File input (#2270)

* doc

* feat: file upload  config

* perf: chat box file params

* feat: markdown show file

* feat: chat file store and clear

* perf: read file contentType

* feat: llm vision config

* feat: file url output

* perf: plugin error text

* perf: image load

* feat: ai chat document

* perf: file block ui

* feat: read file node

* feat: file read response field

* feat: simple mode support read files

* feat: tool call

* feat: read file histories

* perf: select file

* perf: select file config

* i18n

* i18n

* fix: ts; feat: tool response preview result

packages/service/common/buffer/rawText/schema.ts

@@ -1,5 +1,5 @@
-import { connectionMongo, getMongoModel, type Model } from '../../mongo';
-const { Schema, model, models } = connectionMongo;
+import { connectionMongo, getMongoModel } from '../../mongo';
+const { Schema } = connectionMongo;
 import { RawTextBufferSchemaType } from './type';
 
 export const collectionName = 'buffer_rawtexts';

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

@@ -3,16 +3,19 @@ import { BucketNameEnum } from '@fastgpt/global/common/file/constants';
 import fsp from 'fs/promises';
 import fs from 'fs';
 import { DatasetFileSchema } from '@fastgpt/global/core/dataset/type';
-import { MongoFileSchema } from './schema';
+import { MongoChatFileSchema, MongoDatasetFileSchema } from './schema';
 import { detectFileEncoding } from '@fastgpt/global/common/file/tools';
 import { CommonErrEnum } from '@fastgpt/global/common/error/code/common';
 import { MongoRawTextBuffer } from '../../buffer/rawText/schema';
 import { readRawContentByFileBuffer } from '../read/utils';
 import { gridFsStream2Buffer, stream2Encoding } from './utils';
 import { addLog } from '../../system/log';
+import { readFromSecondary } from '../../mongo/utils';
 
 export function getGFSCollection(bucket: `${BucketNameEnum}`) {
-  MongoFileSchema;
+  MongoDatasetFileSchema;
+  MongoChatFileSchema;
+
   return connectionMongo.connection.db.collection(`${bucket}.files`);
 }
 export function getGridBucket(bucket: `${BucketNameEnum}`) {
@@ -49,6 +52,7 @@ export async function uploadFile({
 
   const { stream: readStream, encoding } = await stream2Encoding(fs.createReadStream(path));
 
+  // Add default metadata
   metadata.teamId = teamId;
   metadata.tmbId = tmbId;
   metadata.encoding = encoding;
@@ -103,7 +107,9 @@ export async function delFileByFileIdList({
   try {
     const bucket = getGridBucket(bucketName);
 
-    await Promise.all(fileIdList.map((id) => bucket.delete(new Types.ObjectId(id))));
+    for await (const fileId of fileIdList) {
+      await bucket.delete(new Types.ObjectId(fileId));
+    }
   } catch (error) {
     if (retry > 0) {
       return delFileByFileIdList({ bucketName, fileIdList, retry: retry - 1 });
@@ -138,7 +144,9 @@ export const readFileContentFromMongo = async ({
   filename: string;
 }> => {
   // read buffer
-  const fileBuffer = await MongoRawTextBuffer.findOne({ sourceId: fileId }).lean();
+  const fileBuffer = await MongoRawTextBuffer.findOne({ sourceId: fileId }, undefined, {
+    ...readFromSecondary
+  }).lean();
   if (fileBuffer) {
     return {
       rawText: fileBuffer.rawText,

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

@@ -1,13 +1,17 @@
 import { connectionMongo, getMongoModel, type Model } from '../../mongo';
-const { Schema, model, models } = connectionMongo;
+const { Schema } = connectionMongo;
 
-const FileSchema = new Schema({});
+const DatasetFileSchema = new Schema({});
+const ChatFileSchema = new Schema({});
 
 try {
-  FileSchema.index({ 'metadata.teamId': 1 });
-  FileSchema.index({ 'metadata.uploadDate': -1 });
+  DatasetFileSchema.index({ uploadDate: -1 });
+
+  ChatFileSchema.index({ uploadDate: -1 });
+  ChatFileSchema.index({ 'metadata.chatId': 1 });
 } catch (error) {
   console.log(error);
 }
 
-export const MongoFileSchema = getMongoModel('dataset.files', FileSchema);
+export const MongoDatasetFileSchema = getMongoModel('dataset.files', DatasetFileSchema);
+export const MongoChatFileSchema = getMongoModel('chat.files', ChatFileSchema);

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

@@ -8,28 +8,6 @@ import fs from 'fs';
 import { detectFileEncoding } from '@fastgpt/global/common/file/tools';
 import type { ReadFileResponse } from '../../../worker/readFile/type';
 
-// match md img text and upload to db
-export const matchMdImgTextAndUpload = ({
-  teamId,
-  md,
-  metadata
-}: {
-  md: string;
-  teamId: string;
-  metadata?: Record<string, any>;
-}) =>
-  markdownProcess({
-    rawText: md,
-    uploadImgController: (base64Img) =>
-      uploadMongoImg({
-        type: MongoImageTypeEnum.collectionImage,
-        base64Img,
-        teamId,
-        metadata,
-        expiredTime: addHours(new Date(), 2)
-      })
-  });
-
 export type readRawTextByLocalFileParams = {
   teamId: string;
   path: string;
@@ -72,6 +50,28 @@ export const readRawContentByFileBuffer = async ({
   encoding: string;
   metadata?: Record<string, any>;
 }) => {
+  // Upload image in markdown
+  const matchMdImgTextAndUpload = ({
+    teamId,
+    md,
+    metadata
+  }: {
+    md: string;
+    teamId: string;
+    metadata?: Record<string, any>;
+  }) =>
+    markdownProcess({
+      rawText: md,
+      uploadImgController: (base64Img) =>
+        uploadMongoImg({
+          type: MongoImageTypeEnum.collectionImage,
+          base64Img,
+          teamId,
+          metadata,
+          expiredTime: addHours(new Date(), 1)
+        })
+    });
+
   let { rawText, formatText } = await runWorker<ReadFileResponse>(WorkerNameEnum.readFile, {
     extension,
     encoding,

packages/service/common/file/utils.ts

@@ -18,7 +18,17 @@ export const guessBase64ImageType = (str: string) => {
     i: 'image/png',
     R: 'image/gif',
     U: 'image/webp',
-    Q: 'image/bmp'
+    Q: 'image/bmp',
+    P: 'image/svg+xml',
+    T: 'image/tiff',
+    J: 'image/jp2',
+    S: 'image/x-tga',
+    I: 'image/ief',
+    V: 'image/vnd.microsoft.icon',
+    W: 'image/vnd.wap.wbmp',
+    X: 'image/x-xbitmap',
+    Z: 'image/x-xpixmap',
+    Y: 'image/x-xwindowdump'
   };
 
   const defaultType = 'image/jpeg';
@@ -30,6 +40,11 @@ export const guessBase64ImageType = (str: string) => {
   return imageTypeMap[firstChar] || defaultType;
 };
 
+export const getFileContentTypeFromHeader = (header: string): string | undefined => {
+  const contentType = header.split(';')[0];
+  return contentType;
+};
+
 export const clearDirFiles = (dirPath: string) => {
   if (!fs.existsSync(dirPath)) {
     return;