4.6.7 first pr (#726)

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

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

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

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

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

@@ -0,0 +1,11 @@
+import { MongoImageTypeEnum } from './constants';
+
+export type MongoImageSchemaType = {
+  teamId: string;
+  binary: Buffer;
+  createTime: Date;
+  expiredTime?: Date;
+  type: `${MongoImageTypeEnum}`;
+
+  metadata?: { fileId?: string };
+};

packages/global/common/file/read/index.ts

@@ -1,62 +0,0 @@
-/* read file to txt */
-import * as pdfjsLib from 'pdfjs-dist';
-
-export const readPdfFile = async ({ pdf }: { pdf: string | URL | ArrayBuffer }) => {
-  pdfjsLib.GlobalWorkerOptions.workerSrc = '/js/pdf.worker.js';
-
-  type TokenType = {
-    str: string;
-    dir: string;
-    width: number;
-    height: number;
-    transform: number[];
-    fontName: string;
-    hasEOL: boolean;
-  };
-
-  const readPDFPage = async (doc: any, pageNo: number) => {
-    const page = await doc.getPage(pageNo);
-    const tokenizedText = await page.getTextContent();
-
-    const viewport = page.getViewport({ scale: 1 });
-    const pageHeight = viewport.height;
-    const headerThreshold = pageHeight * 0.95;
-    const footerThreshold = pageHeight * 0.05;
-
-    const pageTexts: TokenType[] = tokenizedText.items.filter((token: TokenType) => {
-      return (
-        !token.transform ||
-        (token.transform[5] < headerThreshold && token.transform[5] > footerThreshold)
-      );
-    });
-
-    // concat empty string 'hasEOL'
-    for (let i = 0; i < pageTexts.length; i++) {
-      const item = pageTexts[i];
-      if (item.str === '' && pageTexts[i - 1]) {
-        pageTexts[i - 1].hasEOL = item.hasEOL;
-        pageTexts.splice(i, 1);
-        i--;
-      }
-    }
-
-    page.cleanup();
-
-    return pageTexts
-      .map((token) => {
-        const paragraphEnd = token.hasEOL && /([。？！.?!\n\r]|(\r\n))$/.test(token.str);
-
-        return paragraphEnd ? `${token.str}\n` : token.str;
-      })
-      .join('');
-  };
-
-  const doc = await pdfjsLib.getDocument(pdf).promise;
-  const pageTextPromises = [];
-  for (let pageNo = 1; pageNo <= doc.numPages; pageNo++) {
-    pageTextPromises.push(readPDFPage(doc, pageNo));
-  }
-  const pageTexts = await Promise.all(pageTextPromises);
-
-  return pageTexts.join('');
-};

packages/global/common/math/date.ts

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

packages/global/common/string/markdown.ts

@@ -15,10 +15,10 @@ export const simpleMarkdownText = (rawText: string) => {
     return `[${cleanedLinkText}](${url})`;
   });
 
-  // replace special \.* ……
-  const reg1 = /\\([-.!`_(){}\[\]])/g;
+  // replace special #\.* ……
+  const reg1 = /\\([#`!*()+-_\[\]{}\\.])/g;
   if (reg1.test(rawText)) {
-    rawText = rawText.replace(/\\([`!*()+-_\[\]{}\\.])/g, '$1');
+    rawText = rawText.replace(reg1, '$1');
   }
 
   // replace \\n
@@ -45,24 +45,26 @@ export const uploadMarkdownBase64 = async ({
   uploadImgController
 }: {
   rawText: string;
-  uploadImgController: (base64: string) => Promise<string>;
+  uploadImgController?: (base64: string) => Promise<string>;
 }) => {
-  // match base64, upload and replace it
-  const base64Regex = /data:image\/.*;base64,([^\)]+)/g;
-  const base64Arr = rawText.match(base64Regex) || [];
-  // upload base64 and replace it
-  await Promise.all(
-    base64Arr.map(async (base64Img) => {
-      try {
-        const str = await uploadImgController(base64Img);
+  if (uploadImgController) {
+    // match base64, upload and replace it
+    const base64Regex = /data:image\/.*;base64,([^\)]+)/g;
+    const base64Arr = rawText.match(base64Regex) || [];
+    // upload base64 and replace it
+    await Promise.all(
+      base64Arr.map(async (base64Img) => {
+        try {
+          const str = await uploadImgController(base64Img);
 
-        rawText = rawText.replace(base64Img, str);
-      } catch (error) {
-        rawText = rawText.replace(base64Img, '');
-        rawText = rawText.replace(/!\[.*\]\(\)/g, '');
-      }
-    })
-  );
+          rawText = rawText.replace(base64Img, str);
+        } catch (error) {
+          rawText = rawText.replace(base64Img, '');
+          rawText = rawText.replace(/!\[.*\]\(\)/g, '');
+        }
+      })
+    );
+  }
 
   // Remove white space on both sides of the picture
   const trimReg = /(!\[.*\]\(.*\))\s*/g;
@@ -70,5 +72,20 @@ export const uploadMarkdownBase64 = async ({
     rawText = rawText.replace(trimReg, '$1');
   }
 
-  return simpleMarkdownText(rawText);
+  return rawText;
+};
+
+export const markdownProcess = async ({
+  rawText,
+  uploadImgController
+}: {
+  rawText: string;
+  uploadImgController?: (base64: string) => Promise<string>;
+}) => {
+  const imageProcess = await uploadMarkdownBase64({
+    rawText,
+    uploadImgController
+  });
+
+  return simpleMarkdownText(imageProcess);
 };

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

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

packages/global/common/string/time.ts

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

packages/global/common/string/tools.ts

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

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

@@ -51,6 +51,10 @@ export type FastGPTFeConfigsType = {
   favicon?: string;
   customApiDomain?: string;
   customSharePageDomain?: string;
+  subscription?: {
+    datasetStoreFreeSize?: number;
+    datasetStorePrice?: number;
+  };
 };
 
 export type SystemEnvType = {
@@ -63,4 +67,5 @@ export type SystemEnvType = {
 declare global {
   var feConfigs: FastGPTFeConfigsType;
   var systemEnv: SystemEnvType;
+  var systemInitd: boolean;
 }