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/schema.ts

@@ -67,6 +67,7 @@ const DatasetSchema = new Schema({
     required: true,
     default: 'gpt-4o-mini'
   },
+  vlmModel: String,
   intro: {
     type: String,
     default: ''