Add image index and pdf parse (#3956)

* feat: think tag parse

* feat: parse think tag test

* feat: pdf parse ux

* feat: doc2x parse

* perf: rewrite training mode setting

* feat: image parse queue

* perf: image index

* feat: image parse process

* feat: add init sh

* fix: ts

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

@@ -7,6 +7,7 @@ import {
 } from '@fastgpt/global/support/user/team/constant';
 import { DatasetCollectionName } from '../schema';
 import { DatasetColCollectionName } from '../collection/schema';
+import { DatasetDataIndexTypeEnum } from '@fastgpt/global/core/dataset/data/constants';
 
 export const DatasetDataCollectionName = 'dataset_datas';
 
@@ -42,10 +43,16 @@ const DatasetDataSchema = new Schema({
   indexes: {
     type: [
       {
+        // Abandon
         defaultIndex: {
           type: Boolean,
           default: false
         },
+        type: {
+          type: String,
+          enum: Object.values(DatasetDataIndexTypeEnum),
+          default: DatasetDataIndexTypeEnum.custom
+        },
         dataId: {
           type: String,
           required: true