMongo, type Model } from '../../../common/mongo';
 const { Schema, model, models } = connectionMongo;
 import { DatasetCollectionSchemaType } from '@fastgpt/global/core/dataset/type.d';
-import { DatasetCollectionTypeMap } from '@fastgpt/global/core/dataset/constant';
+import {
+  DatasetCollectionTrainingTypeMap,
+  DatasetCollectionTypeMap
+} from '@fastgpt/global/core/dataset/constant';
 import { DatasetCollectionName } from '../schema';
 import {
  TeamCollectionName,
@@ -36,33 +39,42 @@ const DatasetCollectionSchema = new Schema({
    ref: DatasetCollectionName,
    required: true
  },
-  name: {
-    type: String,
-    required: true
-  },
  type: {
    type: String,
    enum: Object.keys(DatasetCollectionTypeMap),
    required: true
  },
+
+  name: {
+    type: String,
+    required: true
+  },
+  createTime: {
+    type: Date,
+    default: () => new Date()
+  },
  updateTime: {
    type: Date,
    default: () => new Date()
  },
+  trainingType: {
+    type: String,
+    enum: Object.keys(DatasetCollectionTrainingTypeMap),
+    required: true
+  },
+  chunkSize: {
+    type: Number,
+    required: true
+  },
+  fileId: {
+    type: Schema.Types.ObjectId,
+    ref: 'dataset.files'
+  },
+  rawLink: {
+    type: String
+  },
  metadata: {
-    type: {
-      fileId: {
-        type: Schema.Types.ObjectId,
-        ref: 'dataset.files'
-      },
-      rawLink: {
-        type: String
-      },
-      // 451 初始化
-      pgCollectionId: {
-        type: String
-      }
-    },
+    type: Object,
    default: {}
  }
 });
--- a/packages/service/core/dataset/data/controller.ts
+++ b/packages/service/core/dataset/data/controller.ts
@@ -0,0 +1,75 @@
+import { MongoDatasetData } from './schema';
+import { deletePgDataById } from './pg';
+import { MongoDatasetTraining } from '../training/schema';
+import { delFileById } from '../../../common/file/gridfs/controller';
+import { BucketNameEnum } from '@fastgpt/global/common/file/constants';
+import { MongoDatasetCollection } from '../collection/schema';
+import { delDatasetFiles } from '../file/controller';
+import { delay } from '@fastgpt/global/common/system/utils';
+
+/* 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: { $in: datasetIds }
+  });
+
+  // delete related files
+  await Promise.all(datasetIds.map((id) => delDatasetFiles({ datasetId: id })));
+
+  await delay(1000);
+
+  // delete pg data
+  await deletePgDataById(`dataset_id IN ('${datasetIds.join("','")}')`);
+  // delete dataset.datas
+  await MongoDatasetData.deleteMany({ datasetId: { $in: datasetIds } });
+
+  // delete collections
+  await MongoDatasetCollection.deleteMany({
+    datasetId: { $in: datasetIds }
+  });
+}
+/**
+ * delete all data by collectionIds
+ */
+export async function delCollectionRelevantData({
+  collectionIds,
+  fileIds
+}: {
+  collectionIds: string[];
+  fileIds: string[];
+}) {
+  collectionIds = collectionIds.map((item) => String(item));
+  const filterFileIds = fileIds.filter(Boolean);
+
+  // delete training data
+  await MongoDatasetTraining.deleteMany({
+    collectionId: { $in: collectionIds }
+  });
+
+  // delete file
+  await Promise.all(
+    filterFileIds.map((fileId) => {
+      return delFileById({
+        bucketName: BucketNameEnum.dataset,
+        fileId
+      });
+    })
+  );
+
+  await delay(1000);
+
+  // delete pg data
+  await deletePgDataById(`collection_id IN ('${collectionIds.join("','")}')`);
+  // delete dataset.datas
+  await MongoDatasetData.deleteMany({ collectionId: { $in: collectionIds } });
+}
+/**
+ * delete one data by mongoDataId
+ */
+export async function delDatasetDataByDataId(mongoDataId: string) {
+  await deletePgDataById(['data_id', mongoDataId]);
+  await MongoDatasetData.findByIdAndDelete(mongoDataId);
+}
--- a/packages/service/core/dataset/data/pg.ts
+++ b/packages/service/core/dataset/data/pg.ts
@@ -0,0 +1,28 @@
+import { PgDatasetTableName } from '@fastgpt/global/core/dataset/constant';
+import { delay } from '@fastgpt/global/common/system/utils';
+import { PgClient } from '../../../common/pg';
+
+export async function deletePgDataById(
+  where: ['id' | 'dataset_id' | 'collection_id' | 'data_id', string] | string
+) {
+  let retry = 2;
+  async function deleteData(): Promise<any> {
+    try {
+      await PgClient.delete(PgDatasetTableName, {
+        where: [where]
+      });
+    } catch (error) {
+      if (--retry < 0) {
+        return Promise.reject(error);
+      }
+      await delay(500);
+      return deleteData();
+    }
+  }
+
+  await deleteData();
+
+  return {
+    tokenLen: 0
+  };
+}
--- a/packages/service/core/dataset/data/schema.ts
+++ b/packages/service/core/dataset/data/schema.ts
@@ -70,6 +70,18 @@ const DatasetDataSchema = new Schema({
      }
    ],
    default: []
+  },
+  // metadata
+  updateTime: {
+    type: Date,
+    default: () => new Date()
+  },
+  chunkIndex: {
+    type: Number,
+    default: 0
+  },
+  inited: {
+    type: Boolean
  }
 });

@@ -79,7 +91,7 @@ try {
  DatasetDataSchema.index({ collectionId: 1 });
  // full text index
  DatasetDataSchema.index({ datasetId: 1, fullTextToken: 'text' });
-  DatasetDataSchema.index({ fullTextToken: 1 });
+  DatasetDataSchema.index({ inited: 1 });
 } catch (error) {
  console.log(error);
 }
--- a/packages/service/core/dataset/schema.ts
+++ b/packages/service/core/dataset/schema.ts
@@ -1,7 +1,11 @@
 import { connectionMongo, type Model } from '../../common/mongo';
 const { Schema, model, models } = connectionMongo;
 import { DatasetSchemaType } from '@fastgpt/global/core/dataset/type.d';
-import { DatasetTypeMap } from '@fastgpt/global/core/dataset/constant';
+import {
+  DatasetStatusEnum,
+  DatasetStatusMap,
+  DatasetTypeMap
+} from '@fastgpt/global/core/dataset/constant';
 import {
  TeamCollectionName,
  TeamMemberCollectionName
@@ -31,9 +35,16 @@ const DatasetSchema = new Schema({
    ref: TeamMemberCollectionName,
    required: true
  },
-  updateTime: {
-    type: Date,
-    default: () => new Date()
+  type: {
+    type: String,
+    enum: Object.keys(DatasetTypeMap),
+    required: true,
+    default: 'dataset'
+  },
+  status: {
+    type: String,
+    enum: Object.keys(DatasetStatusMap),
+    default: DatasetStatusEnum.active
  },
  avatar: {
    type: String,
@@ -43,6 +54,10 @@ const DatasetSchema = new Schema({
    type: String,
    required: true
  },
+  updateTime: {
+    type: Date,
+    default: () => new Date()
+  },
  vectorModel: {
    type: String,
    required: true,
@@ -53,24 +68,26 @@ const DatasetSchema = new Schema({
    required: true,
    default: 'gpt-3.5-turbo-16k'
  },
-  type: {
+  intro: {
    type: String,
-    enum: Object.keys(DatasetTypeMap),
-    required: true,
-    default: 'dataset'
-  },
-  tags: {
-    type: [String],
-    default: [],
-    set(val: string | string[]) {
-      if (Array.isArray(val)) return val;
-      return val.split(' ').filter((item) => item);
-    }
+    default: ''
  },
  permission: {
    type: String,
    enum: Object.keys(PermissionTypeMap),
    default: PermissionTypeEnum.private
+  },
+  websiteConfig: {
+    type: {
+      url: {
+        type: String,
+        required: true
+      },
+      selector: {
+        type: String,
+        default: 'body'
+      }
+    }
  }
 });

--- a/packages/service/core/dataset/training/schema.ts
+++ b/packages/service/core/dataset/training/schema.ts
@@ -75,6 +75,10 @@ const TrainingDataSchema = new Schema({
    type: String,
    default: ''
  },
+  chunkIndex: {
+    type: Number,
+    default: 0
+  },
  indexes: {
    type: [
      {
--- a/pnpm-lock.yaml
+++ b/pnpm-lock.yaml
@@ -1,4 +1,4 @@
-lockfileVersion: '6.0'
+lockfileVersion: '6.1'

 settings:
  autoInstallPeers: true
@@ -45,6 +45,9 @@ importers:
      axios:
        specifier: ^1.5.1
        version: registry.npmmirror.com/axios@1.5.1
+      cheerio:
+        specifier: 1.0.0-rc.12
+        version: registry.npmmirror.com/cheerio@1.0.0-rc.12
      dayjs:
        specifier: ^1.11.7
        version: registry.npmmirror.com/dayjs@1.11.10
@@ -54,6 +57,9 @@ importers:
      js-tiktoken:
        specifier: ^1.0.7
        version: registry.npmmirror.com/js-tiktoken@1.0.7
+      node-html-markdown:
+        specifier: ^1.3.0
+        version: registry.npmmirror.com/node-html-markdown@1.3.0
      openai:
        specifier: ^4.16.1
        version: registry.npmmirror.com/openai@4.16.1(encoding@0.1.13)
@@ -64,6 +70,9 @@ importers:
      '@types/node':
        specifier: ^20.8.5
        version: registry.npmmirror.com/@types/node@20.8.7
+      '@types/turndown':
+        specifier: ^5.0.4
+        version: registry.npmmirror.com/@types/turndown@5.0.4

  packages/service:
    dependencies:
@@ -161,9 +170,6 @@ importers:
      '@fastgpt/web':
        specifier: workspace:*
        version: link:../../packages/web
-      '@mozilla/readability':
-        specifier: ^0.4.4
-        version: registry.npmmirror.com/@mozilla/readability@0.4.4
      '@node-rs/jieba':
        specifier: ^1.7.2
        version: registry.npmmirror.com/@node-rs/jieba@1.7.2
@@ -209,9 +215,6 @@ importers:
      jschardet:
        specifier: ^3.0.0
        version: registry.npmmirror.com/jschardet@3.0.0
-      jsdom:
-        specifier: ^22.1.0
-        version: registry.npmmirror.com/jsdom@22.1.0
      jsonwebtoken:
        specifier: ^9.0.2
        version: registry.npmmirror.com/jsonwebtoken@9.0.2
@@ -300,9 +303,6 @@ importers:
      '@types/js-cookie':
        specifier: ^3.0.3
        version: registry.npmmirror.com/@types/js-cookie@3.0.5
-      '@types/jsdom':
-        specifier: ^21.1.1
-        version: registry.npmmirror.com/@types/jsdom@21.1.4
      '@types/jsonwebtoken':
        specifier: ^9.0.3
        version: registry.npmmirror.com/@types/jsonwebtoken@9.0.4
@@ -3575,13 +3575,6 @@ packages:
    dev: false
    optional: true

-  registry.npmmirror.com/@mozilla/readability@0.4.4:
-    resolution: {integrity: sha512-MCgZyANpJ6msfvVMi6+A0UAsvZj//4OHREYUB9f2087uXHVoU+H+SWhuihvb1beKpM323bReQPRio0WNk2+V6g==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/@mozilla/readability/-/readability-0.4.4.tgz}
-    name: '@mozilla/readability'
-    version: 0.4.4
-    engines: {node: '>=14.0.0'}
-    dev: false
-
  registry.npmmirror.com/@next/env@13.5.2:
    resolution: {integrity: sha512-dUseBIQVax+XtdJPzhwww4GetTjlkRSsXeQnisIJWBaHsnxYcN2RGzsPHi58D6qnkATjnhuAtQTJmR1hKYQQPg==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/@next/env/-/env-13.5.2.tgz}
    name: '@next/env'
@@ -4248,13 +4241,6 @@ packages:
      use-sync-external-store: registry.npmmirror.com/use-sync-external-store@1.2.0(react@18.2.0)
    dev: false

-  registry.npmmirror.com/@tootallnate/once@2.0.0:
-    resolution: {integrity: sha512-XCuKFP5PS55gnMVu3dty8KPatLqUoy/ZYzDzAGCQ8JNFCkLXzmI7vNHCR+XpbZaMWQK/vQubr7PkYq8g470J/A==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/@tootallnate/once/-/once-2.0.0.tgz}
-    name: '@tootallnate/once'
-    version: 2.0.0
-    engines: {node: '>= 10'}
-    dev: false
-
  registry.npmmirror.com/@trysound/sax@0.2.0:
    resolution: {integrity: sha512-L7z9BgrNEcYyUYtF+HaEfiS5ebkh9jXqbszz7pC0hRBPaatV0XjSD3+eHrpqFemQfgwiFF0QPIarnIihIDn7OA==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/@trysound/sax/-/sax-0.2.0.tgz}
    name: '@trysound/sax'
@@ -4618,16 +4604,6 @@ packages:
    version: 3.0.5
    dev: true

-  registry.npmmirror.com/@types/jsdom@21.1.4:
-    resolution: {integrity: sha512-NzAMLEV0KQ4cBaDx3Ls8VfJUElyDUm1xrtYRmcMK0gF8L5xYbujFVaQlJ50yinQ/d47j2rEP1XUzkiYrw4YRFA==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/@types/jsdom/-/jsdom-21.1.4.tgz}
-    name: '@types/jsdom'
-    version: 21.1.4
-    dependencies:
-      '@types/node': registry.npmmirror.com/@types/node@20.8.7
-      '@types/tough-cookie': registry.npmmirror.com/@types/tough-cookie@4.0.4
-      parse5: registry.npmmirror.com/parse5@7.1.2
-    dev: true
-
  registry.npmmirror.com/@types/json5@0.0.29:
    resolution: {integrity: sha512-dRLjCWHYg4oaA77cxO64oO+7JwCwnIzkZPdrrC71jQmQtlhM556pwKo5bUzqvZndkVbeFLIIi+9TC40JNF5hNQ==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/@types/json5/-/json5-0.0.29.tgz}
    name: '@types/json5'
@@ -4826,12 +4802,6 @@ packages:
      '@types/node': registry.npmmirror.com/@types/node@20.8.7
    dev: true

-  registry.npmmirror.com/@types/tough-cookie@4.0.4:
-    resolution: {integrity: sha512-95Sfz4nvMAb0Nl9DTxN3j64adfwfbBPEYq14VN7zT5J5O2M9V6iZMIIQU1U+pJyl9agHYHNCqhCXgyEtIRRa5A==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/@types/tough-cookie/-/tough-cookie-4.0.4.tgz}
-    name: '@types/tough-cookie'
-    version: 4.0.4
-    dev: true
-
  registry.npmmirror.com/@types/triple-beam@1.3.4:
    resolution: {integrity: sha512-HlJjF3wxV4R2VQkFpKe0YqJLilYNgtRtsqqZtby7RkVsSs+i+vbyzjtUwpFEdUCKcrGzCiEJE7F/0mKjh0sunA==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/@types/triple-beam/-/triple-beam-1.3.4.tgz}
    name: '@types/triple-beam'
@@ -4846,6 +4816,12 @@ packages:
      '@types/node': registry.npmmirror.com/@types/node@20.8.7
    dev: true

+  registry.npmmirror.com/@types/turndown@5.0.4:
+    resolution: {integrity: sha512-28GI33lCCkU4SGH1GvjDhFgOVr+Tym4PXGBIU1buJUa6xQolniPArtUT+kv42RR2N9MsMLInkr904Aq+ESHBJg==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/@types/turndown/-/turndown-5.0.4.tgz}
+    name: '@types/turndown'
+    version: 5.0.4
+    dev: true
+
  registry.npmmirror.com/@types/unist@2.0.9:
    resolution: {integrity: sha512-zC0iXxAv1C1ERURduJueYzkzZ2zaGyc+P2c95hgkikHPr3z8EdUZOlgEQ5X0DRmwDZn+hekycQnoeiiRVrmilQ==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/@types/unist/-/unist-2.0.9.tgz}
    name: '@types/unist'
@@ -4967,12 +4943,6 @@ packages:
      '@zag-js/dom-query': registry.npmmirror.com/@zag-js/dom-query@0.16.0
    dev: false

-  registry.npmmirror.com/abab@2.0.6:
-    resolution: {integrity: sha512-j2afSsaIENvHZN2B8GOpF566vZ5WVk5opAiMTvWgaQT8DkbOqsTfvNAvHoRGU2zzP8cPoqys+xHTRDWW8L+/BA==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/abab/-/abab-2.0.6.tgz}
-    name: abab
-    version: 2.0.6
-    dev: false
-
  registry.npmmirror.com/abort-controller@3.0.0:
    resolution: {integrity: sha512-h8lQ8tacZYnR3vNQTgibj+tODHI5/+l06Au2Pcriv/Gmet0eaj4TwWH41sO9wnHDiQsEj19q0drzdWdeAHtweg==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/abort-controller/-/abort-controller-3.0.0.tgz}
    name: abort-controller
@@ -5001,17 +4971,6 @@ packages:
    hasBin: true
    dev: true

-  registry.npmmirror.com/agent-base@6.0.2:
-    resolution: {integrity: sha512-RZNwNclF7+MS/8bDg70amg32dyeZGZxiDuQmZxKLAlQjr3jGyLx+4Kkk58UO7D2QdgFIQCovuSuZESne6RG6XQ==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/agent-base/-/agent-base-6.0.2.tgz}
-    name: agent-base
-    version: 6.0.2
-    engines: {node: '>= 6.0.0'}
-    dependencies:
-      debug: registry.npmmirror.com/debug@4.3.4
-    transitivePeerDependencies:
-      - supports-color
-    dev: false
-
  registry.npmmirror.com/agentkeepalive@4.5.0:
    resolution: {integrity: sha512-5GG/5IbQQpC9FpkRGsSvZI5QYeSCzlJHdpBQntCsuTOxhKD8lqKhrleg2Yi7yvMIf82Ycmmqln9U8V9qwEiJew==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/agentkeepalive/-/agentkeepalive-4.5.0.tgz}
    name: agentkeepalive
@@ -5435,7 +5394,6 @@ packages:
    resolution: {integrity: sha512-JZOSA7Mo9sNGB8+UjSgzdLtokWAky1zbztM3WRLCbZ70/3cTANmQmOdR7y2g+J0e2WXywy1yS468tY+IruqEww==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/boolbase/-/boolbase-1.0.0.tgz}
    name: boolbase
    version: 1.0.0
-    dev: true

  registry.npmmirror.com/brace-expansion@1.1.11:
    resolution: {integrity: sha512-iCuPHDFgrHX7H2vEI/5xpz07zSHB00TpugqhmYtVmMO6518mCuRMoOYFldEBl0g187ufozdaHgWKcYFb61qGiA==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/brace-expansion/-/brace-expansion-1.1.11.tgz}
@@ -5720,6 +5678,34 @@ packages:
      get-func-name: registry.npmmirror.com/get-func-name@2.0.2
    dev: true

+  registry.npmmirror.com/cheerio-select@2.1.0:
+    resolution: {integrity: sha512-9v9kG0LvzrlcungtnJtpGNxY+fzECQKhK4EGJX2vByejiMX84MFNQw4UxPJl3bFbTMw+Dfs37XaIkCwTZfLh4g==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/cheerio-select/-/cheerio-select-2.1.0.tgz}
+    name: cheerio-select
+    version: 2.1.0
+    dependencies:
+      boolbase: registry.npmmirror.com/boolbase@1.0.0
+      css-select: registry.npmmirror.com/css-select@5.1.0
+      css-what: registry.npmmirror.com/css-what@6.1.0
+      domelementtype: registry.npmmirror.com/domelementtype@2.3.0
+      domhandler: registry.npmmirror.com/domhandler@5.0.3
+      domutils: registry.npmmirror.com/domutils@3.1.0
+    dev: false
+
+  registry.npmmirror.com/cheerio@1.0.0-rc.12:
+    resolution: {integrity: sha512-VqR8m68vM46BNnuZ5NtnGBKIE/DfN0cRIzg9n40EIq9NOv90ayxLBXA8fXC5gquFRGJSTRqBq25Jt2ECLR431Q==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/cheerio/-/cheerio-1.0.0-rc.12.tgz}
+    name: cheerio
+    version: 1.0.0-rc.12
+    engines: {node: '>= 6'}
+    dependencies:
+      cheerio-select: registry.npmmirror.com/cheerio-select@2.1.0
+      dom-serializer: registry.npmmirror.com/dom-serializer@2.0.0
+      domhandler: registry.npmmirror.com/domhandler@5.0.3
+      domutils: registry.npmmirror.com/domutils@3.1.0
+      htmlparser2: registry.npmmirror.com/htmlparser2@8.0.2
+      parse5: registry.npmmirror.com/parse5@7.1.2
+      parse5-htmlparser2-tree-adapter: registry.npmmirror.com/parse5-htmlparser2-tree-adapter@7.0.0
+    dev: false
+
  registry.npmmirror.com/chokidar@3.5.3:
    resolution: {integrity: sha512-Dr3sfKRP6oTcjf2JmUmFJfeVMvXBdegxB0iVQ5eb2V10uFJUCAS8OByZdVAyVb8xXNz3GjjTgj9kLWsZTqE6kw==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/chokidar/-/chokidar-3.5.3.tgz}
    name: chokidar
@@ -6108,6 +6094,18 @@ packages:
      nth-check: registry.npmmirror.com/nth-check@2.1.1
    dev: true

+  registry.npmmirror.com/css-select@5.1.0:
+    resolution: {integrity: sha512-nwoRF1rvRRnnCqqY7updORDsuqKzqYJ28+oSMaJMMgOauh3fvwHqMS7EZpIPqK8GL+g9mKxF1vP/ZjSeNjEVHg==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/css-select/-/css-select-5.1.0.tgz}
+    name: css-select
+    version: 5.1.0
+    dependencies:
+      boolbase: registry.npmmirror.com/boolbase@1.0.0
+      css-what: registry.npmmirror.com/css-what@6.1.0
+      domhandler: registry.npmmirror.com/domhandler@5.0.3
+      domutils: registry.npmmirror.com/domutils@3.1.0
+      nth-check: registry.npmmirror.com/nth-check@2.1.1
+    dev: false
+
  registry.npmmirror.com/css-tree@1.1.3:
    resolution: {integrity: sha512-tRpdppF7TRazZrjJ6v3stzv93qxRcSsFmW6cX0Zm2NVKpxE1WV1HblnghVv9TreireHkqI/VDEsfolRF1p6y7Q==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/css-tree/-/css-tree-1.1.3.tgz}
    name: css-tree
@@ -6123,7 +6121,6 @@ packages:
    name: css-what
    version: 6.1.0
    engines: {node: '>= 6'}
-    dev: true

  registry.npmmirror.com/csso@4.2.0:
    resolution: {integrity: sha512-wvlcdIbf6pwKEk7vHj8/Bkc0B4ylXZruLvOgs9doS5eOsOpuodOV2zJChSpkp+pRpYQLQMeF04nr3Z68Sta9jA==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/csso/-/csso-4.2.0.tgz}
@@ -6134,15 +6131,6 @@ packages:
      css-tree: registry.npmmirror.com/css-tree@1.1.3
    dev: true

-  registry.npmmirror.com/cssstyle@3.0.0:
-    resolution: {integrity: sha512-N4u2ABATi3Qplzf0hWbVCdjenim8F3ojEXpBDF5hBpjzW182MjNGLqfmQ0SkSPeQ+V86ZXgeH8aXj6kayd4jgg==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/cssstyle/-/cssstyle-3.0.0.tgz}
-    name: cssstyle
-    version: 3.0.0
-    engines: {node: '>=14'}
-    dependencies:
-      rrweb-cssom: registry.npmmirror.com/rrweb-cssom@0.6.0
-    dev: false
-
  registry.npmmirror.com/csstype@3.1.2:
    resolution: {integrity: sha512-I7K1Uu0MBPzaFKg4nI5Q7Vs2t+3gWWW648spaF+Rg7pI9ds18Ugn+lvg4SHczUdKlHI5LWBXyqfS8+DufyBsgQ==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/csstype/-/csstype-3.1.2.tgz}
    name: csstype
@@ -6539,17 +6527,6 @@ packages:
    version: 1.0.8
    dev: true

-  registry.npmmirror.com/data-urls@4.0.0:
-    resolution: {integrity: sha512-/mMTei/JXPqvFqQtfyTowxmJVwr2PVAeCcDxyFf6LhoOu/09TX2OX3kb2wzi4DMXcfj4OItwDOnhl5oziPnT6g==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/data-urls/-/data-urls-4.0.0.tgz}
-    name: data-urls
-    version: 4.0.0
-    engines: {node: '>=14'}
-    dependencies:
-      abab: registry.npmmirror.com/abab@2.0.6
-      whatwg-mimetype: registry.npmmirror.com/whatwg-mimetype@3.0.0
-      whatwg-url: registry.npmmirror.com/whatwg-url@12.0.1
-    dev: false
-
  registry.npmmirror.com/date-fns@2.30.0:
    resolution: {integrity: sha512-fnULvOpxnC5/Vg3NCiWelDsLiUc9bRwAPs/+LfTLNvetFCtCTN+yQz15C/fs4AwX1R9K5GLtLfn8QW+dWisaAw==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/date-fns/-/date-fns-2.30.0.tgz}
    name: date-fns
@@ -6591,12 +6568,6 @@ packages:
    dependencies:
      ms: registry.npmmirror.com/ms@2.1.2

-  registry.npmmirror.com/decimal.js@10.4.3:
-    resolution: {integrity: sha512-VBBaLc1MgL5XpzgIP7ny5Z6Nx3UrRkIViUkPUdtl9aya5amy3De1gsUUSB1g3+3sExYNjCAsAznmukyxCb1GRA==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/decimal.js/-/decimal.js-10.4.3.tgz}
-    name: decimal.js
-    version: 10.4.3
-    dev: false
-
  registry.npmmirror.com/decode-named-character-reference@1.0.2:
    resolution: {integrity: sha512-O8x12RzrUF8xyVcY0KJowWsmaJxQbmy0/EtnNtHRpsOcT7dFk5W598coHqBVpmWo1oQQfsCqfCmkZN5DJrZVdg==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/decode-named-character-reference/-/decode-named-character-reference-1.0.2.tgz}
    name: decode-named-character-reference
@@ -6769,6 +6740,16 @@ packages:
      entities: registry.npmmirror.com/entities@2.2.0
    dev: true

+  registry.npmmirror.com/dom-serializer@2.0.0:
+    resolution: {integrity: sha512-wIkAryiqt/nV5EQKqQpo3SToSOV9J0DnbJqwK7Wv/Trc92zIAYZ4FlMu+JPFW1DfGFt81ZTCGgDEabffXeLyJg==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/dom-serializer/-/dom-serializer-2.0.0.tgz}
+    name: dom-serializer
+    version: 2.0.0
+    dependencies:
+      domelementtype: registry.npmmirror.com/domelementtype@2.3.0
+      domhandler: registry.npmmirror.com/domhandler@5.0.3
+      entities: registry.npmmirror.com/entities@4.5.0
+    dev: false
+
  registry.npmmirror.com/domain-browser@4.23.0:
    resolution: {integrity: sha512-ArzcM/II1wCCujdCNyQjXrAFwS4mrLh4C7DZWlaI8mdh7h3BfKdNd3bKXITfl2PT9FtfQqaGvhi1vPRQPimjGA==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/domain-browser/-/domain-browser-4.23.0.tgz}
    name: domain-browser
@@ -6780,16 +6761,6 @@ packages:
    resolution: {integrity: sha512-OLETBj6w0OsagBwdXnPdN0cnMfF9opN69co+7ZrbfPGrdpPVNBUj02spi6B1N7wChLQiPn4CSH/zJvXw56gmHw==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/domelementtype/-/domelementtype-2.3.0.tgz}
    name: domelementtype
    version: 2.3.0
-    dev: true
-
-  registry.npmmirror.com/domexception@4.0.0:
-    resolution: {integrity: sha512-A2is4PLG+eeSfoTMA95/s4pvAoSo2mKtiM5jlHkAVewmiO8ISFTFKZjH7UAM1Atli/OT/7JHOrJRJiMKUZKYBw==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/domexception/-/domexception-4.0.0.tgz}
-    name: domexception
-    version: 4.0.0
-    engines: {node: '>=12'}
-    dependencies:
-      webidl-conversions: registry.npmmirror.com/webidl-conversions@7.0.0
-    dev: false

  registry.npmmirror.com/domhandler@4.3.1:
    resolution: {integrity: sha512-GrwoxYN+uWlzO8uhUXRl0P+kHE4GtVPfYzVLcUxPL7KNdHKj66vvlhiweIHqYYXWlw+T8iLMp42Lm67ghw4WMQ==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/domhandler/-/domhandler-4.3.1.tgz}
@@ -6800,6 +6771,15 @@ packages:
      domelementtype: registry.npmmirror.com/domelementtype@2.3.0
    dev: true

+  registry.npmmirror.com/domhandler@5.0.3:
+    resolution: {integrity: sha512-cgwlv/1iFQiFnU96XXgROh8xTeetsnJiDsTc7TYCLFd9+/WNkIqPTxiM/8pSd8VIrhXGTf1Ny1q1hquVqDJB5w==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/domhandler/-/domhandler-5.0.3.tgz}
+    name: domhandler
+    version: 5.0.3
+    engines: {node: '>= 4'}
+    dependencies:
+      domelementtype: registry.npmmirror.com/domelementtype@2.3.0
+    dev: false
+
  registry.npmmirror.com/dompurify@3.0.6:
    resolution: {integrity: sha512-ilkD8YEnnGh1zJ240uJsW7AzE+2qpbOUYjacomn3AvJ6J4JhKGSZ2nh4wUIXPZrEPppaCLx5jFe8T89Rk8tQ7w==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/dompurify/-/dompurify-3.0.6.tgz}
    name: dompurify
@@ -6816,6 +6796,16 @@ packages:
      domhandler: registry.npmmirror.com/domhandler@4.3.1
    dev: true

+  registry.npmmirror.com/domutils@3.1.0:
+    resolution: {integrity: sha512-H78uMmQtI2AhgDJjWeQmHwJJ2bLPD3GMmO7Zja/ZZh84wkm+4ut+IUnUdRa8uCGX88DiVx1j6FRe1XfxEgjEZA==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/domutils/-/domutils-3.1.0.tgz}
+    name: domutils
+    version: 3.1.0
+    dependencies:
+      dom-serializer: registry.npmmirror.com/dom-serializer@2.0.0
+      domelementtype: registry.npmmirror.com/domelementtype@2.3.0
+      domhandler: registry.npmmirror.com/domhandler@5.0.3
+    dev: false
+
  registry.npmmirror.com/downloadjs@1.4.7:
    resolution: {integrity: sha512-LN1gO7+u9xjU5oEScGFKvXhYf7Y/empUIIEAGBs1LzUq/rg5duiDrkuH5A2lQGd5jfMOb9X9usDa2oVXwJ0U/Q==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/downloadjs/-/downloadjs-1.4.7.tgz}
    name: downloadjs
@@ -8285,6 +8275,13 @@ packages:
      space-separated-tokens: registry.npmmirror.com/space-separated-tokens@2.0.2
    dev: false

+  registry.npmmirror.com/he@1.2.0:
+    resolution: {integrity: sha512-F/1DnUGPopORZi0ni+CvrCgHQ5FyEAHRLSApuYWMmrbSwoN2Mn/7k+Gl38gJnR7yyDZk6WLXwiGod1JOWNDKGw==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/he/-/he-1.2.0.tgz}
+    name: he
+    version: 1.2.0
+    hasBin: true
+    dev: false
+
  registry.npmmirror.com/heap@0.2.7:
    resolution: {integrity: sha512-2bsegYkkHO+h/9MGbn6KWcE45cHZgPANo5LXF7EvWdT0yT2EguSVO1nDgU5c8+ZOPwp2vMNa7YFsJhVcDR9Sdg==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/heap/-/heap-0.2.7.tgz}
    name: heap
@@ -8321,15 +8318,6 @@ packages:
    dependencies:
      react-is: registry.npmmirror.com/react-is@16.13.1

-  registry.npmmirror.com/html-encoding-sniffer@3.0.0:
-    resolution: {integrity: sha512-oWv4T4yJ52iKrufjnyZPkrN0CH3QnrUqdB6In1g5Fe1mia8GmF36gnfNySxoZtxD5+NmYw1EElVXiBk93UeskA==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/html-encoding-sniffer/-/html-encoding-sniffer-3.0.0.tgz}
-    name: html-encoding-sniffer
-    version: 3.0.0
-    engines: {node: '>=12'}
-    dependencies:
-      whatwg-encoding: registry.npmmirror.com/whatwg-encoding@2.0.0
-    dev: false
-
  registry.npmmirror.com/html-parse-stringify@3.0.1:
    resolution: {integrity: sha512-KknJ50kTInJ7qIScF3jeaFRpMpE8/lfiTdzf/twXyPBLAGrLRTmkz3AdTnKeh40X8k9L2fdYwEp/42WGXIRGcg==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/html-parse-stringify/-/html-parse-stringify-3.0.1.tgz}
    name: html-parse-stringify
@@ -8337,17 +8325,15 @@ packages:
    dependencies:
      void-elements: registry.npmmirror.com/void-elements@3.1.0

-  registry.npmmirror.com/http-proxy-agent@5.0.0:
-    resolution: {integrity: sha512-n2hY8YdoRE1i7r6M0w9DIw5GgZN0G25P8zLCRQ8rjXtTU3vsNFBI/vWK/UIeE6g5MUUz6avwAPXmL6Fy9D/90w==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/http-proxy-agent/-/http-proxy-agent-5.0.0.tgz}
-    name: http-proxy-agent
-    version: 5.0.0
-    engines: {node: '>= 6'}
+  registry.npmmirror.com/htmlparser2@8.0.2:
+    resolution: {integrity: sha512-GYdjWKDkbRLkZ5geuHs5NY1puJ+PXwP7+fHPRz06Eirsb9ugf6d8kkXav6ADhcODhFFPMIXyxkxSuMf3D6NCFA==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/htmlparser2/-/htmlparser2-8.0.2.tgz}
+    name: htmlparser2
+    version: 8.0.2
    dependencies:
-      '@tootallnate/once': registry.npmmirror.com/@tootallnate/once@2.0.0
-      agent-base: registry.npmmirror.com/agent-base@6.0.2
-      debug: registry.npmmirror.com/debug@4.3.4
-    transitivePeerDependencies:
-      - supports-color
+      domelementtype: registry.npmmirror.com/domelementtype@2.3.0
+      domhandler: registry.npmmirror.com/domhandler@5.0.3
+      domutils: registry.npmmirror.com/domutils@3.1.0
+      entities: registry.npmmirror.com/entities@4.5.0
    dev: false

  registry.npmmirror.com/https-browserify@1.0.0:
@@ -8356,18 +8342,6 @@ packages:
    version: 1.0.0
    dev: true

-  registry.npmmirror.com/https-proxy-agent@5.0.1:
-    resolution: {integrity: sha512-dFcAjpTQFgoLMzC2VwU+C/CbS7uRL0lWmxDITmqm7C+7F0Odmj6s9l6alZc6AELXhrnggM2CeWSXHGOdX2YtwA==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/https-proxy-agent/-/https-proxy-agent-5.0.1.tgz}
-    name: https-proxy-agent
-    version: 5.0.1
-    engines: {node: '>= 6'}
-    dependencies:
-      agent-base: registry.npmmirror.com/agent-base@6.0.2
-      debug: registry.npmmirror.com/debug@4.3.4
-    transitivePeerDependencies:
-      - supports-color
-    dev: false
-
  registry.npmmirror.com/human-signals@4.3.1:
    resolution: {integrity: sha512-nZXjEF2nbo7lIw3mgYjItAfgQXog3OjJogSbKa2CQIIvSGWcKgeJnQlNXip6NglNzYH45nSRiEVimMvYL8DDqQ==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/human-signals/-/human-signals-4.3.1.tgz}
    name: human-signals
@@ -8743,12 +8717,6 @@ packages:
    engines: {node: '>=12'}
    dev: false

-  registry.npmmirror.com/is-potential-custom-element-name@1.0.1:
-    resolution: {integrity: sha512-bCYeRA2rVibKZd+s2625gGnGF/t7DSqDs4dP7CrLA1m7jKWz6pps0LpYLJN8Q64HtmPKJ1hrN3nzPNKFEKOUiQ==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/is-potential-custom-element-name/-/is-potential-custom-element-name-1.0.1.tgz}
-    name: is-potential-custom-element-name
-    version: 1.0.1
-    dev: false
-
  registry.npmmirror.com/is-regex@1.1.4:
    resolution: {integrity: sha512-kvRdxDsxZjhzUX07ZnLydzS1TU/TJlTUHHY4YLL87e37oUA49DfkLqgy+VjFocowy29cKvcSiu+kIv728jTTVg==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/is-regex/-/is-regex-1.1.4.tgz}
    name: is-regex
@@ -8921,46 +8889,6 @@ packages:
    engines: {node: '>=0.1.90'}
    dev: false

-  registry.npmmirror.com/jsdom@22.1.0:
-    resolution: {integrity: sha512-/9AVW7xNbsBv6GfWho4TTNjEo9fe6Zhf9O7s0Fhhr3u+awPwAJMKwAMXnkk5vBxflqLW9hTHX/0cs+P3gW+cQw==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/jsdom/-/jsdom-22.1.0.tgz}
-    name: jsdom
-    version: 22.1.0
-    engines: {node: '>=16'}
-    peerDependencies:
-      canvas: ^2.5.0
-    peerDependenciesMeta:
-      canvas:
-        optional: true
-    dependencies:
-      abab: registry.npmmirror.com/abab@2.0.6
-      cssstyle: registry.npmmirror.com/cssstyle@3.0.0
-      data-urls: registry.npmmirror.com/data-urls@4.0.0
-      decimal.js: registry.npmmirror.com/decimal.js@10.4.3
-      domexception: registry.npmmirror.com/domexception@4.0.0
-      form-data: registry.npmmirror.com/form-data@4.0.0
-      html-encoding-sniffer: registry.npmmirror.com/html-encoding-sniffer@3.0.0
-      http-proxy-agent: registry.npmmirror.com/http-proxy-agent@5.0.0
-      https-proxy-agent: registry.npmmirror.com/https-proxy-agent@5.0.1
-      is-potential-custom-element-name: registry.npmmirror.com/is-potential-custom-element-name@1.0.1
-      nwsapi: registry.npmmirror.com/nwsapi@2.2.7
-      parse5: registry.npmmirror.com/parse5@7.1.2
-      rrweb-cssom: registry.npmmirror.com/rrweb-cssom@0.6.0
-      saxes: registry.npmmirror.com/saxes@6.0.0
-      symbol-tree: registry.npmmirror.com/symbol-tree@3.2.4
-      tough-cookie: registry.npmmirror.com/tough-cookie@4.1.3
-      w3c-xmlserializer: registry.npmmirror.com/w3c-xmlserializer@4.0.0
-      webidl-conversions: registry.npmmirror.com/webidl-conversions@7.0.0
-      whatwg-encoding: registry.npmmirror.com/whatwg-encoding@2.0.0
-      whatwg-mimetype: registry.npmmirror.com/whatwg-mimetype@3.0.0
-      whatwg-url: registry.npmmirror.com/whatwg-url@12.0.1
-      ws: registry.npmmirror.com/ws@8.14.2
-      xml-name-validator: registry.npmmirror.com/xml-name-validator@4.0.0
-    transitivePeerDependencies:
-      - bufferutil
-      - supports-color
-      - utf-8-validate
-    dev: false
-
  registry.npmmirror.com/jsesc@0.5.0:
    resolution: {integrity: sha512-uZz5UnB7u4T9LvwmFqXii7pZSouaRPorGs5who1Ip7VO0wxanFvBL7GkM6dTHlgX+jhBApRetaWpnDabOeTcnA==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/jsesc/-/jsesc-0.5.0.tgz}
    name: jsesc
@@ -10343,6 +10271,24 @@ packages:
      whatwg-url: registry.npmmirror.com/whatwg-url@5.0.0
    dev: false

+  registry.npmmirror.com/node-html-markdown@1.3.0:
+    resolution: {integrity: sha512-OeFi3QwC/cPjvVKZ114tzzu+YoR+v9UXW5RwSXGUqGb0qCl0DvP406tzdL7SFn8pZrMyzXoisfG2zcuF9+zw4g==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/node-html-markdown/-/node-html-markdown-1.3.0.tgz}
+    name: node-html-markdown
+    version: 1.3.0
+    engines: {node: '>=10.0.0'}
+    dependencies:
+      node-html-parser: registry.npmmirror.com/node-html-parser@6.1.11
+    dev: false
+
+  registry.npmmirror.com/node-html-parser@6.1.11:
+    resolution: {integrity: sha512-FAgwwZ6h0DSDWxfD0Iq1tsDcBCxdJB1nXpLPPxX8YyVWzbfCjKWEzaynF4gZZ/8hziUmp7ZSaKylcn0iKhufUQ==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/node-html-parser/-/node-html-parser-6.1.11.tgz}
+    name: node-html-parser
+    version: 6.1.11
+    dependencies:
+      css-select: registry.npmmirror.com/css-select@5.1.0
+      he: registry.npmmirror.com/he@1.2.0
+    dev: false
+
  registry.npmmirror.com/node-releases@2.0.13:
    resolution: {integrity: sha512-uYr7J37ae/ORWdZeQ1xxMJe3NtdmqMC/JZK+geofDrkLUApKRHPd18/TxtBOJ4A0/+uUIliorNrfYV6s1b02eQ==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/node-releases/-/node-releases-2.0.13.tgz}
    name: node-releases
@@ -10416,13 +10362,6 @@ packages:
    version: 2.1.1
    dependencies:
      boolbase: registry.npmmirror.com/boolbase@1.0.0
-    dev: true
-
-  registry.npmmirror.com/nwsapi@2.2.7:
-    resolution: {integrity: sha512-ub5E4+FBPKwAZx0UwIQOjYWGHTEq5sPqHQNRN8Z9e4A7u3Tj1weLJsL59yH9vmvqEtBHaOmT6cYQKIZOxp35FQ==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/nwsapi/-/nwsapi-2.2.7.tgz}
-    name: nwsapi
-    version: 2.2.7
-    dev: false

  registry.npmmirror.com/object-assign@4.1.1:
    resolution: {integrity: sha512-rJgTQnkUnH1sFw8yT6VSU3zD3sWmu6sZhIseY8VX+GRu3P6F7Fu+JNDoXfklElbLJSnc3FUQHVe4cU5hj+BcUg==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/object-assign/-/object-assign-4.1.1.tgz}
@@ -10703,12 +10642,22 @@ packages:
      json-parse-even-better-errors: registry.npmmirror.com/json-parse-even-better-errors@2.3.1
      lines-and-columns: registry.npmmirror.com/lines-and-columns@1.2.4

+  registry.npmmirror.com/parse5-htmlparser2-tree-adapter@7.0.0:
+    resolution: {integrity: sha512-B77tOZrqqfUfnVcOrUvfdLbz4pu4RopLD/4vmu3HUPswwTA8OH0EMW9BlWR2B0RCoiZRAHEUu7IxeP1Pd1UU+g==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/parse5-htmlparser2-tree-adapter/-/parse5-htmlparser2-tree-adapter-7.0.0.tgz}
+    name: parse5-htmlparser2-tree-adapter
+    version: 7.0.0
+    dependencies:
+      domhandler: registry.npmmirror.com/domhandler@5.0.3
+      parse5: registry.npmmirror.com/parse5@7.1.2
+    dev: false
+
  registry.npmmirror.com/parse5@7.1.2:
    resolution: {integrity: sha512-Czj1WaSVpaoj0wbhMzLmWD69anp2WH7FXMB9n1Sy8/ZFF9jolSQVMu1Ij5WIyGmcBmhk7EOndpO4mIpihVqAXw==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/parse5/-/parse5-7.1.2.tgz}
    name: parse5
    version: 7.1.2
    dependencies:
      entities: registry.npmmirror.com/entities@4.5.0
+    dev: false

  registry.npmmirror.com/path-browserify@1.0.1:
    resolution: {integrity: sha512-b7uo2UCUOYZcnF/3ID0lulOJi/bafxa1xPe7ZPsammBSpjSWQkjNxlt635YGS2MiR9GjvuXCtz2emr3jbsz98g==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/path-browserify/-/path-browserify-1.0.1.tgz}
@@ -11060,12 +11009,6 @@ packages:
    version: 1.1.0
    dev: false

-  registry.npmmirror.com/psl@1.9.0:
-    resolution: {integrity: sha512-E/ZsdU4HLs/68gYzgGTkMicWTLPdAftJLfJFlLUAAKZGkStNU72sZjT66SnMDVOfOWY/YAoiD7Jxa9iHvngcag==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/psl/-/psl-1.9.0.tgz}
-    name: psl
-    version: 1.9.0
-    dev: false
-
  registry.npmmirror.com/public-encrypt@4.0.3:
    resolution: {integrity: sha512-zVpa8oKZSz5bTMTFClc1fQOnyyEzpl5ozpi1B5YcvBrdohMjH2rfsBtyXcuNuwjsDIXmBYlF2N5FlJYhR29t8Q==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/public-encrypt/-/public-encrypt-4.0.3.tgz}
    name: public-encrypt
@@ -11106,12 +11049,6 @@ packages:
    engines: {node: '>=0.4.x'}
    dev: true

-  registry.npmmirror.com/querystringify@2.2.0:
-    resolution: {integrity: sha512-FIqgj2EUvTa7R50u0rGsyTftzjYmv/a3hO345bZNrqabNqjtgiDMgmo4mkUjd+nzU5oF3dClKqFIPUKybUyqoQ==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/querystringify/-/querystringify-2.2.0.tgz}
-    name: querystringify
-    version: 2.2.0
-    dev: false
-
  registry.npmmirror.com/queue-microtask@1.2.3:
    resolution: {integrity: sha512-NuaNSa6flKT5JaSYQzJok04JzTL1CA6aGhv5rfLW3PgqA+M2ChpZQnAC8h8i4ZFkBS8X5RqkDBHA7r4hej3K9A==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/queue-microtask/-/queue-microtask-1.2.3.tgz}
    name: queue-microtask
@@ -11628,12 +11565,6 @@ packages:
    engines: {node: '>=4'}
    dev: false

-  registry.npmmirror.com/requires-port@1.0.0:
-    resolution: {integrity: sha512-KigOCHcocU3XODJxsu8i/j8T9tzT4adHiecwORRQ0ZZFcp7ahwXuRU1m+yuO90C5ZUyGeGfocHDI14M3L3yDAQ==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/requires-port/-/requires-port-1.0.0.tgz}
-    name: requires-port
-    version: 1.0.0
-    dev: false
-
  registry.npmmirror.com/resolve-from@4.0.0:
    resolution: {integrity: sha512-pb/MYmXstAkysRFx8piNI1tGFNQIFA3vkE3Gq4EuA1dF6gHp/+vgZqsCGJapvy8N3Q+4o7FwvquPJcnZ7RYy4g==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/resolve-from/-/resolve-from-4.0.0.tgz}
    name: resolve-from
@@ -11724,12 +11655,6 @@ packages:
      fsevents: registry.npmmirror.com/fsevents@2.3.3
    dev: true

-  registry.npmmirror.com/rrweb-cssom@0.6.0:
-    resolution: {integrity: sha512-APM0Gt1KoXBz0iIkkdB/kfvGOwC4UuJFeG/c+yV7wSc7q96cG/kJ0HiYCnzivD9SB53cLV1MlHFNfOuPaadYSw==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/rrweb-cssom/-/rrweb-cssom-0.6.0.tgz}
-    name: rrweb-cssom
-    version: 0.6.0
-    dev: false
-
  registry.npmmirror.com/run-parallel@1.2.0:
    resolution: {integrity: sha512-5l4VyZR86LZ/lDxZTR6jqL8AFE2S0IFLMP26AbjsLVADxHdhB/c0GUsH+y39UfCi3dzz8OlQuPmnaJOMoDHQBA==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/run-parallel/-/run-parallel-1.2.0.tgz}
    name: run-parallel
@@ -11820,15 +11745,6 @@ packages:
      immutable: registry.npmmirror.com/immutable@4.3.4
      source-map-js: registry.npmmirror.com/source-map-js@1.0.2

-  registry.npmmirror.com/saxes@6.0.0:
-    resolution: {integrity: sha512-xAg7SOnEhrm5zI3puOOKyy1OMcMlIJZYNJY7xLBwSze0UjhPLnWfj2GF2EpT0jmzaJKIWKHLsaSSajf35bcYnA==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/saxes/-/saxes-6.0.0.tgz}
-    name: saxes
-    version: 6.0.0
-    engines: {node: '>=v12.22.7'}
-    dependencies:
-      xmlchars: registry.npmmirror.com/xmlchars@2.2.0
-    dev: false
-
  registry.npmmirror.com/scheduler@0.23.0:
    resolution: {integrity: sha512-CtuThmgHNg7zIZWAXi3AsyIzA3n4xx7aNyjwC2VJldO2LMVDhFK+63xGqq6CsJH4rTAt6/M+N4GhZiDYPx9eUw==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/scheduler/-/scheduler-0.23.0.tgz}
    name: scheduler
@@ -12271,12 +12187,6 @@ packages:
      stable: registry.npmmirror.com/stable@0.1.8
    dev: true

-  registry.npmmirror.com/symbol-tree@3.2.4:
-    resolution: {integrity: sha512-9QNk5KwDF+Bvz+PyObkmSYjI5ksVUYtjW7AU22r2NKcfLJcXp96hkDWU3+XndOsUb+AQ9QhfzfCT2O+CNWT5Tw==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/symbol-tree/-/symbol-tree-3.2.4.tgz}
-    name: symbol-tree
-    version: 3.2.4
-    dev: false
-
  registry.npmmirror.com/tapable@2.2.1:
    resolution: {integrity: sha512-GNzQvQTOIP6RyTfE2Qxb8ZVlNmw0n88vp1szwWRimP02mnTsx3Wtn5qRdqY9w2XduFNUgvOwhNnQsjwCp+kqaQ==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/tapable/-/tapable-2.2.1.tgz}
    name: tapable
@@ -12351,18 +12261,6 @@ packages:
    version: 1.0.6
    dev: false

-  registry.npmmirror.com/tough-cookie@4.1.3:
-    resolution: {integrity: sha512-aX/y5pVRkfRnfmuX+OdbSdXvPe6ieKX/G2s7e98f4poJHnqH3281gDPm/metm6E/WRamfx7WC4HUqkWHfQHprw==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/tough-cookie/-/tough-cookie-4.1.3.tgz}
-    name: tough-cookie
-    version: 4.1.3
-    engines: {node: '>=6'}
-    dependencies:
-      psl: registry.npmmirror.com/psl@1.9.0
-      punycode: registry.npmmirror.com/punycode@2.3.0
-      universalify: registry.npmmirror.com/universalify@0.2.0
-      url-parse: registry.npmmirror.com/url-parse@1.5.10
-    dev: false
-
  registry.npmmirror.com/tr46@0.0.3:
    resolution: {integrity: sha512-N3WMsuqV66lT30CrXNbEjx4GEwlow3v6rr4mCcv6prnfwhS01rkgyFdjPNBYd9br7LpXV1+Emh01fHnq2Gdgrw==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/tr46/-/tr46-0.0.3.tgz}
    name: tr46
@@ -12378,15 +12276,6 @@ packages:
      punycode: registry.npmmirror.com/punycode@2.3.0
    dev: false

-  registry.npmmirror.com/tr46@4.1.1:
-    resolution: {integrity: sha512-2lv/66T7e5yNyhAAC4NaKe5nVavzuGJQVVtRYLyQ2OI8tsJ61PMLlelehb0wi2Hx6+hT/OJUWZcw8MjlSRnxvw==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/tr46/-/tr46-4.1.1.tgz}
-    name: tr46
-    version: 4.1.1
-    engines: {node: '>=14'}
-    dependencies:
-      punycode: registry.npmmirror.com/punycode@2.3.0
-    dev: false
-
  registry.npmmirror.com/trim-lines@3.0.1:
    resolution: {integrity: sha512-kRj8B+YHZCc9kQYdWfJB2/oUl9rA99qbowYYBtr4ui4mZyAQ2JpvVBd/6U2YloATfqBhBTSMhTpgBHtU0Mf3Rg==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/trim-lines/-/trim-lines-3.0.1.tgz}
    name: trim-lines
@@ -12786,13 +12675,6 @@ packages:
      unist-util-visit-parents: registry.npmmirror.com/unist-util-visit-parents@5.1.3
    dev: false

-  registry.npmmirror.com/universalify@0.2.0:
-    resolution: {integrity: sha512-CJ1QgKmNg3CwvAv/kOFmtnEN05f0D/cn9QntgNOQlQF9dgvVTHj3t+8JPdjqawCHk7V/KA+fbUqzZ9XWhcqPUg==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/universalify/-/universalify-0.2.0.tgz}
-    name: universalify
-    version: 0.2.0
-    engines: {node: '>= 4.0.0'}
-    dev: false
-
  registry.npmmirror.com/update-browserslist-db@1.0.13(browserslist@4.22.1):
    resolution: {integrity: sha512-xebP81SNcPuNpPP3uzeW1NYXxI3rxyJzF3pD6sH4jE7o/IX+WtSpwnVU+qIsDPyk0d3hmFQ7mjqc6AtV604hbg==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/update-browserslist-db/-/update-browserslist-db-1.0.13.tgz}
    id: registry.npmmirror.com/update-browserslist-db/1.0.13
@@ -12814,15 +12696,6 @@ packages:
      punycode: registry.npmmirror.com/punycode@2.3.0
    dev: true

-  registry.npmmirror.com/url-parse@1.5.10:
-    resolution: {integrity: sha512-WypcfiRhfeUP9vvF0j6rw0J3hrWrw6iZv3+22h6iRMJ/8z1Tj6XfLP4DsUix5MhMPnXpiHDoKyoZ/bdCkwBCiQ==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/url-parse/-/url-parse-1.5.10.tgz}
-    name: url-parse
-    version: 1.5.10
-    dependencies:
-      querystringify: registry.npmmirror.com/querystringify@2.2.0
-      requires-port: registry.npmmirror.com/requires-port@1.0.0
-    dev: false
-
  registry.npmmirror.com/url@0.11.3:
    resolution: {integrity: sha512-6hxOLGfZASQK/cijlZnZJTq8OXAkt/3YGfQX45vvMYXpZoo8NdWZcY73K108Jf759lS1Bv/8wXnHDTSz17dSRw==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/url/-/url-0.11.3.tgz}
    name: url
@@ -13073,15 +12946,6 @@ packages:
    version: 3.1.0
    engines: {node: '>=0.10.0'}

-  registry.npmmirror.com/w3c-xmlserializer@4.0.0:
-    resolution: {integrity: sha512-d+BFHzbiCx6zGfz0HyQ6Rg69w9k19nviJspaj4yNscGjrHu94sVP+aRm75yEbCh+r2/yR+7q6hux9LVtbuTGBw==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/w3c-xmlserializer/-/w3c-xmlserializer-4.0.0.tgz}
-    name: w3c-xmlserializer
-    version: 4.0.0
-    engines: {node: '>=14'}
-    dependencies:
-      xml-name-validator: registry.npmmirror.com/xml-name-validator@4.0.0
-    dev: false
-
  registry.npmmirror.com/watchpack@2.4.0:
    resolution: {integrity: sha512-Lcvm7MGST/4fup+ifyKi2hjyIAwcdI4HRgtvTpIUxBRhB+RFtUh8XtDOxUfctVCnhVi+QQj49i91OyvzkJl6cg==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/watchpack/-/watchpack-2.4.0.tgz}
    name: watchpack
@@ -13130,22 +12994,6 @@ packages:
    engines: {node: '>=12'}
    dev: false

-  registry.npmmirror.com/whatwg-encoding@2.0.0:
-    resolution: {integrity: sha512-p41ogyeMUrw3jWclHWTQg1k05DSVXPLcVxRTYsXUk+ZooOCZLcoYgPZ/HL/D/N+uQPOtcp1me1WhBEaX02mhWg==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/whatwg-encoding/-/whatwg-encoding-2.0.0.tgz}
-    name: whatwg-encoding
-    version: 2.0.0
-    engines: {node: '>=12'}
-    dependencies:
-      iconv-lite: registry.npmmirror.com/iconv-lite@0.6.3
-    dev: false
-
-  registry.npmmirror.com/whatwg-mimetype@3.0.0:
-    resolution: {integrity: sha512-nt+N2dzIutVRxARx1nghPKGv1xHikU7HKdfafKkLNLindmPU/ch3U31NOCGGA/dmPcmb1VlofO0vnKAcsm0o/Q==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/whatwg-mimetype/-/whatwg-mimetype-3.0.0.tgz}
-    name: whatwg-mimetype
-    version: 3.0.0
-    engines: {node: '>=12'}
-    dev: false
-
  registry.npmmirror.com/whatwg-url@11.0.0:
    resolution: {integrity: sha512-RKT8HExMpoYx4igMiVMY83lN6UeITKJlBQ+vR/8ZJ8OCdSiN3RwCq+9gH0+Xzj0+5IrM6i4j/6LuvzbZIQgEcQ==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/whatwg-url/-/whatwg-url-11.0.0.tgz}
    name: whatwg-url
@@ -13156,16 +13004,6 @@ packages:
      webidl-conversions: registry.npmmirror.com/webidl-conversions@7.0.0
    dev: false

-  registry.npmmirror.com/whatwg-url@12.0.1:
-    resolution: {integrity: sha512-Ed/LrqB8EPlGxjS+TrsXcpUond1mhccS3pchLhzSgPCnTimUCKj3IZE75pAs5m6heB2U2TMerKFUXheyHY+VDQ==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/whatwg-url/-/whatwg-url-12.0.1.tgz}
-    name: whatwg-url
-    version: 12.0.1
-    engines: {node: '>=14'}
-    dependencies:
-      tr46: registry.npmmirror.com/tr46@4.1.1
-      webidl-conversions: registry.npmmirror.com/webidl-conversions@7.0.0
-    dev: false
-
  registry.npmmirror.com/whatwg-url@5.0.0:
    resolution: {integrity: sha512-saE57nupxk6v3HY35+jzBwYa0rKSy0XR8JSxZPwgLr7ys0IBzhGviA1/TUGJLmSVqs8pb9AnvICXEuOHLprYTw==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/whatwg-url/-/whatwg-url-5.0.0.tgz}
    name: whatwg-url
@@ -13308,28 +13146,6 @@ packages:
    name: wrappy
    version: 1.0.2

-  registry.npmmirror.com/ws@8.14.2:
-    resolution: {integrity: sha512-wEBG1ftX4jcglPxgFCMJmZ2PLtSbJ2Peg6TmpJFTbe9GZYOQCDPdMYu/Tm0/bGZkw8paZnJY45J4K2PZrLYq8g==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/ws/-/ws-8.14.2.tgz}
-    name: ws
-    version: 8.14.2
-    engines: {node: '>=10.0.0'}
-    peerDependencies:
-      bufferutil: ^4.0.1
-      utf-8-validate: '>=5.0.2'
-    peerDependenciesMeta:
-      bufferutil:
-        optional: true
-      utf-8-validate:
-        optional: true
-    dev: false
-
-  registry.npmmirror.com/xml-name-validator@4.0.0:
-    resolution: {integrity: sha512-ICP2e+jsHvAj2E2lIHxa5tjXRlKDJo4IdvPvCXbXQGdzSfmSpNVyIKMvoZHjDY9DP0zV17iI85o90vRFXNccRw==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/xml-name-validator/-/xml-name-validator-4.0.0.tgz}
-    name: xml-name-validator
-    version: 4.0.0
-    engines: {node: '>=12'}
-    dev: false
-
  registry.npmmirror.com/xmlbuilder@10.1.1:
    resolution: {integrity: sha512-OyzrcFLL/nb6fMGHbiRDuPup9ljBycsdCypwuyg5AAHvyWzGfChJpCXMG88AGTIMFhGZ9RccFN1e6lhg3hkwKg==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/xmlbuilder/-/xmlbuilder-10.1.1.tgz}
    name: xmlbuilder
@@ -13337,12 +13153,6 @@ packages:
    engines: {node: '>=4.0'}
    dev: false

-  registry.npmmirror.com/xmlchars@2.2.0:
-    resolution: {integrity: sha512-JZnDKK8B0RCDw84FNdDAIpZK+JuJw+s7Lz8nksI7SIuU3UXJJslUthsi+uWBUYOwPFwW7W7PRLRfUKpxjtjFCw==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/xmlchars/-/xmlchars-2.2.0.tgz}
-    name: xmlchars
-    version: 2.2.0
-    dev: false
-
  registry.npmmirror.com/xtend@4.0.2:
    resolution: {integrity: sha512-LKYU1iAXJXUgAXn9URjiu+MWhyUXHsvfp7mcuYm9dSUKK0/CjtrUwFAxD82/mCWbtLsGjFIad0wIsod4zrTAEQ==, registry: https://registry.npm.taobao.org/, tarball: https://registry.npmmirror.com/xtend/-/xtend-4.0.2.tgz}
    name: xtend
--- a/projects/app/package.json
+++ b/projects/app/package.json
@@ -1,6 +1,6 @@
 {
  "name": "app",
-  "version": "4.6.2",
+  "version": "4.6.3",
  "private": false,
  "scripts": {
    "dev": "next dev",
@@ -19,7 +19,6 @@
    "@fastgpt/global": "workspace:*",
    "@fastgpt/service": "workspace:*",
    "@fastgpt/web": "workspace:*",
-    "@mozilla/readability": "^0.4.4",
    "@node-rs/jieba": "^1.7.2",
    "@tanstack/react-query": "^4.24.10",
    "@types/nprogress": "^0.2.0",
@@ -35,7 +34,6 @@
    "i18next": "^22.5.1",
    "immer": "^9.0.19",
    "jschardet": "^3.0.0",
-    "jsdom": "^22.1.0",
    "jsonwebtoken": "^9.0.2",
    "lodash": "^4.17.21",
    "mammoth": "^1.6.0",
@@ -67,7 +65,6 @@
    "@types/downloadjs": "^1.4.3",
    "@types/formidable": "^2.0.5",
    "@types/js-cookie": "^3.0.3",
-    "@types/jsdom": "^21.1.1",
    "@types/jsonwebtoken": "^9.0.3",
    "@types/lodash": "^4.14.191",
    "@types/multer": "^1.4.10",
--- a/projects/app/public/docs/versionIntro.md
+++ b/projects/app/public/docs/versionIntro.md
@@ -1,13 +1,11 @@
 ### Fast GPT V4.6.2

-1. 新增 - 团队空间
-2. 新增 - 多路向量（多个向量映射一组数据）
-3. 新增 - tts语音
-4. 新增 - 语音输入
-5. 新增 - 增强召回方式，提高召回精度
-6. 优化 - 知识库导出，可直接触发流下载，无需等待转圈圈
-7. [知识库结构详解](https://doc.fastgpt.in/docs/use-cases/datasetengine/)
-8. [知识库提示词详解](https://doc.fastgpt.in/docs/use-cases/ai_settings/#引用模板--引用提示词)
-9. [使用文档](https://doc.fastgpt.in/docs/intro/)
-10. [点击查看高级编排介绍文档](https://doc.fastgpt.in/docs/workflow)
-11. [点击查看商业版](https://doc.fastgpt.in/docs/commercial/)
+1. 商业版新增 - web站点同步
+2. 新增 - 集合元数据记录
+3. 优化 - url 读取内容
+4. 优化 - 流读取文件，防止内存溢出
+5. [知识库结构详解](https://doc.fastgpt.in/docs/use-cases/datasetengine/)
+6. [知识库提示词详解](https://doc.fastgpt.in/docs/use-cases/ai_settings/#引用模板--引用提示词)
+7. [使用文档](https://doc.fastgpt.in/docs/intro/)
+8. [点击查看高级编排介绍文档](https://doc.fastgpt.in/docs/workflow)
+9. [点击查看商业版](https://doc.fastgpt.in/docs/commercial/)
--- a/projects/app/public/locales/en/common.json
+++ b/projects/app/public/locales/en/common.json
@@ -3,7 +3,6 @@
  "Cancel": "No",
  "Confirm": "Yes",
  "Create New": "Create",
-  "Dataset": "Dataset",
  "Export": "Export",
  "Folder": "Folder",
  "Move": "Move",
@@ -129,6 +128,7 @@
    "Choose": "Choose",
    "Close": "Close",
    "Collect": "Collect",
+    "Config": "Config",
    "Confirm": "Confirm",
    "Confirm Create": "Create",
    "Confirm Move": "Move here",
@@ -138,7 +138,6 @@
    "Course": "",
    "Create Failed": "Create Failed",
    "Create Success": "Create Success",
-    "Create Virtual File Failed": "Create Virtual File Failed",
    "Custom Title": "Custom Title",
    "Delete": "Delete",
    "Delete Failed": "Delete Failed",
@@ -152,6 +151,7 @@
    "Filed is repeat": "Filed is repeated",
    "Filed is repeated": "",
    "Input": "Input",
+    "Intro": "Intro",
    "Last Step": "Last",
    "Loading": "Loading",
    "Max credit": "Credit",
@@ -190,6 +190,14 @@
    "Update Time": "Update Time",
    "Upload File Failed": "Upload File Failed",
    "Username": "UserName",
+    "Website": "Website",
+    "choosable": "choosable",
+    "confirm": {
+      "Common Tip": "Operational Confirm"
+    },
+    "empty": {
+      "Common Tip": "No data"
+    },
    "error": {
      "unKnow": "There was an accident"
    },
@@ -207,11 +215,15 @@
    "input": {
      "Repeat Value": "Repeat Value"
    },
+    "link": {
+      "UnValid": "UnValid Link"
+    },
    "speech": {
      "error tip": "Speech Failed"
    }
  },
  "core": {
+    "Max Token": "MaxTokens",
    "ai": {
      "Model": "Model",
      "Prompt": "Prompt"
@@ -238,12 +250,13 @@
        "Speech model": "Speech model",
        "Speech speed": "Speed",
        "Test Listen": "Test",
-        "Test Listen Text": "Hello, this is FastGPT, how can I help you?",
+        "Test Listen Text": "Hello, this is a voice test, if you can hear this sentence, it means that the voice playback function is normal",
        "Web": "Browser (free)"
      }
    },
    "chat": {
      "Audio Speech Error": "Audio Speech Error",
+      "Quote Amount": "Dataset Quote:{{amount}}",
      "Record": "Speech",
      "Restart": "Restart",
      "Select File": "Select file",
@@ -252,29 +265,84 @@
      "Speaking": "I'm listening...",
      "Stop Speak": "Stop Speak",
      "Type a message": "Input problem",
+      "quote": {
+        "Quote Tip": "Only the actual reference content is displayed here. If the data is updated, it will not be updated in real time",
+        "Read Quote": "Read Quote",
+        "Read Source": "Read Source"
+      },
      "tts": {
        "Stop Speech": "Stop"
      }
    },
    "dataset": {
+      "All Dataset": "All Dataset",
      "Choose Dataset": "Choose Dataset",
+      "Common Dataset": "Common Dataset",
+      "Common Dataset Desc": "Knowledge bases can be built by importing files, web links, or manual entry",
      "Create dataset": "Create Dataset",
      "Dataset": "Dataset",
+      "Dataset Type": "Dataset Type",
+      "Delete Website Tips": "Confirm to delete the website",
+      "Empty Dataset": "",
+      "Empty Dataset Tips": "There is no knowledge base yet, go create one!",
+      "Folder Dataset": "Folder",
      "Go Dataset": "To Dataset",
+      "Intro Placeholder": "This dataset has not yet been introduced~",
      "Quote Length": "Quote Length",
      "Read Dataset": "Read Dataset",
      "Search Top K": "Top K",
      "Set Empty Result Tip": ",Response empty text",
+      "Set Website Config": "Configuring Website",
      "Similarity": "Similarity",
+      "Sync Time": "Update Time",
+      "Virtual File": "Virtual File",
+      "Website Dataset": "Website Sync",
+      "Website Dataset Desc": "Web site synchronization allows you to build a knowledge base directly from a web link",
+      "collection": {
+        "Click top config website": "Config",
+        "Empty Tip": "The collection is empty",
+        "Website Create Success": "Created successfully, data is being synchronized",
+        "Website Empty Tip": "No associated website yet,",
+        "Website Link": "Website Link",
+        "Website Sync": "Website",
+        "metadata": {
+          "Chunk Size": "Chunk Size",
+          "Createtime": "Create Time",
+          "Read Metadata": "Read Metadata",
+          "Training Type": "Training Type",
+          "Updatetime": "Update Time",
+          "metadata": "Metadata",
+          "read source": "Read Source",
+          "source": "Source",
+          "source name": "Source Name",
+          "source size": "Source Size"
+        },
+        "status": {
+          "active": "Ready",
+          "syncing": "Syncing"
+        },
+        "training": {
+          "type chunk": "Chunk",
+          "type manual": "Manual",
+          "type qa": "QA"
+        }
+      },
      "data": {
        "Edit": "Edit Data",
        "data is deleted": "Data is deleted",
        "id": "Data ID"
      },
+      "file": "File",
+      "folder": "Folder",
      "import": {
+        "Fetch Error": "Get link failed",
+        "Fetch Url": "Url",
+        "Fetch url placeholder": "Up to 10 links, one per line.",
+        "Fetch url tip": "Only static links can be read, please check the results",
        "Ideal chunk length": "Ideal chunk length",
        "Ideal chunk length Tips": "Segment by end symbol. We recommend that your document should be properly punctuated to ensure that each complete sentence length does not exceed this value \n Chinese document recommended 400~1000\n English document recommended 600~1200"
      },
+      "link": "Link",
      "search": {
        "Empty result response": "Empty Response",
        "Empty result response Tips": "If you fill in the content, if no suitable content is found, you will directly reply to the content.",
@@ -289,7 +357,12 @@
          "embedding desc": "Direct vector topk correlation query ",
          "embeddingReRank": "Enhanced semantic retrieval ",
          "embeddingReRank desc": "Sort using Rerank after overperforming vector topk queries "
-        }
+        },
+        "search mode": "Search Mode"
+      },
+      "status": {
+        "active": "Ready",
+        "syncing": "Syncing"
      },
      "test": {
        "Test": "Start",
@@ -300,6 +373,20 @@
        "test history": "Test History",
        "test result placeholder": "The test results will be presented here",
        "test result tip": "The contents of the knowledge base are sorted according to their similarity to the test text, and you can adjust the corresponding text according to the test results. Note: The data in the test record may have been modified, clicking on a test data will show the latest data."
+      },
+      "training": {
+        "Website Sync": "Website Sync",
+        "type chunk": "Chunk",
+        "type qa": "QA"
+      },
+      "website": {
+        "Base Url": "BaseUrl",
+        "Config": "Website Configuring",
+        "Config Description": "The Web site synchronization function allows you to fill in the root address of a website, and the system will automatically crawl the relevant pages deeply for knowledge base training. Only crawls static websites, mainly project documents and blogs.",
+        "Confirm Create Tips": "Confirm to synchronize the site, the synchronization task will start later, please confirm!",
+        "Confirm Update Tips": "Are you sure to update the site configuration? The synchronization starts immediately with the new configuration. Please confirm",
+        "Selector": "Selector",
+        "Start Sync": "Start Sync"
      }
    },
    "module": {
@@ -405,7 +492,6 @@
      "Create Training Data": "Training-{{filename}}",
      "Create Virtual File Success": "Create Virtual File Success",
      "Data Amount": "Data Amount",
-      "Ready": "Ready",
      "Select Collection": "Select Collection",
      "Select One Collection To Store": "Select the collection to store"
    },
@@ -437,6 +523,10 @@
    "import csv tip": "Ensure that the CSV is in UTF-8 format; otherwise, garbled characters will be displayed",
    "test": {
      "noResult": "Search results are empty"
+    },
+    "website": {
+      "Base Url": "BaseUrl",
+      "Selector": "Selector"
    }
  },
  "error": {
@@ -453,7 +543,6 @@
    "Fetch Url": "Fetch Url",
    "If the imported file is garbled, please convert CSV to UTF-8 encoding format": "If the imported file is garbled, please convert CSV to UTF-8 encoding format",
    "Parse": "{{name}} Parsing...",
-    "Ready": "Ready",
    "Release the mouse to upload the file": "Release the mouse to upload the file",
    "Select a maximum of 10 files": "Select a maximum of 10 files",
    "Uploading": "Uploading: {{name}}, Progress: {{percent}}%",
@@ -693,9 +782,13 @@
  "wallet": {
    "bill": {
      "Audio Speech": "Audio Speech",
+      "ReRank": "ReRank",
      "Whisper": "Whisper",
-      "bill username": "User",
-      "ReRank": "ReRank"
+      "bill username": "User"
+    },
+    "moduleName": {
+      "index": "Index Generation",
+      "qa": "QA Generation"
    }
  }
 }
--- a/projects/app/public/locales/zh/common.json
+++ b/projects/app/public/locales/zh/common.json
@@ -3,7 +3,6 @@
  "Cancel": "取消",
  "Confirm": "确认",
  "Create New": "新建",
-  "Dataset": "知识库",
  "Export": "导出",
  "Folder": "文件夹",
  "Move": "移动",
@@ -129,6 +128,7 @@
    "Choose": "选择",
    "Close": "关闭",
    "Collect": "收藏",
+    "Config": "配置",
    "Confirm": "确认",
    "Confirm Create": "确认创建",
    "Confirm Move": "移动到这",
@@ -138,7 +138,6 @@
    "Course": "",
    "Create Failed": "创建异常",
    "Create Success": "创建成功",
-    "Create Virtual File Failed": "创建虚拟文件失败",
    "Custom Title": "自定义标题",
    "Delete": "删除",
    "Delete Failed": "删除失败",
@@ -152,6 +151,7 @@
    "Filed is repeat": "",
    "Filed is repeated": "字段重复了",
    "Input": "输入",
+    "Intro": "介绍",
    "Last Step": "上一步",
    "Loading": "加载中",
    "Max credit": "最大金额",
@@ -190,6 +190,14 @@
    "Update Time": "更新时间",
    "Upload File Failed": "上传文件失败",
    "Username": "用户名",
+    "Website": "网站",
+    "choosable": "可选",
+    "confirm": {
+      "Common Tip": "操作确认"
+    },
+    "empty": {
+      "Common Tip": "没有什么数据噢~"
+    },
    "error": {
      "unKnow": "出现了点意外~"
    },
@@ -207,11 +215,15 @@
    "input": {
      "Repeat Value": "有重复的值"
    },
+    "link": {
+      "UnValid": "无效的链接"
+    },
    "speech": {
      "error tip": "语音转文字失败"
    }
  },
  "core": {
+    "Max Token": "单条数据上限",
    "ai": {
      "Model": "AI 模型",
      "Prompt": "提示词"
@@ -238,12 +250,13 @@
        "Speech model": "语音模型",
        "Speech speed": "语速",
        "Test Listen": "试听",
-        "Test Listen Text": "你好，我是 FastGPT，有什么可以帮助你么？",
+        "Test Listen Text": "你好，这是语音测试，如果你能听到这句话，说明语音播放功能正常",
        "Web": "浏览器自带(免费)"
      }
    },
    "chat": {
      "Audio Speech Error": "语音播报异常",
+      "Quote Amount": "知识库引用({{amount}}条)",
      "Record": "语音输入",
      "Restart": "重开对话",
      "Select File": "选择文件",
@@ -252,29 +265,84 @@
      "Speaking": "我在听，请说...",
      "Stop Speak": "停止录音",
      "Type a message": "输入问题",
+      "quote": {
+        "Quote Tip": "此处仅显示实际引用内容，若数据有更新，此处不会实时更新",
+        "Read Quote": "查看引用",
+        "Read Source": "查看来源"
+      },
      "tts": {
        "Stop Speech": "停止"
      }
    },
    "dataset": {
+      "All Dataset": "全部知识库",
      "Choose Dataset": "关联知识库",
+      "Common Dataset": "通用知识库",
+      "Common Dataset Desc": "可通过导入文件、网页链接或手动录入形式构建知识库",
      "Create dataset": "创建一个知识库",
      "Dataset": "知识库",
+      "Dataset Type": "知识库类型",
+      "Delete Website Tips": "确认删除该站点？",
+      "Empty Dataset": "",
+      "Empty Dataset Tips": "还没有知识库，快去创建一个吧！",
+      "Folder Dataset": "文件夹",
      "Go Dataset": "前往知识库",
+      "Intro Placeholder": "这个知识库还没有介绍~",
      "Quote Length": "引用内容长度",
      "Read Dataset": "查看知识库详情",
      "Search Top K": "单次搜索数量",
      "Set Empty Result Tip": ",未搜索到内容时回复指定内容",
+      "Set Website Config": "开始配置网站信息",
      "Similarity": "相似度",
+      "Sync Time": "最后更新时间",
+      "Virtual File": "虚拟文件",
+      "Website Dataset": "Web 站点同步",
+      "Website Dataset Desc": "Web 站点同步允许你直接使用一个网页链接构建知识库",
+      "collection": {
+        "Click top config website": "点击配置网站",
+        "Empty Tip": "数据集空空如也",
+        "Website Create Success": "创建成功，正在同步数据",
+        "Website Empty Tip": "还没有关联网站，",
+        "Website Link": "Web 站点地址",
+        "Website Sync": "Web 站点同步",
+        "metadata": {
+          "Chunk Size": "分割大小",
+          "Createtime": "创建时间",
+          "Read Metadata": "查看元数据",
+          "Training Type": "训练模式",
+          "Updatetime": "更新时间",
+          "metadata": "元数据",
+          "read source": "查看原始内容",
+          "source": "数据来源",
+          "source name": "来源名",
+          "source size": "来源大小"
+        },
+        "status": {
+          "active": "已就绪",
+          "syncing": "同步中"
+        },
+        "training": {
+          "type chunk": "直接分段",
+          "type manual": "手动",
+          "type qa": "问答拆分"
+        }
+      },
      "data": {
        "Edit": "编辑数据",
        "data is deleted": "该数据已被删除",
        "id": "数据ID"
      },
+      "file": "文件",
+      "folder": "目录",
      "import": {
+        "Fetch Error": "获取链接失败",
+        "Fetch Url": "网络链接",
+        "Fetch url placeholder": "最多10个链接，每行一个。",
+        "Fetch url tip": "仅支持读取静态链接，请注意检查结果",
        "Ideal chunk length": "理想分块长度",
        "Ideal chunk length Tips": "按结束符号进行分段。我们建议您的文档应合理的使用标点符号，以确保每个完整的句子长度不要超过该值\n中文文档建议400~1000\n英文文档建议600~1200"
      },
+      "link": "链接",
      "search": {
        "Empty result response": "空搜索回复",
        "Empty result response Tips": "若填写该内容，没有搜索到合适内容时，将直接回复填写的内容。",
@@ -289,7 +357,12 @@
          "embedding desc": "直接进行向量 topk 相关性查询",
          "embeddingReRank": "增强语义检索",
          "embeddingReRank desc": "超额进行向量 topk 查询后再使用 Rerank 进行排序"
-        }
+        },
+        "search mode": "检索模式"
+      },
+      "status": {
+        "active": "已就绪",
+        "syncing": "同步中"
      },
      "test": {
        "Test": "测试",
@@ -300,6 +373,20 @@
        "test history": "测试历史",
        "test result placeholder": "测试结果将在这里展示",
        "test result tip": "根据知识库内容与测试文本的相似度进行排序，你可以根据测试结果调整对应的文本。\n注意：测试记录中的数据可能已经被修改过，点击某条测试数据后将展示最新的数据。"
+      },
+      "training": {
+        "Website Sync": "Web 站点同步",
+        "type chunk": "直接分段",
+        "type qa": "问答拆分"
+      },
+      "website": {
+        "Base Url": "根地址",
+        "Config": "Web站点配置",
+        "Config Description": "Web 站点同步功能允许你填写一个网站的根地址，系统会自动深度抓取相关的网页进行知识库训练。仅会抓取静态的网站，以项目文档、博客为主。",
+        "Confirm Create Tips": "确认同步该站点，同步任务将随后开启，请确认！",
+        "Confirm Update Tips": "确认更新站点配置？会立即按新的配置开始同步，请确认！",
+        "Selector": "选择器",
+        "Start Sync": "开始同步"
      }
    },
    "module": {
@@ -405,7 +492,6 @@
      "Create Training Data": "文件训练-{{filename}}",
      "Create Virtual File Success": "创建虚拟文件成功",
      "Data Amount": "数据总量",
-      "Ready": "已就绪",
      "Select Collection": "选择文件",
      "Select One Collection To Store": "选择一个文件进行存储"
    },
@@ -437,6 +523,10 @@
    "import csv tip": "请确保CSV为UTF-8格式，否则会乱码",
    "test": {
      "noResult": "搜索结果为空"
+    },
+    "website": {
+      "Base Url": "",
+      "Selector": ""
    }
  },
  "error": {
@@ -453,7 +543,6 @@
    "Fetch Url": "链接读取",
    "If the imported file is garbled, please convert CSV to UTF-8 encoding format": "如果导入文件乱码，请将 CSV 转成 UTF-8 编码格式",
    "Parse": "{{name}} 解析中...",
-    "Ready": "",
    "Release the mouse to upload the file": "松开鼠标上传文件",
    "Select a maximum of 10 files": "最多选择10个文件",
    "Uploading": "正在上传 {{name}}，进度: {{percent}}%",
@@ -693,9 +782,13 @@
  "wallet": {
    "bill": {
      "Audio Speech": "语音播报",
+      "ReRank": "结果重排",
      "Whisper": "语音输入",
-      "bill username": "用户",
-      "ReRank": "结果重排"
+      "bill username": "用户"
+    },
+    "moduleName": {
+      "index": "索引生成",
+      "qa": "QA 拆分"
    }
  }
 }
--- a/projects/app/src/components/ChatBox/MessageInput.tsx
+++ b/projects/app/src/components/ChatBox/MessageInput.tsx
@@ -74,8 +74,8 @@ const MessageInput = ({
      try {
        const src = await compressImgFileAndUpload({
          file: file.rawFile,
-          maxW: 1000,
-          maxH: 1000,
+          maxW: 4329,
+          maxH: 4329,
          maxSize: 1024 * 1024 * 5,
          // 30 day expired.
          expiredTime: addDays(new Date(), 30)
--- a/projects/app/src/components/ChatBox/QuoteModal.tsx
+++ b/projects/app/src/components/ChatBox/QuoteModal.tsx
@@ -71,9 +71,9 @@ const QuoteModal = ({
        iconSrc="/imgs/modal/quote.svg"
        title={
          <Box>
-            知识库引用({rawSearch.length}条)
-            <Box fontSize={'10px'} color={'myGray.500'} fontWeight={'normal'}>
-              注意: 修改知识库内容成功后，此处不会显示变更情况。点击编辑后，会显示知识库最新的内容。
+            {t('core.chat.Quote Amount', { amount: rawSearch.length })}
+            <Box fontSize={'sm'} color={'myGray.500'} fontWeight={'normal'}>
+              {t('core.chat.quote.Quote Tip')}
            </Box>
          </Box>
        }
--- a/projects/app/src/components/ChatBox/ResponseTags.tsx
+++ b/projects/app/src/components/ChatBox/ResponseTags.tsx
@@ -1,7 +1,7 @@
 import React, { useMemo, useState } from 'react';
 import type { ChatHistoryItemResType } from '@fastgpt/global/core/chat/api.d';
 import type { ChatItemType } from '@fastgpt/global/core/chat/type';
-import { Flex, BoxProps, useDisclosure, Image, useTheme } from '@chakra-ui/react';
+import { Flex, BoxProps, useDisclosure, Image, useTheme, Box } from '@chakra-ui/react';
 import { useTranslation } from 'next-i18next';
 import { useSystemStore } from '@/web/common/system/useSystemStore';
 import type { SearchDataResponseItemType } from '@fastgpt/global/core/dataset/type';
@@ -11,6 +11,8 @@ import MyTooltip from '../MyTooltip';
 import { FlowNodeTypeEnum } from '@fastgpt/global/core/module/node/constant';
 import { getSourceNameIcon } from '@fastgpt/global/core/dataset/utils';
 import ChatBoxDivider from '@/components/core/chat/Divider';
+import MyIcon from '../Icon';
+import { getFileAndOpen } from '@/web/core/dataset/utils';

 const QuoteModal = dynamic(() => import('./QuoteModal'), { ssr: false });
 const ContextModal = dynamic(() => import('./ContextModal'), { ssr: false });
@@ -59,6 +61,7 @@ const ResponseTags = ({ responseData = [] }: { responseData?: ChatHistoryItemRes
        .flat()
        .map((item) => ({
          sourceName: item.sourceName,
+          sourceId: item.sourceId,
          icon: getSourceNameIcon({ sourceId: item.sourceId, sourceName: item.sourceName })
        })),
      historyPreview: chatData?.historyPreview,
@@ -83,18 +86,67 @@ const ResponseTags = ({ responseData = [] }: { responseData?: ChatHistoryItemRes
                alignItems={'center'}
                flexWrap={'wrap'}
                fontSize={'sm'}
-                cursor={'pointer'}
                border={theme.borders.sm}
                py={1}
                px={2}
                borderRadius={'md'}
                _hover={{
-                  bg: 'myBlue.100'
+                  '.controller': {
+                    display: 'flex'
+                  }
                }}
+                overflow={'hidden'}
+                position={'relative'}
                onClick={() => setQuoteModalData(quoteList)}
              >
                <Image src={item.icon} alt={''} mr={1} w={'12px'} />
-                {item.sourceName}
+                <Box className="textEllipsis" flex={'1 0 0'}>
+                  {item.sourceName}
+                </Box>
+
+                <Box
+                  className="controller"
+                  display={['flex', 'none']}
+                  pr={2}
+                  position={'absolute'}
+                  right={0}
+                  left={0}
+                  justifyContent={'flex-end'}
+                  alignItems={'center'}
+                  h={'100%'}
+                  lineHeight={0}
+                  bg={`linear-gradient(to left, white,white ${
+                    item.sourceId ? '60px' : '30px'
+                  }, rgba(255,255,255,0) 80%)`}
+                >
+                  <MyTooltip label={t('core.chat.quote.Read Quote')}>
+                    <MyIcon
+                      name="common/viewLight"
+                      w={'14px'}
+                      cursor={'pointer'}
+                      _hover={{
+                        color: 'green.600'
+                      }}
+                    />
+                  </MyTooltip>
+                  {item.sourceId && (
+                    <MyTooltip label={t('core.chat.quote.Read Source')}>
+                      <MyIcon
+                        ml={4}
+                        name="common/routePushLight"
+                        w={'14px'}
+                        cursor={'pointer'}
+                        _hover={{ color: 'myBlue.600' }}
+                        onClick={async (e) => {
+                          e.stopPropagation();
+
+                          if (!item.sourceId) return;
+                          await getFileAndOpen(item.sourceId);
+                        }}
+                      />
+                    </MyTooltip>
+                  )}
+                </Box>
              </Flex>
            ))}
          </Flex>
--- a/projects/app/src/components/ChatBox/WholeResponseModal.tsx
+++ b/projects/app/src/components/ChatBox/WholeResponseModal.tsx
@@ -10,6 +10,7 @@ import MyTooltip from '../MyTooltip';
 import { QuestionOutlineIcon } from '@chakra-ui/icons';
 import { formatPrice } from '@fastgpt/global/support/wallet/bill/tools';
 import Markdown from '../Markdown';
+import { DatasetSearchModeMap } from '@fastgpt/global/core/dataset/constant';

 function Row({ label, value }: { label: string; value?: string | number }) {
  const theme = useTheme();
@@ -127,6 +128,13 @@ const WholeResponseModal = ({
          )}

          {/* dataset search */}
+          {activeModule?.searchMode && (
+            <Row
+              label={t('core.dataset.search.search mode')}
+              // @ts-ignore
+              value={t(DatasetSearchModeMap[activeModule.searchMode]?.title)}
+            />
+          )}
          <Row label={t('chat.response.module similarity')} value={activeModule?.similarity} />
          <Row label={t('chat.response.module limit')} value={activeModule?.limit} />

--- a/projects/app/src/components/ChatBox/index.module.scss
+++ b/projects/app/src/components/ChatBox/index.module.scss
@@ -1,14 +1,6 @@
 .stopIcon {
  animation: zoomStopIcon 0.4s infinite alternate;
 }
-@keyframes zoomStopIcon {
-  0% {
-    transform: scale(0.8);
-  }
-  100% {
-    transform: scale(1.2);
-  }
-}

 .statusAnimation {
  animation: statusBox 0.8s linear infinite alternate;
--- a/projects/app/src/components/EmptyTip/index.tsx
+++ b/projects/app/src/components/EmptyTip/index.tsx
@@ -1,17 +1,19 @@
 import React from 'react';
 import { Flex, Box, FlexProps } from '@chakra-ui/react';
 import MyIcon from '../Icon';
+import { useTranslation } from 'next-i18next';

 type Props = FlexProps & {
-  text?: string | null;
+  text?: string | React.ReactNode;
 };

 const EmptyTip = ({ text, ...props }: Props) => {
+  const { t } = useTranslation();
  return (
    <Flex mt={5} flexDirection={'column'} alignItems={'center'} pt={'10vh'} {...props}>
      <MyIcon name="empty" w={'48px'} h={'48px'} color={'transparent'} />
      <Box mt={2} color={'myGray.500'}>
-        {text || '没有什么数据噢~'}
+        {text || t('common.empty.Common Tip')}
      </Box>
    </Flex>
  );
--- a/projects/app/src/components/Icon/icons/common/confirm/commonTip.svg
+++ b/projects/app/src/components/Icon/icons/common/confirm/commonTip.svg
@@ -0,0 +1 @@
+<?xml version="1.0" standalone="no"?><!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.1//EN" "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd"><svg t="1701410305116" class="icon" viewBox="0 0 1024 1024" version="1.1" xmlns="http://www.w3.org/2000/svg" p-id="8647" xmlns:xlink="http://www.w3.org/1999/xlink" width="128" height="128"><path d="M138.9056 180.5312m94.7712 0l563.3536 0q94.7712 0 94.7712 94.7712l0 576q0 94.7712-94.7712 94.7712l-563.3536 0q-94.7712 0-94.7712-94.7712l0-576q0-94.7712 94.7712-94.7712Z" fill="#CCDAFF" p-id="8648"></path><path d="M292.3008 81.92m64.768 0l305.3056 0q64.768 0 64.768 64.768l0 70.4q0 64.768-64.768 64.768l-305.3056 0q-64.768 0-64.768-64.768l0-70.4q0-64.768 64.768-64.768Z" fill="#7A7AF9" p-id="8649"></path><path d="M480.768 736.8704a49.408 49.408 0 0 1-34.7648-14.2848L332.8 611.3792a49.6128 49.6128 0 1 1 69.7344-70.7072l77.7216 76.4928L634.5216 460.8a49.6128 49.6128 0 1 1 70.6048 69.6832L516.096 721.92a49.6128 49.6128 0 0 1-35.328 14.9504z" fill="#7A7AF9" p-id="8650"></path></svg>
--- a/projects/app/src/components/Icon/icons/common/confirm/deleteTip.svg
+++ b/projects/app/src/components/Icon/icons/common/confirm/deleteTip.svg
@@ -0,0 +1 @@
+<?xml version="1.0" standalone="no"?><!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.1//EN" "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd"><svg t="1701403554068" class="icon" viewBox="0 0 1024 1024" version="1.1" xmlns="http://www.w3.org/2000/svg" p-id="5098" xmlns:xlink="http://www.w3.org/1999/xlink" width="128" height="128"><path d="M572.074667 337.134933a57.275733 57.275733 0 1 0-114.176-6.007466h-0.170667l12.936533 272.896v0.443733a44.544 44.544 0 1 0 89.019734-1.194667l12.424533-266.1376z m-196.949334-191.214933c76.151467-130.048 199.816533-129.774933 275.797334 0l340.3776 581.085867c76.117333 130.048 15.7696 235.4176-135.236267 235.4176H169.984c-150.8352 0-211.217067-105.6768-135.202133-235.4176L375.125333 145.92z m140.049067 687.581867a57.275733 57.275733 0 1 0 0-114.517334 57.275733 57.275733 0 0 0 0 114.517334z" fill="#FB6547" p-id="5099"></path></svg>
--- a/projects/app/src/components/Icon/icons/common/routePushLight.svg
+++ b/projects/app/src/components/Icon/icons/common/routePushLight.svg
@@ -0,0 +1,11 @@
+<?xml version="1.0" standalone="no"?>
+<!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.1//EN" "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd"><svg t="1701418384907"
+    class="icon" viewBox="0 0 1024 1024" version="1.1" xmlns="http://www.w3.org/2000/svg" p-id="11367"
+    xmlns:xlink="http://www.w3.org/1999/xlink" width="128" height="128">
+    <path
+        d="M892 928.1H134c-19.9 0-36-16.1-36-36v-758c0-19.9 16.1-36 36-36h314.1c19.9 0 36 16.1 36 36s-16.1 36-36 36H170v686h686V579.6c0-19.9 16.1-36 36-36s36 16.1 36 36v312.5c0 19.9-16.1 36-36 36z"
+        p-id="11368"></path>
+    <path
+        d="M927.9 131.6v-0.5c-0.1-1.7-0.4-3.3-0.7-4.9 0-0.1 0-0.2-0.1-0.3-0.4-1.7-0.9-3.3-1.5-4.9v-0.1c-0.6-1.6-1.4-3.1-2.2-4.6 0-0.1-0.1-0.1-0.1-0.2-0.8-1.4-1.7-2.8-2.7-4.1-0.1-0.1-0.2-0.3-0.3-0.4-0.5-0.6-0.9-1.1-1.4-1.7 0-0.1-0.1-0.1-0.1-0.2-0.5-0.6-1-1.1-1.6-1.6l-0.4-0.4c-0.5-0.5-1.1-1-1.6-1.5l-0.1-0.1c-0.6-0.5-1.2-1-1.9-1.4-0.1-0.1-0.3-0.2-0.4-0.3-1.4-1-2.8-1.8-4.3-2.6l-0.1-0.1c-1.6-0.8-3.2-1.5-4.9-2-1.6-0.5-3.3-1-5-1.2-0.1 0-0.2 0-0.3-0.1l-2.4-0.3h-0.3c-0.7-0.1-1.3-0.1-2-0.1H640.1c-19.9 0-36 16.1-36 36s16.1 36 36 36h165L487.6 487.6c-14.1 14.1-14.1 36.9 0 50.9 7 7 16.2 10.5 25.5 10.5 9.2 0 18.4-3.5 25.5-10.5L856 221v162.8c0 19.9 16.1 36 36 36s36-16.1 36-36V134.1c0-0.8 0-1.7-0.1-2.5z"
+        p-id="11369"></path>
+</svg>
--- a/projects/app/src/components/Icon/icons/common/viewLight.svg
+++ b/projects/app/src/components/Icon/icons/common/viewLight.svg
@@ -0,0 +1 @@
+<?xml version="1.0" standalone="no"?><!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.1//EN" "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd"><svg t="1701420318127" class="icon" viewBox="0 0 1024 1024" version="1.1" xmlns="http://www.w3.org/2000/svg" p-id="13238" xmlns:xlink="http://www.w3.org/1999/xlink" width="128" height="128"><path d="M987.52 367.36c-108.16-146.56-266.88-239.36-444.16-239.36-177.28 0-335.36 92.8-444.16 239.36-48 64.64-48 160.64 0 225.28C208 739.2 366.72 832 543.36 832c177.28 0 335.36-92.8 444.16-239.36C1035.52 528 1035.52 432 987.52 367.36zM939.52 539.52C839.04 684.8 694.4 768 542.72 768c-151.68 0-296.32-83.2-396.8-228.48C121.6 505.6 121.6 455.04 145.92 420.48 246.4 275.2 391.04 192 542.72 192c151.68 0 296.32 83.2 396.8 228.48C963.2 455.04 963.2 505.6 939.52 539.52zM544 256C420.48 256 320 356.48 320 480S420.48 704 544 704 768 603.52 768 480 667.52 256 544 256zM544 640C455.68 640 384 568.32 384 480S455.68 320 544 320C632.32 320 704 391.68 704 480S632.32 640 544 640z" p-id="13239"></path></svg>
--- a/projects/app/src/components/Icon/icons/core/dataset/commonDataset.svg
+++ b/projects/app/src/components/Icon/icons/core/dataset/commonDataset.svg
@@ -0,0 +1 @@
+<?xml version="1.0" standalone="no"?><!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.1//EN" "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd"><svg t="1697622173220" class="icon" viewBox="0 0 1024 1024" version="1.1" xmlns="http://www.w3.org/2000/svg" p-id="2398" xmlns:xlink="http://www.w3.org/1999/xlink" width="128" height="128"><path d="M722.36246914 1024.8960632h-415.54678519c-120.26260543 0-218.12969876-97.86709333-218.12969877-218.12969875v-586.42583704c0-120.26260543 97.86709333-218.12969876 218.12969877-218.12969877h415.54678519c120.26260543 0 218.12969876 97.86709333 218.12969876 218.12969877v586.42583704c0 120.26260543-97.86709333 218.12969876-218.12969876 218.12969875z m-415.54678519-898.28010667c-51.65207703 0-93.72457086 42.07249383-93.72457086 93.72457088v586.42583704c0 51.65207703 42.07249383 93.72457086 93.72457086 93.72457086h415.54678519c51.65207703 0 93.72457086-42.07249383 93.72457086-93.72457086v-586.42583704c0-51.65207703-42.07249383-93.72457086-93.72457086-93.72457088h-415.54678519z" fill="#BDD2EF" p-id="2399"></path><path d="M684.0441363 599.76969482H338.27296395c-42.07249383 0-76.11885037-34.04635653-76.11885037-76.11885037s34.04635653-76.11885037 76.11885037-76.11885037h345.77117235c42.07249383 0 76.11885037 34.04635653 76.11885037 76.11885037s-34.17581037 76.11885037-76.11885037 76.11885037zM465.00826075 360.66847605h-126.7352968c-42.07249383 0-76.11885037-34.04635653-76.11885037-76.11885036s34.04635653-76.11885037 76.11885037-76.11885038h126.7352968c42.07249383 0 76.11885037 34.04635653 76.11885036 76.11885038s-34.04635653 76.11885037-76.11885036 76.11885036zM684.0441363 360.66847605h-25.37295013c-42.07249383 0-76.11885037-34.04635653-76.11885036-76.11885036s34.04635653-76.11885037 76.11885036-76.11885038h25.37295013c42.07249383 0 76.11885037 34.04635653 76.11885037 76.11885038s-34.17581037 76.11885037-76.11885037 76.11885036zM684.0441363 838.87091358H338.27296395c-42.07249383 0-76.11885037-34.04635653-76.11885037-76.11885038s34.04635653-76.11885037 76.11885037-76.11885037h345.77117235c42.07249383 0 76.11885037 34.04635653 76.11885037 76.11885037s-34.17581037 76.11885037-76.11885037 76.11885038z" fill="#2867CE" p-id="2400"></path></svg>
--- a/projects/app/src/components/Icon/icons/core/dataset/folderDataset.svg
+++ b/projects/app/src/components/Icon/icons/core/dataset/folderDataset.svg
@@ -0,0 +1 @@
+<?xml version="1.0" standalone="no"?><!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.1//EN" "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd"><svg t="1694141197423" class="icon" viewBox="0 0 1024 1024" version="1.1" xmlns="http://www.w3.org/2000/svg" p-id="4891" xmlns:xlink="http://www.w3.org/1999/xlink" width="64" height="64"><path d="M855.04 385.024q19.456 2.048 38.912 10.24t33.792 23.04 21.504 37.376 2.048 54.272q-2.048 8.192-8.192 40.448t-14.336 74.24-18.432 86.528-19.456 76.288q-5.12 18.432-14.848 37.888t-25.088 35.328-36.864 26.112-51.2 10.24l-567.296 0q-21.504 0-44.544-9.216t-42.496-26.112-31.744-40.96-12.288-53.76l0-439.296q0-62.464 33.792-97.792t95.232-35.328l503.808 0q22.528 0 46.592 8.704t43.52 24.064 31.744 35.84 12.288 44.032l0 11.264-53.248 0q-40.96 0-95.744-0.512t-116.736-0.512-115.712-0.512-92.672-0.512l-47.104 0q-26.624 0-41.472 16.896t-23.04 44.544q-8.192 29.696-18.432 62.976t-18.432 61.952q-10.24 33.792-20.48 65.536-2.048 8.192-2.048 13.312 0 17.408 11.776 29.184t29.184 11.776q31.744 0 43.008-39.936l54.272-198.656q133.12 1.024 243.712 1.024l286.72 0z" fill="#FFCC66" p-id="4892"></path></svg>
--- a/projects/app/src/components/Icon/icons/core/dataset/websiteDataset.svg
+++ b/projects/app/src/components/Icon/icons/core/dataset/websiteDataset.svg
@@ -0,0 +1,14 @@
+<?xml version="1.0" standalone="no"?>
+<!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.1//EN" "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd"><svg t="1701324062325"
+    class="icon" viewBox="0 0 1024 1024" version="1.1" xmlns="http://www.w3.org/2000/svg" p-id="4651"
+    xmlns:xlink="http://www.w3.org/1999/xlink" width="128" height="128">
+    <path d="M512 512m-512 0a512 512 0 1 0 1024 0 512 512 0 1 0-1024 0Z" fill="#c6dafe" p-id="4652"></path>
+    <path d="M486.4 665.6h51.2v153.6h-51.2z" fill="#515151" p-id="4653"
+        data-spm-anchor-id="a313x.search_index.0.i3.5ac83a811R1Mg6" class="selected"></path>
+    <path
+        d="M435.2 768h153.6v51.2h-153.6zM230.4 281.6v384h563.2V281.6H230.4z m0-51.2h563.2a51.2 51.2 0 0 1 51.2 51.2v384a51.2 51.2 0 0 1-51.2 51.2H230.4a51.2 51.2 0 0 1-51.2-51.2V281.6a51.2 51.2 0 0 1 51.2-51.2z"
+        fill="#515151" p-id="4654" data-spm-anchor-id="a313x.search_index.0.i1.5ac83a811R1Mg6" class="selected"></path>
+    <path
+        d="M662.272 388.864c6.144-21.5296 8.448-63.0272-29.952-68.3776-30.72-3.84-67.584 16.128-86.8352 29.2096-6.144-0.768-13.056-1.536-19.968-1.536-49.9712-0.7936-82.2016 16.128-109.8496 52.224-9.984 13.056-19.2 35.3536-22.2976 60.672 13.824-23.808 56.8576-67.584 102.1952-85.248 0 0-68.352 49.152-102.1952 118.3232v0.768c-1.5616 3.072-3.072 6.144-4.6336 9.984-33.024 82.2016-6.144 117.5552 19.2256 123.6992 23.04 6.144 55.3216-5.376 81.408-33.024 43.776 9.984 87.6288-1.536 103.7312-9.984 30.72-16.896 52.2496-46.848 56.8832-77.6192h-84.5312s-3.84 26.88-49.1776 26.88c-41.472 0-43.776-48.384-43.776-48.384h178.9952s3.072-52.2496-22.272-86.8352c-14.6176-19.2-33.8176-36.1216-60.6976-45.312 8.448-6.144 22.272-15.4112 34.56-18.4832 23.04-6.144 38.4256-2.304 48.4096 14.592 13.056 23.04-7.68 76.0832-7.68 76.0832s12.288-15.36 18.432-37.632z m-185.1648 203.6224c-35.328 29.2096-64.512 25.3696-76.0576 8.4736-9.984-15.36-11.52-42.2656 0-79.8976 5.376 14.592 13.824 28.416 26.112 40.704 15.36 15.36 32.256 25.344 49.9456 30.72z m-1.536-149.8368s1.536-34.56 39.168-37.632c32.3072-3.072 49.2032 11.52 54.5536 39.1936l-93.7472-1.536z"
+        fill="#2394FB" p-id="4655"></path>
+</svg>
--- a/projects/app/src/components/Icon/index.tsx
+++ b/projects/app/src/components/Icon/index.tsx
@@ -114,7 +114,14 @@ const iconPaths = {
  'core/dataset/modeEmbFTRerank': () => import('./icons/core/dataset/modeEmbFTRerank.svg'),
  'core/app/variable/input': () => import('./icons/core/app/variable/input.svg'),
  'core/app/variable/textarea': () => import('./icons/core/app/variable/textarea.svg'),
-  'core/app/variable/select': () => import('./icons/core/app/variable/select.svg')
+  'core/app/variable/select': () => import('./icons/core/app/variable/select.svg'),
+  'core/dataset/websiteDataset': () => import('./icons/core/dataset/websiteDataset.svg'),
+  'core/dataset/commonDataset': () => import('./icons/core/dataset/commonDataset.svg'),
+  'core/dataset/folderDataset': () => import('./icons/core/dataset/folderDataset.svg'),
+  'common/confirm/deleteTip': () => import('./icons/common/confirm/deleteTip.svg'),
+  'common/confirm/commonTip': () => import('./icons/common/confirm/commonTip.svg'),
+  'common/routePushLight': () => import('./icons/common/routePushLight.svg'),
+  'common/viewLight': () => import('./icons/common/viewLight.svg')
 };

 export type IconName = keyof typeof iconPaths;
--- a/projects/app/src/components/Layout/index.tsx
+++ b/projects/app/src/components/Layout/index.tsx
@@ -111,7 +111,7 @@ const Layout = ({ children }: { children: JSX.Element }) => {
          </>
        )}
      </Box>
-      <Loading loading={loading} zIndex={9999} />
+      <Loading loading={loading} zIndex={999999} />
      {!!userInfo && <UpdateInviteModal />}
    </>
  );
--- a/projects/app/src/components/Markdown/chat/Image.tsx
+++ b/projects/app/src/components/Markdown/chat/Image.tsx
@@ -1,30 +1,33 @@
-import { Box, Flex } from '@chakra-ui/react';
+import { Box, Flex, Grid } from '@chakra-ui/react';
 import MdImage from '../img/Image';
 import { useMemo } from 'react';

 const ImageBlock = ({ images }: { images: string }) => {
  const formatData = useMemo(
    () =>
-      images.split('\n').map((item) => {
-        try {
-          return JSON.parse(item) as { src: string };
-        } catch (error) {
-          return { src: '' };
-        }
-      }),
+      images
+        .split('\n')
+        .filter((item) => item)
+        .map((item) => {
+          try {
+            return JSON.parse(item) as { src: string };
+          } catch (error) {
+            return { src: '' };
+          }
+        }),
    [images]
  );

  return (
-    <Flex alignItems={'center'} wrap={'wrap'} gap={4}>
+    <Grid gridTemplateColumns={['1fr', '1fr 1fr']} gap={4}>
      {formatData.map(({ src }) => {
        return (
-          <Box key={src} rounded={'md'} flex={'0 0 auto'} w={'120px'}>
+          <Box key={src} rounded={'md'} flex={'1 0 0'} minW={'120px'}>
            <MdImage src={src} />
          </Box>
        );
      })}
-    </Flex>
+    </Grid>
  );
 };

--- a/projects/app/src/components/Markdown/img/Image.tsx
+++ b/projects/app/src/components/Markdown/img/Image.tsx
@@ -29,7 +29,6 @@ const MdImage = ({ src }: { src?: string }) => {
        borderRadius={'md'}
        src={src}
        alt={''}
-        maxH={'150px'}
        fallbackSrc={'/imgs/errImg.png'}
        fallbackStrategy={'onError'}
        cursor={succeed ? 'pointer' : 'default'}
--- a/projects/app/src/components/MyModal/index.tsx
+++ b/projects/app/src/components/MyModal/index.tsx
@@ -9,6 +9,7 @@ import {
  Box,
  Image
 } from '@chakra-ui/react';
+import MyIcon from '../Icon';

 export interface MyModalProps extends ModalContentProps {
  iconSrc?: string;
@@ -56,7 +57,15 @@ const MyModal = ({
            roundedTop={'lg'}
            py={'10px'}
          >
-            {iconSrc && <Image mr={3} objectFit={'contain'} alt="" src={iconSrc} w={'20px'} />}
+            {iconSrc && (
+              <>
+                {iconSrc.startsWith('/') ? (
+                  <Image mr={3} objectFit={'contain'} alt="" src={iconSrc} w={'20px'} />
+                ) : (
+                  <MyIcon mr={3} name={iconSrc as any} w={'20px'} />
+                )}
+              </>
+            )}
            {title}
            <Box flex={1} />
            {onClose && <ModalCloseButton position={'relative'} top={0} right={0} />}
--- a/projects/app/src/components/common/MyRadio/index.tsx
+++ b/projects/app/src/components/common/MyRadio/index.tsx
@@ -1,5 +1,5 @@
 import React from 'react';
-import { Box, Flex, useTheme, Grid, type GridProps, theme } from '@chakra-ui/react';
+import { Box, Flex, useTheme, Grid, type GridProps, theme, Image } from '@chakra-ui/react';
 import MyIcon from '@/components/Icon';
 import { useTranslation } from 'next-i18next';

@@ -36,16 +36,16 @@ const MyRadio = ({
          border={theme.borders.sm}
          borderWidth={'1.5px'}
          borderRadius={'md'}
-          bg={'myWhite.300'}
          position={'relative'}
          {...(value === item.value
            ? {
-                borderColor: 'myBlue.700'
+                borderColor: 'myBlue.500',
+                bg: 'myBlue.100'
              }
            : {
+                bg: 'myWhite.300',
                _hover: {
-                  bg: 'myBlue.100',
-                  borderColor: 'myBlue.600'
+                  borderColor: 'myBlue.500'
                }
              })}
          _after={{
@@ -70,7 +70,15 @@ const MyRadio = ({
          }}
          onClick={() => onChange(item.value)}
        >
-          {!!item.icon && <MyIcon mr={'14px'} name={item.icon as any} w={iconSize} />}
+          {!!item.icon && (
+            <>
+              {item.icon.startsWith('/') ? (
+                <Image src={item.icon} mr={'14px'} w={iconSize} alt={''} />
+              ) : (
+                <MyIcon mr={'14px'} name={item.icon as any} w={iconSize} />
+              )}
+            </>
+          )}
          <Box pr={2}>
            <Box>{t(item.title)}</Box>
            {!!item.desc && (
--- a/projects/app/src/components/core/module/DatasetSelectModal.tsx
+++ b/projects/app/src/components/core/module/DatasetSelectModal.tsx
@@ -7,29 +7,20 @@ import {
  ModalBody,
  ModalFooter,
  useTheme,
-  Textarea,
  Grid,
-  Divider,
-  Switch,
-  Image
+  Divider
 } from '@chakra-ui/react';
 import Avatar from '@/components/Avatar';
-import { useForm } from 'react-hook-form';
-import { QuestionOutlineIcon } from '@chakra-ui/icons';
 import type { SelectedDatasetType } from '@fastgpt/global/core/module/api.d';
 import { useToast } from '@/web/common/hooks/useToast';
-import MySlider from '@/components/Slider';
 import MyTooltip from '@/components/MyTooltip';
-import MyModal from '@/components/MyModal';
 import MyIcon from '@/components/Icon';
-import { DatasetSearchModeEnum, DatasetTypeEnum } from '@fastgpt/global/core/dataset/constant';
+import { DatasetTypeEnum } from '@fastgpt/global/core/dataset/constant';
 import { useTranslation } from 'next-i18next';
 import { useDatasetStore } from '@/web/core/dataset/store/dataset';
-import { feConfigs } from '@/web/common/system/staticData';
 import DatasetSelectContainer, { useDatasetSelect } from '@/components/core/dataset/SelectModal';
 import { useLoading } from '@/web/common/hooks/useLoading';
 import EmptyTip from '@/components/EmptyTip';
-import { AppSimpleEditFormType } from '@fastgpt/global/core/app/type';

 export const DatasetSelectModal = ({
  isOpen,
@@ -132,9 +123,9 @@ export const DatasetSelectModal = ({
                  <MyTooltip
                    key={item._id}
                    label={
-                      item.type === DatasetTypeEnum.dataset
-                        ? t('dataset.Select Dataset')
-                        : t('dataset.Select Folder')
+                      item.type === DatasetTypeEnum.folder
+                        ? t('dataset.Select Folder')
+                        : t('dataset.Select Dataset')
                    }
                  >
                    <Card
@@ -149,7 +140,7 @@ export const DatasetSelectModal = ({
                      onClick={() => {
                        if (item.type === DatasetTypeEnum.folder) {
                          setParentId(item._id);
-                        } else if (item.type === DatasetTypeEnum.dataset) {
+                        } else {
                          const vectorModel = selectedDatasets[0]?.vectorModel?.model;

                          if (vectorModel && vectorModel !== item.vectorModel.model) {
--- a/projects/app/src/components/core/module/Flow/ModuleTemplateList.tsx
+++ b/projects/app/src/components/core/module/Flow/ModuleTemplateList.tsx
@@ -1,14 +1,5 @@
 import React, { useCallback, useMemo } from 'react';
-import {
-  Box,
-  Flex,
-  Accordion,
-  AccordionItem,
-  AccordionButton,
-  AccordionPanel,
-  AccordionIcon,
-  useTheme
-} from '@chakra-ui/react';
+import { Box, Flex } from '@chakra-ui/react';
 import type {
  FlowModuleTemplateType,
  moduleTemplateListType
--- a/projects/app/src/components/support/user/team/TeamManageModal/EditModal.tsx
+++ b/projects/app/src/components/support/user/team/TeamManageModal/EditModal.tsx
@@ -51,8 +51,8 @@ function EditModal({
      try {
        const src = await compressImgFileAndUpload({
          file,
-          maxW: 100,
-          maxH: 100
+          maxW: 300,
+          maxH: 300
        });
        setValue('avatar', src);
        setRefresh((state) => !state);
--- a/projects/app/src/constants/dataset.ts
+++ b/projects/app/src/constants/dataset.ts
@@ -14,7 +14,8 @@ export const defaultDatasetDetail: DatasetItemType = {
  type: 'dataset',
  avatar: '/icon/logo.svg',
  name: '',
-  tags: [],
+  intro: '',
+  status: 'active',
  permission: 'private',
  isOwner: false,
  canWrite: false,
@@ -24,7 +25,6 @@ export const defaultDatasetDetail: DatasetItemType = {

 export const defaultCollectionDetail: DatasetCollectionItemType = {
  _id: '',
-  userId: '',
  teamId: '',
  tmbId: '',
  datasetId: {
@@ -37,7 +37,8 @@ export const defaultCollectionDetail: DatasetCollectionItemType = {
    type: 'dataset',
    avatar: '/icon/logo.svg',
    name: '',
-    tags: [],
+    intro: '',
+    status: 'active',
    permission: 'private',
    vectorModel: defaultVectorModels[0].model,
    agentModel: defaultQAModels[0].model
@@ -46,8 +47,10 @@ export const defaultCollectionDetail: DatasetCollectionItemType = {
  name: '',
  type: 'file',
  updateTime: new Date(),
-  metadata: {},
  canWrite: false,
  sourceName: '',
-  sourceId: ''
+  sourceId: '',
+  createTime: new Date(),
+  trainingType: 'chunk',
+  chunkSize: 0
 };
--- a/projects/app/src/global/core/api/datasetReq.d.ts
+++ b/projects/app/src/global/core/api/datasetReq.d.ts
@@ -1,4 +1,8 @@
-import { DatasetCollectionTypeEnum, DatasetTypeEnum } from '@fastgpt/global/core/dataset/constant';
+import {
+  DatasetCollectionTrainingModeEnum,
+  DatasetCollectionTypeEnum,
+  DatasetTypeEnum
+} from '@fastgpt/global/core/dataset/constant';
 import type { RequestPaging } from '@/types';
 import { TrainingModeEnum } from '@fastgpt/global/core/dataset/constant';
 import type { SearchTestItemType } from '@/types/core/dataset';
@@ -8,15 +12,6 @@ import { PermissionTypeEnum } from '@fastgpt/global/support/permission/constant'
 import type { LLMModelItemType } from '@fastgpt/global/core/ai/model.d';

 /* ===== dataset ===== */
-export type DatasetUpdateParams = {
-  id: string;
-  parentId?: string;
-  tags?: string[];
-  name?: string;
-  avatar?: string;
-  permission?: `${PermissionTypeEnum}`;
-  agentModel?: LLMModelItemType;
-};

 /* ======= collections =========== */
 export type GetDatasetCollectionsProps = RequestPaging & {
@@ -26,19 +21,11 @@ export type GetDatasetCollectionsProps = RequestPaging & {
  simple?: boolean;
  selectFolder?: boolean;
 };
-export type CreateDatasetCollectionParams = {
-  datasetId: string;
-  parentId?: string;
-  name: string;
-  type: `${DatasetCollectionTypeEnum}`;
-  metadata?: DatasetCollectionSchemaType['metadata'];
-  updateTime?: string;
-};
+
 export type UpdateDatasetCollectionParams = {
  id: string;
  parentId?: string;
  name?: string;
-  metadata?: DatasetCollectionSchemaType['metadata'];
 };

 /* ==== data ===== */
--- a/projects/app/src/global/core/dataset/api.d.ts
+++ b/projects/app/src/global/core/dataset/api.d.ts
@@ -1,5 +1,9 @@
 import { PushDatasetDataChunkProps } from '@fastgpt/global/core/dataset/api';
-import { DatasetSearchModeEnum, TrainingModeEnum } from '@fastgpt/global/core/dataset/constant';
+import {
+  DatasetSearchModeEnum,
+  DatasetTypeEnum,
+  TrainingModeEnum
+} from '@fastgpt/global/core/dataset/constant';
 import {
  DatasetDataIndexItemType,
  SearchDataResponseItemType
@@ -8,8 +12,9 @@ import {
 /* ================= dataset ===================== */
 export type CreateDatasetParams = {
  parentId?: string;
+  type: `${DatasetTypeEnum}`;
  name: string;
-  tags: string;
+  intro: string;
  avatar: string;
  vectorModel?: string;
  agentModel?: string;
--- a/projects/app/src/global/core/dataset/type.d.ts
+++ b/projects/app/src/global/core/dataset/type.d.ts
@@ -16,7 +16,8 @@ export type DatasetCollectionsListItemType = {
  updateTime: Date;
  dataAmount: number;
  trainingAmount: number;
-  metadata: DatasetCollectionSchemaType['metadata'];
+  fileId?: string;
+  rawLink?: string;
  canWrite: boolean;
 };

--- a/projects/app/src/global/core/prompt/AIChat.ts
+++ b/projects/app/src/global/core/prompt/AIChat.ts
@@ -27,57 +27,56 @@ export const Prompt_QuotePromptList: PromptTemplateItem[] = [
  {
    title: '标准模板',
    desc: '',
-    value: `你的背景知识:
+    value: `你的知识库:
 """
 {{quote}}
 """
-对话要求：
-1. 背景知识是最新的实时的信息，使用背景知识回答问题。
-2. 优先使用背景知识的内容回答我的问题，答案应与背景知识严格一致。
-3. 背景知识无法回答我的问题时，可以忽略背景知识，根据你的知识来自由回答。
-4. 使用对话的风格，自然的回答问题。包含markdown内容，需按markdown格式返回。
+回答要求：
+1. 优先使用知识库内容回答问题。
+2. 你可以回答我不知道。
+3. 不要提及你是从知识库获取的知识。
+4. 知识库包含 markdown 内容时，按 markdown 格式返回。
 我的问题是:"{{question}}"`
  },
  {
    title: '问答模板',
    desc: '',
-    value: `你的背景知识:
+    value: `你的知识库:
 """
 {{quote}}
 """
-对话要求：
-1. 背景知识是最新的实时的信息，使用背景知识回答问题，其中 instruction 是相关介绍，output 是预期回答或补充。
-2. 优先使用背景知识的内容回答我的问题，答案应与背景知识严格一致。
-3. 背景知识无法回答我的问题时，可以忽略背景知识，根据你的知识来自由回答。
-4. 使用对话的风格，自然的回答问题。包含markdown内容，需按markdown格式返回。
+回答要求：
+1. 优先使用知识库内容回答问题，其中 instruction 是相关介绍，output 是预期回答或补充。
+2. 你可以回答我不知道。
+3. 不要提及你是从知识库获取的知识。
+4. 知识库包含 markdown 内容时，按 markdown 格式返回。
 我的问题是:"{{question}}"`
  },
  {
    title: '标准严格模板',
    desc: '',
-    value: `你的背景知识:
+    value: `你的知识库:
 """
 {{quote}}
 """
-对话要求：
-1. 背景知识是最新的实时的信息，是你的唯一信息来源，使用背景知识回答问题。
-2. 优先使用背景知识回答我的问题，答案与背景知识完全一致，无需做其他回答。
-3. 背景知识与问题无关，或背景知识无法回答本次问题时，则拒绝回答本次问题：“我不太清除xxx”。
-4. 使用对话的风格，自然的回答问题。包含markdown内容，需按markdown格式返回。
+回答要求：
+1. 仅使用知识库内容回答问题。
+2. 与知识库无关的问题，你直接回答我不知道。
+3. 不要提及你是从知识库获取的知识。
+4. 知识库包含 markdown 内容时，按 markdown 格式返回。
 我的问题是:"{{question}}"`
  },
  {
    title: '严格问答模板',
    desc: '',
-    value: `你的背景知识:
+    value: `你的知识库:
 """
 {{quote}}
 """
-对话要求：
-1. 背景知识是最新的实时的信息，是你的唯一信息来源，使用背景知识回答问题。
-2. 在背景知识的 JSON 中，question 是相关问题，answer 是已知答案。
-3. 选择 answer 中的内容作为答案，要求答案与 answer 完全一致，无需做其他回答。
-4. answer 中的答案无法满足问题，直接回复：“我不太清除xxx”。
+回答要求：
+1. 从知识库中选择一个合适的答案进行回答，其中 instruction 是相关问题，answer 是已知答案。
+2. 与知识库无关的问题，你直接回答我不知道。
+3. 不要提及你是从知识库获取的知识。
 我的问题是:"{{question}}"`
  }
 ];
--- a/projects/app/src/pages/account/components/BillDetail.tsx
+++ b/projects/app/src/pages/account/components/BillDetail.tsx
@@ -35,7 +35,7 @@ const BillDetail = ({ bill, onClose }: { bill: BillItemType; onClose: () => void
      <ModalBody>
        <Flex alignItems={'center'} pb={4}>
          <Box flex={'0 0 80px'}>用户:</Box>
-          <Box>{bill.memberName}</Box>
+          <Box>{t(bill.memberName)}</Box>
        </Flex>
        <Flex alignItems={'center'} pb={4}>
          <Box flex={'0 0 80px'}>订单号:</Box>
--- a/projects/app/src/pages/account/components/Info.tsx
+++ b/projects/app/src/pages/account/components/Info.tsx
@@ -96,8 +96,8 @@ const UserInfo = () => {
      try {
        const src = await compressImgFileAndUpload({
          file,
-          maxW: 100,
-          maxH: 100
+          maxW: 300,
+          maxH: 300
        });

        onclickSave({
--- a/projects/app/src/pages/api/admin/initv46-2.ts
+++ b/projects/app/src/pages/api/admin/initv46-2.ts
@@ -1,7 +1,7 @@
 import type { NextApiRequest, NextApiResponse } from 'next';
 import { jsonRes } from '@fastgpt/service/common/response';
 import { connectToDatabase } from '@/service/mongo';
-import { delay } from '@/utils/tools';
+import { delay } from '@fastgpt/global/common/system/utils';
 import { PgClient } from '@fastgpt/service/common/pg';
 import {
  DatasetDataIndexTypeEnum,
--- a/projects/app/src/pages/api/admin/initv46-fix.ts
+++ b/projects/app/src/pages/api/admin/initv46-fix.ts
@@ -1,12 +1,9 @@
 import type { NextApiRequest, NextApiResponse } from 'next';
 import { jsonRes } from '@fastgpt/service/common/response';
 import { connectToDatabase } from '@/service/mongo';
-import { delay } from '@/utils/tools';
+import { delay } from '@fastgpt/global/common/system/utils';
 import { PgClient } from '@fastgpt/service/common/pg';
-import {
-  DatasetDataIndexTypeEnum,
-  PgDatasetTableName
-} from '@fastgpt/global/core/dataset/constant';
+import { PgDatasetTableName } from '@fastgpt/global/core/dataset/constant';

 import { authCert } from '@fastgpt/service/support/permission/auth/common';
 import { MongoDatasetData } from '@fastgpt/service/core/dataset/data/schema';
--- a/projects/app/src/pages/api/admin/initv46.ts
+++ b/projects/app/src/pages/api/admin/initv46.ts
@@ -8,7 +8,7 @@ import {
 } from '@fastgpt/service/support/user/team/controller';
 import { MongoUser } from '@fastgpt/service/support/user/schema';
 import { UserModelSchema } from '@fastgpt/global/support/user/type';
-import { delay } from '@/utils/tools';
+import { delay } from '@fastgpt/global/common/system/utils';
 import { MongoDataset } from '@fastgpt/service/core/dataset/schema';
 import { PermissionTypeEnum } from '@fastgpt/global/support/permission/constant';
 import { MongoDatasetCollection } from '@fastgpt/service/core/dataset/collection/schema';
--- a/projects/app/src/pages/api/admin/initv462-2.ts
+++ b/projects/app/src/pages/api/admin/initv462-2.ts
@@ -1,7 +1,7 @@
 import type { NextApiRequest, NextApiResponse } from 'next';
 import { jsonRes } from '@fastgpt/service/common/response';
 import { connectToDatabase } from '@/service/mongo';
-import { delay } from '@/utils/tools';
+import { delay } from '@fastgpt/global/common/system/utils';
 import { authCert } from '@fastgpt/service/support/permission/auth/common';
 import { MongoApp } from '@fastgpt/service/core/app/schema';
 import { FlowNodeInputTypeEnum, FlowNodeTypeEnum } from '@fastgpt/global/core/module/node/constant';
--- a/projects/app/src/pages/api/admin/initv462.ts
+++ b/projects/app/src/pages/api/admin/initv462.ts
@@ -1,7 +1,7 @@
 import type { NextApiRequest, NextApiResponse } from 'next';
 import { jsonRes } from '@fastgpt/service/common/response';
 import { connectToDatabase } from '@/service/mongo';
-import { delay } from '@/utils/tools';
+import { delay } from '@fastgpt/global/common/system/utils';
 import { authCert } from '@fastgpt/service/support/permission/auth/common';
 import { MongoDatasetData } from '@fastgpt/service/core/dataset/data/schema';
 import { jiebaSplit } from '@/service/core/dataset/utils';
@@ -17,10 +17,13 @@ export default async function handler(req: NextApiRequest, res: NextApiResponse)

    console.log(
      'total',
-      await MongoDatasetData.countDocuments({ fullTextToken: { $exists: false } })
+      await MongoDatasetData.countDocuments({
+        fullTextToken: { $exists: false },
+        updateTime: { $lt: new Date() }
+      })
    );

-    await initFullTextToken(limit);
+    await initFullTextToken(limit, new Date());

    jsonRes(res, {
      message: 'success'
@@ -34,9 +37,12 @@ export default async function handler(req: NextApiRequest, res: NextApiResponse)
    });
  }
 }
-export async function initFullTextToken(limit = 50): Promise<any> {
+export async function initFullTextToken(limit = 50, endDate: Date): Promise<any> {
  try {
-    const dataList = await MongoDatasetData.find({ fullTextToken: { $exists: false } }, '_id q a')
+    const dataList = await MongoDatasetData.find(
+      { fullTextToken: { $exists: false }, updateTime: { $lt: endDate } },
+      '_id q a'
+    )
      .limit(limit)
      .lean();
    if (dataList.length === 0) return;
@@ -56,9 +62,9 @@ export async function initFullTextToken(limit = 50): Promise<any> {

    success += result.filter((item) => item.status === 'fulfilled').length;
    console.log(`success: ${success}`);
-    return initFullTextToken(limit);
+    return initFullTextToken(limit, endDate);
  } catch (error) {
    await delay(1000);
-    return initFullTextToken(limit);
+    return initFullTextToken(limit, endDate);
  }
 }
--- a/projects/app/src/pages/api/admin/initv463-2.ts
+++ b/projects/app/src/pages/api/admin/initv463-2.ts
@@ -0,0 +1,62 @@
+import type { NextApiRequest, NextApiResponse } from 'next';
+import { jsonRes } from '@fastgpt/service/common/response';
+import { connectToDatabase } from '@/service/mongo';
+import { delay } from '@fastgpt/global/common/system/utils';
+import { authCert } from '@fastgpt/service/support/permission/auth/common';
+import { MongoDatasetData } from '@fastgpt/service/core/dataset/data/schema';
+import { jiebaSplit } from '@/service/core/dataset/utils';
+
+let success = 0;
+/* pg 中的数据搬到 mongo dataset.datas 中，并做映射 */
+export default async function handler(req: NextApiRequest, res: NextApiResponse) {
+  try {
+    const { limit = 50 } = req.body as { limit: number };
+    await authCert({ req, authRoot: true });
+    await connectToDatabase();
+    success = 0;
+
+    console.log('total', await MongoDatasetData.countDocuments({ inited: { $exists: false } }));
+
+    await initFullTextToken(limit);
+
+    jsonRes(res, {
+      message: 'success'
+    });
+  } catch (error) {
+    console.log(error);
+
+    jsonRes(res, {
+      code: 500,
+      error
+    });
+  }
+}
+export async function initFullTextToken(limit = 50): Promise<any> {
+  try {
+    const dataList = await MongoDatasetData.find({ inited: { $exists: false } }, '_id q a')
+      .limit(limit)
+      .lean();
+    if (dataList.length === 0) return;
+
+    const result = await Promise.allSettled(
+      dataList.map((item) => {
+        const text = item.q + (item.a || '');
+        const tokens = jiebaSplit({ text });
+
+        return MongoDatasetData.findByIdAndUpdate(item._id, {
+          $set: {
+            inited: true,
+            fullTextToken: tokens
+          }
+        });
+      })
+    );
+
+    success += result.filter((item) => item.status === 'fulfilled').length;
+    console.log(`success: ${success}`);
+    return initFullTextToken(limit);
+  } catch (error) {
+    await delay(1000);
+    return initFullTextToken(limit);
+  }
+}
--- a/projects/app/src/pages/api/admin/initv463.ts
+++ b/projects/app/src/pages/api/admin/initv463.ts
@@ -0,0 +1,109 @@
+import type { NextApiRequest, NextApiResponse } from 'next';
+import { jsonRes } from '@fastgpt/service/common/response';
+import { connectToDatabase } from '@/service/mongo';
+import { authCert } from '@fastgpt/service/support/permission/auth/common';
+import { MongoDatasetData } from '@fastgpt/service/core/dataset/data/schema';
+import { MongoDatasetCollection } from '@fastgpt/service/core/dataset/collection/schema';
+import { DatasetStatusEnum, TrainingModeEnum } from '@fastgpt/global/core/dataset/constant';
+import { MongoDataset } from '@fastgpt/service/core/dataset/schema';
+
+let success = 0;
+/* pg 中的数据搬到 mongo dataset.datas 中，并做映射 */
+export default async function handler(req: NextApiRequest, res: NextApiResponse) {
+  try {
+    const { limit = 50 } = req.body as { limit: number };
+    await authCert({ req, authRoot: true });
+    await connectToDatabase();
+    success = 0;
+
+    await MongoDatasetCollection.updateMany({ createTime: { $exists: false } }, [
+      {
+        $set: {
+          createTime: '$updateTime'
+        }
+      }
+    ]);
+    await MongoDatasetCollection.updateMany({ trainingType: { $exists: false } }, [
+      {
+        $set: {
+          trainingType: {
+            $cond: {
+              if: { $ifNull: ['$a', false] },
+              then: TrainingModeEnum.qa,
+              else: TrainingModeEnum.chunk
+            }
+          }
+        }
+      }
+    ]);
+    await MongoDatasetCollection.updateMany({ chunkSize: { $exists: false } }, [
+      {
+        $set: {
+          chunkSize: 0
+        }
+      }
+    ]);
+    await MongoDatasetCollection.updateMany({ fileId: { $exists: false } }, [
+      {
+        $set: {
+          fileId: '$metadata.fileId'
+        }
+      }
+    ]);
+    await MongoDatasetCollection.updateMany({ rawLink: { $exists: false } }, [
+      {
+        $set: {
+          rawLink: '$metadata.rawLink'
+        }
+      }
+    ]);
+
+    await MongoDatasetData.updateMany(
+      { chunkIndex: { $exists: false } },
+      {
+        chunkIndex: 0
+      }
+    );
+    await MongoDatasetData.updateMany(
+      { updateTime: { $exists: false } },
+      {
+        updateTime: new Date()
+      }
+    );
+
+    await MongoDataset.updateMany(
+      { status: { $exists: false } },
+      {
+        $set: {
+          status: DatasetStatusEnum.active
+        }
+      }
+    );
+
+    // dataset tags to intro
+    await MongoDataset.updateMany({ tags: { $exists: true } }, [
+      {
+        $set: {
+          intro: {
+            $reduce: {
+              input: '$tags',
+              initialValue: '',
+              in: { $concat: ['$$value', ' ', '$$this'] }
+            }
+          }
+        }
+      }
+    ]);
+
+    jsonRes(res, {
+      message: 'success'
+    });
+  } catch (error) {
+    console.log(error);
+
+    jsonRes(res, {
+      code: 500,
+      error
+    });
+  }
+}
--- a/projects/app/src/pages/api/admin/timeTasks/checkUnValidDatasetFiles.ts
+++ b/projects/app/src/pages/api/admin/timeTasks/checkUnValidDatasetFiles.ts
@@ -0,0 +1,92 @@
+import type { NextApiRequest, NextApiResponse } from 'next';
+import { jsonRes } from '@fastgpt/service/common/response';
+import { connectToDatabase } from '@/service/mongo';
+import { authCert } from '@fastgpt/service/support/permission/auth/common';
+import { delFileById, getGFSCollection } from '@fastgpt/service/common/file/gridfs/controller';
+import { addLog } from '@fastgpt/service/common/mongo/controller';
+import { MongoDatasetCollection } from '@fastgpt/service/core/dataset/collection/schema';
+import { delay } from '@fastgpt/global/common/system/utils';
+
+/* 
+  check dataset.files data. If there is no match in dataset.collections, delete it
+*/
+let deleteFileAmount = 0;
+
+export default async function handler(req: NextApiRequest, res: NextApiResponse) {
+  try {
+    const {
+      startDay = 10,
+      endDay = 3,
+      limit = 30
+    } = req.body as { startDay?: number; endDay?: number; limit?: number };
+    await authCert({ req, authRoot: true });
+    await connectToDatabase();
+
+    // start: now - maxDay, end: now - 3 day
+    const start = new Date(Date.now() - startDay * 24 * 60 * 60 * 1000);
+    const end = new Date(Date.now() - endDay * 24 * 60 * 60 * 1000);
+    deleteFileAmount = 0;
+
+    checkFiles(start, end, limit);
+
+    jsonRes(res, {
+      message: 'success'
+    });
+  } catch (error) {
+    addLog.error(`check valid dataset files error`, error);
+
+    jsonRes(res, {
+      code: 500,
+      error
+    });
+  }
+}
+
+export async function checkFiles(start: Date, end: Date, limit: number) {
+  const collection = getGFSCollection('dataset');
+  const where = {
+    uploadDate: { $gte: start, $lte: end }
+  };
+
+  // 1. get all _id
+  const ids = await collection
+    .find(where, {
+      projection: {
+        _id: 1
+      }
+    })
+    .toArray();
+  console.log('total files', ids.length);
+
+  for (let i = 0; i < limit; i++) {
+    check(i);
+  }
+
+  async function check(index: number): Promise<any> {
+    const id = ids[index];
+    if (!id) {
+      console.log(`检测完成，共删除 ${deleteFileAmount} 个无效文件`);
+
+      return;
+    }
+    try {
+      const { _id } = id;
+
+      // 2. find fileId in dataset.collections
+      const hasCollection = await MongoDatasetCollection.countDocuments({ fileId: _id });
+
+      // 3. if not found, delete file
+      if (hasCollection === 0) {
+        await delFileById({ bucketName: 'dataset', fileId: String(_id) });
+        console.log('delete file', _id);
+        deleteFileAmount++;
+      }
+      index % 100 === 0 && console.log(index);
+      return check(index + limit);
+    } catch (error) {
+      console.log(error);
+      await delay(2000);
+      return check(index);
+    }
+  }
+}
--- a/projects/app/src/pages/api/common/file/read.ts
+++ b/projects/app/src/pages/api/common/file/read.ts
@@ -2,8 +2,8 @@ import type { NextApiRequest, NextApiResponse } from 'next';
 import { jsonRes } from '@fastgpt/service/common/response';
 import { connectToDatabase } from '@/service/mongo';
 import { authFileToken } from '@fastgpt/service/support/permission/controller';
-import jschardet from 'jschardet';
-import { getDownloadBuf, getFileById } from '@fastgpt/service/common/file/gridfs/controller';
+import { detect } from 'jschardet';
+import { getDownloadStream, getFileById } from '@fastgpt/service/common/file/gridfs/controller';

 export default async function handler(req: NextApiRequest, res: NextApiResponse<any>) {
  try {
@@ -11,24 +11,43 @@ export default async function handler(req: NextApiRequest, res: NextApiResponse<

    const { token } = req.query as { token: string };

-    const { fileId, teamId, tmbId, bucketName } = await authFileToken(token);
+    const { fileId, bucketName } = await authFileToken(token);

    if (!fileId) {
      throw new Error('fileId is empty');
    }

-    const [file, buffer] = await Promise.all([
+    const [file, encodeStream] = await Promise.all([
      getFileById({ bucketName, fileId }),
-      getDownloadBuf({ bucketName, fileId })
+      getDownloadStream({ bucketName, fileId })
    ]);

-    const encoding = jschardet.detect(buffer)?.encoding;
+    // get encoding
+    let buffers: Buffer = Buffer.from([]);
+    for await (const chunk of encodeStream) {
+      buffers = Buffer.concat([buffers, chunk]);
+      if (buffers.length > 10) {
+        encodeStream.abort();
+        break;
+      }
+    }
+
+    const encoding = detect(buffers)?.encoding || 'utf-8';

    res.setHeader('Content-Type', `${file.contentType}; charset=${encoding}`);
    res.setHeader('Cache-Control', 'public, max-age=3600');
    res.setHeader('Content-Disposition', `inline; filename="${encodeURIComponent(file.filename)}"`);

-    res.end(buffer);
+    const fileStream = await getDownloadStream({ bucketName, fileId });
+
+    fileStream.pipe(res);
+
+    fileStream.on('error', () => {
+      res.status(500).end();
+    });
+    fileStream.on('end', () => {
+      res.end();
+    });
  } catch (error) {
    jsonRes(res, {
      code: 500,
--- a/projects/app/src/pages/api/core/chat/chatTest.ts
+++ b/projects/app/src/pages/api/core/chat/chatTest.ts
@@ -52,12 +52,12 @@ export default async function handler(req: NextApiRequest, res: NextApiResponse)
    /* start process */
    const { responseData } = await dispatchModules({
      res,
-      appId,
-      modules,
-      variables,
      teamId,
      tmbId,
      user,
+      appId,
+      modules,
+      variables,
      params: {
        history,
        userChatInput: prompt
--- a/projects/app/src/pages/api/core/chat/update.ts
+++ b/projects/app/src/pages/api/core/chat/update.ts
@@ -13,10 +13,13 @@ export default async function handler(req: NextApiRequest, res: NextApiResponse)

    await authChat({ req, authToken: true, chatId });

-    await MongoChat.findByIdAndUpdate(chatId, {
-      ...(customTitle ? { customTitle } : {}),
-      ...(top ? { top } : { top: null })
-    });
+    await MongoChat.findOneAndUpdate(
+      { chatId },
+      {
+        ...(customTitle !== undefined && { customTitle }),
+        ...(top !== undefined && { top })
+      }
+    );
    jsonRes(res);
  } catch (err) {
    jsonRes(res, {
--- a/projects/app/src/pages/api/core/dataset/allDataset.ts
+++ b/projects/app/src/pages/api/core/dataset/allDataset.ts
@@ -2,10 +2,11 @@ import type { NextApiRequest, NextApiResponse } from 'next';
 import { jsonRes } from '@fastgpt/service/common/response';
 import { connectToDatabase } from '@/service/mongo';
 import { MongoDataset } from '@fastgpt/service/core/dataset/schema';
-import { getQAModel, getVectorModel } from '@/service/core/ai/model';
-import type { DatasetItemType } from '@fastgpt/global/core/dataset/type.d';
+import { getVectorModel } from '@/service/core/ai/model';
+import type { DatasetListItemType } from '@fastgpt/global/core/dataset/type.d';
 import { mongoRPermission } from '@fastgpt/global/support/permission/utils';
 import { authUserRole } from '@fastgpt/service/support/permission/auth/user';
+import { DatasetTypeEnum } from '@fastgpt/global/core/dataset/constant';

 /* get all dataset by teamId or tmbId */
 export default async function handler(req: NextApiRequest, res: NextApiResponse<any>) {
@@ -16,18 +17,23 @@ export default async function handler(req: NextApiRequest, res: NextApiResponse<

    const datasets = await MongoDataset.find({
      ...mongoRPermission({ teamId, tmbId, role }),
-      type: 'dataset'
+      type: { $ne: DatasetTypeEnum.folder }
    }).lean();

    const data = datasets.map((item) => ({
-      ...item,
+      _id: item._id,
+      parentId: item.parentId,
+      avatar: item.avatar,
+      name: item.name,
+      intro: item.intro,
+      type: item.type,
+      permission: item.permission,
      vectorModel: getVectorModel(item.vectorModel),
-      agentModel: getQAModel(item.agentModel),
      canWrite: String(item.tmbId) === tmbId,
      isOwner: teamOwner || String(item.tmbId) === tmbId
    }));

-    jsonRes<DatasetItemType[]>(res, {
+    jsonRes<DatasetListItemType[]>(res, {
      data
    });
  } catch (err) {
--- a/projects/app/src/pages/api/core/dataset/collection/create.ts
+++ b/projects/app/src/pages/api/core/dataset/collection/create.ts
@@ -4,12 +4,10 @@
 import type { NextApiRequest, NextApiResponse } from 'next';
 import { jsonRes } from '@fastgpt/service/common/response';
 import { connectToDatabase } from '@/service/mongo';
-import type { CreateDatasetCollectionParams } from '@/global/core/api/datasetReq.d';
-import { MongoDatasetCollection } from '@fastgpt/service/core/dataset/collection/schema';
-import { DatasetCollectionTypeEnum } from '@fastgpt/global/core/dataset/constant';
-import { getCollectionUpdateTime } from '@fastgpt/service/core/dataset/collection/utils';
+import type { CreateDatasetCollectionParams } from '@fastgpt/global/core/dataset/api.d';
 import { authUserNotVisitor } from '@fastgpt/service/support/permission/auth/user';
 import { authDataset } from '@fastgpt/service/support/permission/auth/dataset';
+import { createOneCollection } from '@fastgpt/service/core/dataset/collection/controller';

 export default async function handler(req: NextApiRequest, res: NextApiResponse<any>) {
  try {
@@ -39,62 +37,3 @@ export default async function handler(req: NextApiRequest, res: NextApiResponse<
    });
  }
 }
-
-export async function createOneCollection({
-  name,
-  parentId,
-  datasetId,
-  type,
-  metadata = {},
-  teamId,
-  tmbId
-}: CreateDatasetCollectionParams & { teamId: string; tmbId: string }) {
-  const { _id } = await MongoDatasetCollection.create({
-    name,
-    teamId,
-    tmbId,
-    datasetId,
-    parentId: parentId || null,
-    type,
-    metadata,
-    updateTime: getCollectionUpdateTime({ name })
-  });
-
-  // create default collection
-  if (type === DatasetCollectionTypeEnum.folder) {
-    await createDefaultCollection({
-      datasetId,
-      parentId: _id,
-      teamId,
-      tmbId
-    });
-  }
-
-  return _id;
-}
-
-// create default collection
-export function createDefaultCollection({
-  name = '手动录入',
-  datasetId,
-  parentId,
-  teamId,
-  tmbId
-}: {
-  name?: '手动录入' | '手动标注';
-  datasetId: string;
-  parentId?: string;
-  teamId: string;
-  tmbId: string;
-}) {
-  return MongoDatasetCollection.create({
-    name,
-    teamId,
-    tmbId,
-    datasetId,
-    parentId,
-    type: DatasetCollectionTypeEnum.virtual,
-    updateTime: new Date('2099'),
-    metadata: {}
-  });
-}
--- a/projects/app/src/pages/api/core/dataset/collection/delById.ts
+++ b/projects/app/src/pages/api/core/dataset/collection/delById.ts
@@ -1,13 +1,10 @@
 import type { NextApiRequest, NextApiResponse } from 'next';
 import { jsonRes } from '@fastgpt/service/common/response';
 import { connectToDatabase } from '@/service/mongo';
-import { MongoDatasetTraining } from '@fastgpt/service/core/dataset/training/schema';
 import { findCollectionAndChild } from '@fastgpt/service/core/dataset/collection/utils';
-import { delDataByCollectionId } from '@/service/core/dataset/data/controller';
-import { MongoDatasetCollection } from '@fastgpt/service/core/dataset/collection/schema';
+import { delCollectionRelevantData } from '@fastgpt/service/core/dataset/data/controller';
 import { authDatasetCollection } from '@fastgpt/service/support/permission/auth/dataset';
-import { delFileById } from '@fastgpt/service/common/file/gridfs/controller';
-import { BucketNameEnum } from '@fastgpt/global/common/file/constants';
+import { MongoDatasetCollection } from '@fastgpt/service/core/dataset/collection/schema';

 export default async function handler(req: NextApiRequest, res: NextApiResponse<any>) {
  try {
@@ -19,7 +16,7 @@ export default async function handler(req: NextApiRequest, res: NextApiResponse<
      throw new Error('CollectionIdId is required');
    }

-    const { teamId } = await authDatasetCollection({
+    await authDatasetCollection({
      req,
      authToken: true,
      collectionId,
@@ -30,26 +27,12 @@ export default async function handler(req: NextApiRequest, res: NextApiResponse<
    const collections = await findCollectionAndChild(collectionId, '_id metadata');
    const delIdList = collections.map((item) => item._id);

-    // delete training data
-    await MongoDatasetTraining.deleteMany({
-      collectionId: { $in: delIdList },
-      teamId
+    // delete
+    await delCollectionRelevantData({
+      collectionIds: delIdList,
+      fileIds: collections.map((item) => String(item.metadata?.fileId)).filter(Boolean)
    });

-    // delete pg data
-    await delDataByCollectionId({ collectionIds: delIdList });
-
-    // delete file
-    await Promise.all(
-      collections.map((collection) => {
-        if (!collection.metadata?.fileId) return;
-        return delFileById({
-          bucketName: BucketNameEnum.dataset,
-          fileId: collection.metadata.fileId
-        });
-      })
-    );
-
    // delete collection
    await MongoDatasetCollection.deleteMany({
      _id: { $in: delIdList }
--- a/projects/app/src/pages/api/core/dataset/collection/detail.ts
+++ b/projects/app/src/pages/api/core/dataset/collection/detail.ts
@@ -6,6 +6,8 @@ import { jsonRes } from '@fastgpt/service/common/response';
 import { connectToDatabase } from '@/service/mongo';
 import { authDatasetCollection } from '@fastgpt/service/support/permission/auth/dataset';
 import { DatasetCollectionItemType } from '@fastgpt/global/core/dataset/type';
+import { BucketNameEnum } from '@fastgpt/global/common/file/constants';
+import { getFileById } from '@fastgpt/service/common/file/gridfs/controller';

 export default async function handler(req: NextApiRequest, res: NextApiResponse<any>) {
  try {
@@ -24,12 +26,18 @@ export default async function handler(req: NextApiRequest, res: NextApiResponse<
      per: 'r'
    });

+    // get file
+    const file = collection?.fileId
+      ? await getFileById({ bucketName: BucketNameEnum.dataset, fileId: collection.fileId })
+      : undefined;
+
    jsonRes<DatasetCollectionItemType>(res, {
      data: {
        ...collection,
        canWrite,
        sourceName: collection?.name,
-        sourceId: collection?.metadata?.fileId || collection?.metadata?.rawLink
+        sourceId: collection?.fileId || collection?.rawLink,
+        file
      }
    });
  } catch (err) {
--- a/projects/app/src/pages/api/core/dataset/collection/list.ts
+++ b/projects/app/src/pages/api/core/dataset/collection/list.ts
@@ -6,7 +6,10 @@ import { Types } from '@fastgpt/service/common/mongo';
 import type { DatasetCollectionsListItemType } from '@/global/core/dataset/type.d';
 import type { GetDatasetCollectionsProps } from '@/global/core/api/datasetReq';
 import { PagingData } from '@/types';
-import { MongoDatasetCollection } from '@fastgpt/service/core/dataset/collection/schema';
+import {
+  DatasetColCollectionName,
+  MongoDatasetCollection
+} from '@fastgpt/service/core/dataset/collection/schema';
 import { DatasetCollectionTypeEnum } from '@fastgpt/global/core/dataset/constant';
 import { startQueue } from '@/service/utils/tools';
 import { authDataset } from '@fastgpt/service/support/permission/auth/dataset';
@@ -45,7 +48,7 @@ export default async function handler(req: NextApiRequest, res: NextApiResponse<

    // not count data amount
    if (simple) {
-      const collections = await MongoDatasetCollection.find(match, '_id name type parentId')
+      const collections = await MongoDatasetCollection.find(match, '_id parentId type name')
        .sort({
          updateTime: -1
        })
@@ -72,6 +75,7 @@ export default async function handler(req: NextApiRequest, res: NextApiResponse<
        {
          $match: match
        },
+        // count training data
        {
          $lookup: {
            from: DatasetTrainingCollectionName,
@@ -89,6 +93,7 @@ export default async function handler(req: NextApiRequest, res: NextApiResponse<
            as: 'trainings'
          }
        },
+        // count collection total data
        {
          $lookup: {
            from: DatasetDataCollectionName,
@@ -106,7 +111,6 @@ export default async function handler(req: NextApiRequest, res: NextApiResponse<
            as: 'datas'
          }
        },
-        // 统计子集合的数量和子训练的数量
        {
          $project: {
            _id: 1,
@@ -114,10 +118,12 @@ export default async function handler(req: NextApiRequest, res: NextApiResponse<
            tmbId: 1,
            name: 1,
            type: 1,
+            status: 1,
            updateTime: 1,
-            trainingAmount: { $size: '$trainings' },
            dataAmount: { $size: '$datas' },
-            metadata: 1
+            trainingAmount: { $size: '$trainings' },
+            fileId: 1,
+            rawLink: 1
          }
        },
        {
--- a/projects/app/src/pages/api/core/dataset/collection/update.ts
+++ b/projects/app/src/pages/api/core/dataset/collection/update.ts
@@ -9,7 +9,7 @@ import { authDatasetCollection } from '@fastgpt/service/support/permission/auth/
 export default async function handler(req: NextApiRequest, res: NextApiResponse<any>) {
  try {
    await connectToDatabase();
-    const { id, parentId, name, metadata = {} } = req.body as UpdateDatasetCollectionParams;
+    const { id, parentId, name } = req.body as UpdateDatasetCollectionParams;

    if (!id) {
      throw new Error('缺少参数');
@@ -23,11 +23,6 @@ export default async function handler(req: NextApiRequest, res: NextApiResponse<
      ...(name && { name, updateTime: getCollectionUpdateTime({ name }) })
    };

-    // 将metadata的每个字段添加到updateFields中
-    for (const [key, value] of Object.entries(metadata)) {
-      updateFields[`metadata.${key}`] = value;
-    }
-
    await MongoDatasetCollection.findByIdAndUpdate(id, {
      $set: updateFields
    });
--- a/projects/app/src/pages/api/core/dataset/create.ts
+++ b/projects/app/src/pages/api/core/dataset/create.ts
@@ -3,20 +3,20 @@ import { jsonRes } from '@fastgpt/service/common/response';
 import { connectToDatabase } from '@/service/mongo';
 import { MongoDataset } from '@fastgpt/service/core/dataset/schema';
 import type { CreateDatasetParams } from '@/global/core/dataset/api.d';
-import { createDefaultCollection } from './collection/create';
+import { createDefaultCollection } from '@fastgpt/service/core/dataset/collection/controller';
 import { authUserNotVisitor } from '@fastgpt/service/support/permission/auth/user';
+import { DatasetTypeEnum } from '@fastgpt/global/core/dataset/constant';

 export default async function handler(req: NextApiRequest, res: NextApiResponse<any>) {
  try {
    await connectToDatabase();
    const {
+      parentId,
      name,
-      tags,
+      type,
      avatar,
      vectorModel = global.vectorModels[0].model,
-      agentModel,
-      parentId,
-      type
+      agentModel
    } = req.body as CreateDatasetParams;

    // 凭证校验
@@ -26,7 +26,6 @@ export default async function handler(req: NextApiRequest, res: NextApiResponse<
      name,
      teamId,
      tmbId,
-      tags,
      vectorModel,
      agentModel,
      avatar,
@@ -34,11 +33,13 @@ export default async function handler(req: NextApiRequest, res: NextApiResponse<
      type
    });

-    await createDefaultCollection({
-      datasetId: _id,
-      teamId,
-      tmbId
-    });
+    if (type === DatasetTypeEnum.dataset) {
+      await createDefaultCollection({
+        datasetId: _id,
+        teamId,
+        tmbId
+      });
+    }

    jsonRes(res, { data: _id });
  } catch (err) {
--- a/projects/app/src/pages/api/core/dataset/data/delete.ts
+++ b/projects/app/src/pages/api/core/dataset/data/delete.ts
@@ -3,7 +3,7 @@ import { jsonRes } from '@fastgpt/service/common/response';
 import { withNextCors } from '@fastgpt/service/common/middle/cors';
 import { connectToDatabase } from '@/service/mongo';
 import { authDatasetData } from '@/service/support/permission/auth/dataset';
-import { deleteDataByDataId } from '@/service/core/dataset/data/controller';
+import { delDatasetDataByDataId } from '@fastgpt/service/core/dataset/data/controller';

 export default withNextCors(async function handler(req: NextApiRequest, res: NextApiResponse<any>) {
  try {
@@ -19,7 +19,7 @@ export default withNextCors(async function handler(req: NextApiRequest, res: Nex
    // 凭证校验
    await authDatasetData({ req, authToken: true, dataId, per: 'w' });

-    await deleteDataByDataId(dataId);
+    await delDatasetDataByDataId(dataId);

    jsonRes(res, {
      data: 'success'
--- a/projects/app/src/pages/api/core/dataset/data/insertData.ts
+++ b/projects/app/src/pages/api/core/dataset/data/insertData.ts
@@ -76,6 +76,7 @@ export default withNextCors(async function handler(req: NextApiRequest, res: Nex
      collectionId,
      q: formatQ,
      a: formatA,
+      chunkIndex: 0,
      model: vectorModelData.model,
      indexes: formatIndexes
    });
--- a/projects/app/src/pages/api/core/dataset/data/list.ts
+++ b/projects/app/src/pages/api/core/dataset/data/list.ts
@@ -32,8 +32,8 @@ export default async function handler(req: NextApiRequest, res: NextApiResponse<
    };

    const [data, total] = await Promise.all([
-      MongoDatasetData.find(match, '_id datasetId collectionId q a  indexes')
-        .sort({ _id: -1 })
+      MongoDatasetData.find(match, '_id datasetId collectionId q a indexes')
+        .sort({ chunkIndex: 1, updateTime: -1 })
        .skip((pageNum - 1) * pageSize)
        .limit(pageSize)
        .lean(),
--- a/projects/app/src/pages/api/core/dataset/data/pushData.ts
+++ b/projects/app/src/pages/api/core/dataset/data/pushData.ts
@@ -125,7 +125,7 @@ export async function pushDataToDatasetCollection({

  // 插入记录
  const insertRes = await MongoDatasetTraining.insertMany(
-    filterResult.success.map((item) => ({
+    filterResult.success.map((item, i) => ({
      teamId,
      tmbId,
      datasetId,
@@ -136,6 +136,7 @@ export async function pushDataToDatasetCollection({
      model,
      q: item.q,
      a: item.a,
+      chunkIndex: i,
      indexes: item.indexes
    }))
  );
--- a/projects/app/src/pages/api/core/dataset/delete.ts
+++ b/projects/app/src/pages/api/core/dataset/delete.ts
@@ -1,14 +1,10 @@
 import type { NextApiRequest, NextApiResponse } from 'next';
 import { jsonRes } from '@fastgpt/service/common/response';
 import { connectToDatabase } from '@/service/mongo';
-import { MongoDatasetTraining } from '@fastgpt/service/core/dataset/training/schema';
-import { MongoDataset } from '@fastgpt/service/core/dataset/schema';
-import { delDatasetFiles } from '@fastgpt/service/core/dataset/file/controller';
-import { Types } from '@fastgpt/service/common/mongo';
-import { MongoDatasetCollection } from '@fastgpt/service/core/dataset/collection/schema';
 import { authDataset } from '@fastgpt/service/support/permission/auth/dataset';
-import { delDataByDatasetId } from '@/service/core/dataset/data/controller';
+import { delDatasetRelevantData } from '@fastgpt/service/core/dataset/data/controller';
 import { findDatasetIdTreeByTopDatasetId } from '@fastgpt/service/core/dataset/controller';
+import { MongoDataset } from '@fastgpt/service/core/dataset/schema';

 export default async function handler(req: NextApiRequest, res: NextApiResponse<any>) {
  try {
@@ -26,21 +22,8 @@ export default async function handler(req: NextApiRequest, res: NextApiResponse<

    const deletedIds = await findDatasetIdTreeByTopDatasetId(id);

-    // delete training data(There could be a training mission)
-    await MongoDatasetTraining.deleteMany({
-      datasetId: { $in: deletedIds }
-    });
-
    // delete all dataset.data and pg data
-    await delDataByDatasetId({ datasetIds: deletedIds });
-
-    // delete related files
-    await delDatasetFiles({ datasetId: id });
-
-    // delete collections
-    await MongoDatasetCollection.deleteMany({
-      datasetId: { $in: deletedIds }
-    });
+    await delDatasetRelevantData({ datasetIds: deletedIds });

    // delete dataset data
    await MongoDataset.deleteMany({
--- a/projects/app/src/pages/api/core/dataset/list.ts
+++ b/projects/app/src/pages/api/core/dataset/list.ts
@@ -1,12 +1,12 @@
 import type { NextApiRequest, NextApiResponse } from 'next';
 import { jsonRes } from '@fastgpt/service/common/response';
 import { connectToDatabase } from '@/service/mongo';
-import { getQAModel, getVectorModel } from '@/service/core/ai/model';
-import type { DatasetItemType } from '@fastgpt/global/core/dataset/type.d';
+import type { DatasetListItemType } from '@fastgpt/global/core/dataset/type.d';
 import { DatasetTypeEnum } from '@fastgpt/global/core/dataset/constant';
 import { MongoDataset } from '@fastgpt/service/core/dataset/schema';
 import { mongoRPermission } from '@fastgpt/global/support/permission/utils';
 import { authUserRole } from '@fastgpt/service/support/permission/auth/user';
+import { getVectorModel } from '@/service/core/ai/model';

 export default async function handler(req: NextApiRequest, res: NextApiResponse<any>) {
  try {
@@ -27,16 +27,21 @@ export default async function handler(req: NextApiRequest, res: NextApiResponse<
      .lean();

    const data = await Promise.all(
-      datasets.map(async (item) => ({
-        ...item,
-        vectorModel: getVectorModel(item.vectorModel),
-        agentModel: getQAModel(item.agentModel),
+      datasets.map<DatasetListItemType>((item) => ({
+        _id: item._id,
+        parentId: item.parentId,
+        avatar: item.avatar,
+        name: item.name,
+        intro: item.intro,
+        type: item.type,
+        permission: item.permission,
        canWrite,
-        isOwner: teamOwner || String(item.tmbId) === tmbId
+        isOwner: teamOwner || String(item.tmbId) === tmbId,
+        vectorModel: getVectorModel(item.vectorModel)
      }))
    );

-    jsonRes<DatasetItemType[]>(res, {
+    jsonRes<DatasetListItemType[]>(res, {
      data
    });
  } catch (err) {
--- a/projects/app/src/pages/api/core/dataset/searchTest.ts
+++ b/projects/app/src/pages/api/core/dataset/searchTest.ts
@@ -44,7 +44,7 @@ export default withNextCors(async function handler(req: NextApiRequest, res: Nex
    });

    // push bill
-    pushGenerateVectorBill({
+    const { total } = pushGenerateVectorBill({
      teamId,
      tmbId,
      tokenLen: tokenLen,
@@ -54,11 +54,7 @@ export default withNextCors(async function handler(req: NextApiRequest, res: Nex
    if (apikey) {
      updateApiKeyUsage({
        apikey,
-        usage: countModelPrice({
-          model: dataset.vectorModel,
-          tokens: tokenLen,
-          type: ModelTypeEnum.vector
-        })
+        usage: total
      });
    }

--- a/projects/app/src/pages/api/core/dataset/update.ts
+++ b/projects/app/src/pages/api/core/dataset/update.ts
@@ -2,14 +2,14 @@ import type { NextApiRequest, NextApiResponse } from 'next';
 import { jsonRes } from '@fastgpt/service/common/response';
 import { connectToDatabase } from '@/service/mongo';
 import { MongoDataset } from '@fastgpt/service/core/dataset/schema';
-import type { DatasetUpdateParams } from '@/global/core/api/datasetReq.d';
+import type { DatasetUpdateBody } from '@fastgpt/global/core/dataset/api.d';
 import { authDataset } from '@fastgpt/service/support/permission/auth/dataset';

 export default async function handler(req: NextApiRequest, res: NextApiResponse<any>) {
  try {
    await connectToDatabase();
-    const { id, parentId, name, avatar, tags, permission, agentModel } =
-      req.body as DatasetUpdateParams;
+    const { id, parentId, name, avatar, tags, permission, agentModel, websiteConfig, status } =
+      req.body as DatasetUpdateBody;

    if (!id) {
      throw new Error('缺少参数');
@@ -28,7 +28,9 @@ export default async function handler(req: NextApiRequest, res: NextApiResponse<
        ...(avatar && { avatar }),
        ...(tags && { tags }),
        ...(permission && { permission }),
-        ...(agentModel && { agentModel: agentModel.model })
+        ...(agentModel && { agentModel: agentModel.model }),
+        ...(websiteConfig && { websiteConfig }),
+        ...(status && { status })
      }
    );

--- a/projects/app/src/pages/api/core/plugin/templates.ts
+++ b/projects/app/src/pages/api/core/plugin/templates.ts
@@ -16,7 +16,7 @@ export default async function handler(req: NextApiRequest, res: NextApiResponse<

    const [userPlugins, plusPlugins] = await Promise.all([
      MongoPlugin.find({ teamId }).lean(),
-      GET<PluginTemplateType[]>('/core/plugin/getTemplates')
+      global.systemEnv.pluginBaseUrl ? GET<PluginTemplateType[]>('/core/plugin/getTemplates') : []
    ]);

    const data: FlowModuleTemplateType[] = [
--- a/projects/app/src/pages/api/plugins/urlFetch.ts
+++ b/projects/app/src/pages/api/plugins/urlFetch.ts
@@ -1,73 +0,0 @@
-// pages/api/fetchContent.ts
-import { NextApiRequest, NextApiResponse } from 'next';
-import axios from 'axios';
-import { JSDOM } from 'jsdom';
-import { Readability } from '@mozilla/readability';
-import { jsonRes } from '@fastgpt/service/common/response';
-import { authCert } from '@fastgpt/service/support/permission/auth/common';
-import type { FetchResultItem } from '@fastgpt/global/common/plugin/types/pluginRes.d';
-import { simpleText } from '@fastgpt/global/common/string/tools';
-import { connectToDatabase } from '@/service/mongo';
-
-export type UrlFetchResponse = FetchResultItem[];
-
-const fetchContent = async (req: NextApiRequest, res: NextApiResponse) => {
-  try {
-    await connectToDatabase();
-    let { urlList = [] } = req.body as { urlList: string[] };
-
-    if (!urlList || urlList.length === 0) {
-      throw new Error('urlList is empty');
-    }
-
-    await authCert({ req, authToken: true });
-
-    urlList = urlList.filter((url) => /^(http|https):\/\/[^ "]+$/.test(url));
-
-    const response = (
-      await Promise.allSettled(
-        urlList.map(async (url) => {
-          try {
-            const fetchRes = await axios.get(url, {
-              timeout: 30000
-            });
-
-            const dom = new JSDOM(fetchRes.data, {
-              url,
-              contentType: 'text/html'
-            });
-
-            const reader = new Readability(dom.window.document);
-            const article = reader.parse();
-
-            const content = article?.textContent || '';
-
-            return {
-              url,
-              content: simpleText(`${article?.title}\n${content}`)
-            };
-          } catch (error) {
-            return {
-              url,
-              content: ''
-            };
-          }
-        })
-      )
-    )
-      .filter((item) => item.status === 'fulfilled')
-      .map((item: any) => item.value)
-      .filter((item) => item.content);
-
-    jsonRes<UrlFetchResponse>(res, {
-      data: response
-    });
-  } catch (error: any) {
-    jsonRes(res, {
-      code: 500,
-      error: error
-    });
-  }
-};
-
-export default fetchContent;
--- a/projects/app/src/pages/api/support/wallet/bill/createTrainingBill.ts
+++ b/projects/app/src/pages/api/support/wallet/bill/createTrainingBill.ts
@@ -24,13 +24,13 @@ export default async function handler(req: NextApiRequest, res: NextApiResponse)
      source: BillSourceEnum.training,
      list: [
        {
-          moduleName: '索引生成',
+          moduleName: 'wallet.moduleName.index',
          model: vectorModelData.name,
          amount: 0,
          tokenLen: 0
        },
        {
-          moduleName: 'QA 拆分',
+          moduleName: 'wallet.moduleName.qa',
          model: agentModelData.name,
          amount: 0,
          tokenLen: 0
--- a/projects/app/src/pages/api/tools/urlFetch.ts
+++ b/projects/app/src/pages/api/tools/urlFetch.ts
@@ -0,0 +1,34 @@
+// pages/api/fetchContent.ts
+import { NextApiRequest, NextApiResponse } from 'next';
+import { jsonRes } from '@fastgpt/service/common/response';
+import { authCert } from '@fastgpt/service/support/permission/auth/common';
+import { connectToDatabase } from '@/service/mongo';
+import { UrlFetchParams, UrlFetchResponse } from '@fastgpt/global/common/file/api.d';
+import { urlsFetch } from '@fastgpt/global/common/file/tools';
+
+const fetchContent = async (req: NextApiRequest, res: NextApiResponse) => {
+  try {
+    await connectToDatabase();
+    let { urlList = [], selector } = req.body as UrlFetchParams;
+
+    if (!urlList || urlList.length === 0) {
+      throw new Error('urlList is empty');
+    }
+
+    await authCert({ req, authToken: true });
+
+    jsonRes<UrlFetchResponse>(res, {
+      data: await urlsFetch({
+        urlList,
+        selector
+      })
+    });
+  } catch (error: any) {
+    jsonRes(res, {
+      code: 500,
+      error: error
+    });
+  }
+};
+
+export default fetchContent;
--- a/projects/app/src/pages/api/v1/chat/completions.ts
+++ b/projects/app/src/pages/api/v1/chat/completions.ts
@@ -14,10 +14,10 @@ import { getChatHistory } from './getHistory';
 import { saveChat } from '@/service/utils/chat/saveChat';
 import { responseWrite } from '@fastgpt/service/common/response';
 import { pushChatBill } from '@/service/support/wallet/bill/push';
-import { BillSourceEnum } from '@fastgpt/global/support/wallet/bill/constants';
 import { authOutLinkChat } from '@/service/support/permission/auth/outLink';
 import { pushResult2Remote, updateOutLinkUsage } from '@fastgpt/service/support/outLink/tools';
 import requestIp from 'request-ip';
+import { getBillSourceByAuthType } from '@fastgpt/global/support/wallet/bill/tools';

 import { selectShareResponse } from '@/utils/service/core/chat';
 import { updateApiKeyUsage } from '@fastgpt/service/support/openapi/tools';
@@ -142,7 +142,7 @@ export default withNextCors(async function handler(req: NextApiRequest, res: Nex
          responseDetail: detail,
          apikey,
          authType,
-          canWrite: false
+          canWrite: true
        };
      }

@@ -276,11 +276,7 @@ export default withNextCors(async function handler(req: NextApiRequest, res: Nex
      appId: app._id,
      teamId: user.team.teamId,
      tmbId: user.team.tmbId,
-      source: (() => {
-        if (authType === 'apikey') return BillSourceEnum.api;
-        if (shareId) return BillSourceEnum.shareLink;
-        return BillSourceEnum.fastgpt;
-      })(),
+      source: getBillSourceByAuthType({ shareId, authType }),
      response: responseData
    });

--- a/projects/app/src/pages/api/v1/embeddings.ts
+++ b/projects/app/src/pages/api/v1/embeddings.ts
@@ -6,6 +6,8 @@ import { pushGenerateVectorBill } from '@/service/support/wallet/bill/push';
 import { connectToDatabase } from '@/service/mongo';
 import { authTeamBalance } from '@/service/support/permission/auth/bill';
 import { getVectorsByText, GetVectorProps } from '@/service/core/ai/vector';
+import { updateApiKeyUsage } from '@fastgpt/service/support/openapi/tools';
+import { getBillSourceByAuthType } from '@fastgpt/global/support/wallet/bill/tools';

 type Props = GetVectorProps & {
  billId?: string;
@@ -15,24 +17,21 @@ export default withNextCors(async function handler(req: NextApiRequest, res: Nex
  try {
    let { input, model, billId } = req.body as Props;
    await connectToDatabase();
-    const { teamId, tmbId } = await authCert({ req, authToken: true, authApiKey: true });

-    if (!Array.isArray(input) || typeof input !== 'string') {
+    if (!Array.isArray(input) && typeof input !== 'string') {
      throw new Error('input is nor array or string');
    }

+    const { teamId, tmbId, apikey, authType } = await authCert({
+      req,
+      authToken: true,
+      authApiKey: true
+    });
+
    await authTeamBalance(teamId);

    const { tokenLen, vectors } = await getVectorsByText({ input, model });

-    pushGenerateVectorBill({
-      teamId,
-      tmbId,
-      tokenLen: tokenLen,
-      model,
-      billId
-    });
-
    jsonRes(res, {
      data: {
        object: 'list',
@@ -48,6 +47,22 @@ export default withNextCors(async function handler(req: NextApiRequest, res: Nex
        }
      }
    });
+
+    const { total } = pushGenerateVectorBill({
+      teamId,
+      tmbId,
+      tokenLen,
+      model,
+      billId,
+      source: getBillSourceByAuthType({ authType })
+    });
+
+    if (apikey) {
+      updateApiKeyUsage({
+        apikey,
+        usage: total
+      });
+    }
  } catch (err) {
    console.log(err);
    jsonRes(res, {
--- a/projects/app/src/pages/api/v1/rerank.ts
+++ b/projects/app/src/pages/api/v1/rerank.ts
@@ -7,12 +7,13 @@ import { connectToDatabase } from '@/service/mongo';
 import { authTeamBalance } from '@/service/support/permission/auth/bill';
 import { PostReRankProps, PostReRankResponse } from '@fastgpt/global/core/ai/api';
 import { reRankRecall } from '@/service/core/ai/rerank';
+import { updateApiKeyUsage } from '@fastgpt/service/support/openapi/tools';

 export default withNextCors(async function handler(req: NextApiRequest, res: NextApiResponse<any>) {
  let { query, inputs } = req.body as PostReRankProps;
  try {
    await connectToDatabase();
-    const { teamId, tmbId } = await authCert({
+    const { teamId, tmbId, apikey } = await authCert({
      req,
      authApiKey: true
    });
@@ -23,12 +24,19 @@ export default withNextCors(async function handler(req: NextApiRequest, res: Nex

    const result = await reRankRecall({ query, inputs });

-    pushReRankBill({
+    const { total } = pushReRankBill({
      teamId,
      tmbId,
      source: 'api'
    });

+    if (apikey) {
+      updateApiKeyUsage({
+        apikey,
+        usage: total
+      });
+    }
+
    jsonRes<PostReRankResponse>(res, {
      data: result
    });
--- a/projects/app/src/pages/app/detail/components/InfoModal.tsx
+++ b/projects/app/src/pages/app/detail/components/InfoModal.tsx
@@ -103,8 +103,8 @@ const InfoModal = ({
      try {
        const src = await compressImgFileAndUpload({
          file,
-          maxW: 100,
-          maxH: 100
+          maxW: 300,
+          maxH: 300
        });
        setValue('avatar', src);
        setRefresh((state) => !state);
--- a/projects/app/src/pages/app/detail/components/SimpleEdit/index.tsx
+++ b/projects/app/src/pages/app/detail/components/SimpleEdit/index.tsx
@@ -144,6 +144,7 @@ function ConfigForm({
      templateId: appDetail.simpleTemplateId,
      modules: appDetail.modules
    });
+
    reset(formVal);
    setTimeout(() => {
      setRefresh((state) => !state);
--- a/projects/app/src/pages/app/list/component/CreateModal.tsx
+++ b/projects/app/src/pages/app/list/component/CreateModal.tsx
@@ -60,8 +60,8 @@ const CreateModal = ({ onClose, onSuccess }: { onClose: () => void; onSuccess: (
      try {
        const src = await compressImgFileAndUpload({
          file,
-          maxW: 100,
-          maxH: 100
+          maxW: 300,
+          maxH: 300
        });
        setValue('avatar', src);
        setRefresh((state) => !state);
--- a/projects/app/src/pages/chat/index.tsx
+++ b/projects/app/src/pages/chat/index.tsx
@@ -328,7 +328,7 @@ const Chat = ({ appId, chatId }: { appId: string; chatId: string }) => {
              }}
              onSetCustomTitle={async (e) => {
                try {
-                  await putChatHistory({
+                  putChatHistory({
                    chatId: e.chatId,
                    customTitle: e.title
                  });
--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
Archer	9c77dfbddd	fix: img compress (#546 )	2023-12-03 23:56:45 +08:00
NongMO	7fc05af09e	fix: custom chat title (#534 ) * Fix: Update Custom Chat Title Based on chatId * remove `new:true` option * Update update.ts --------- Co-authored-by: Archer <545436317@qq.com>	2023-12-03 21:19:22 +08:00
Archer	a9ae270335	4.6.3-website dataset (#532 )	2023-12-03 20:45:57 +08:00
Archer	b916183848	4.6.3-alpha1 (#529 )	2023-11-29 20:45:36 +08:00
				`@@ -0,0 +1 @@`
				<?xml version="1.0" standalone="no"?><!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.1//EN" "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd"><svg t="1701410305116" class="icon" viewBox="0 0 1024 1024" version="1.1" xmlns="http://www.w3.org/2000/svg" p-id="8647" xmlns:xlink="http://www.w3.org/1999/xlink" width="128" height="128"><path d="M138.9056 180.5312m94.7712 0l563.3536 0q94.7712 0 94.7712 94.7712l0 576q0 94.7712-94.7712 94.7712l-563.3536 0q-94.7712 0-94.7712-94.7712l0-576q0-94.7712 94.7712-94.7712Z" fill="#CCDAFF" p-id="8648"></path><path d="M292.3008 81.92m64.768 0l305.3056 0q64.768 0 64.768 64.768l0 70.4q0 64.768-64.768 64.768l-305.3056 0q-64.768 0-64.768-64.768l0-70.4q0-64.768 64.768-64.768Z" fill="#7A7AF9" p-id="8649"></path><path d="M480.768 736.8704a49.408 49.408 0 0 1-34.7648-14.2848L332.8 611.3792a49.6128 49.6128 0 1 1 69.7344-70.7072l77.7216 76.4928L634.5216 460.8a49.6128 49.6128 0 1 1 70.6048 69.6832L516.096 721.92a49.6128 49.6128 0 0 1-35.328 14.9504z" fill="#7A7AF9" p-id="8650"></path></svg>