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/global/core/dataset/training/type.d.ts

@@ -0,0 +1,20 @@
+import { PushDatasetDataChunkProps } from '../api';
+import { TrainingModeEnum } from '../constants';
+
+export type PushDataToTrainingQueueProps = {
+  teamId: string;
+  tmbId: string;
+  datasetId: string;
+  collectionId: string;
+
+  mode?: TrainingModeEnum;
+  data: PushDatasetDataChunkProps[];
+  prompt?: string;
+
+  agentModel: string;
+  vectorModel: string;
+  vlmModel?: string;
+
+  billId?: string;
+  session?: ClientSession;
+};