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
This commit is contained in:
Archer
2025-03-03 23:08:29 +08:00
committed by archer
parent 08b6f594df
commit adf5377ebe
106 changed files with 2337 additions and 1454 deletions

View File

@@ -1,4 +1,4 @@
import { DatasetCollectionTypeEnum, TrainingModeEnum, TrainingTypeMap } from '../constants';
import { DatasetCollectionTypeEnum } from '../constants';
import { DatasetCollectionSchemaType } from '../type';
export const getCollectionSourceData = (collection?: DatasetCollectionSchemaType) => {
@@ -16,9 +16,3 @@ export const getCollectionSourceData = (collection?: DatasetCollectionSchemaType
export const checkCollectionIsFolder = (type: DatasetCollectionTypeEnum) => {
return type === DatasetCollectionTypeEnum.folder || type === DatasetCollectionTypeEnum.virtual;
};
export const getTrainingTypeLabel = (type?: TrainingModeEnum) => {
if (!type) return '';
if (!TrainingTypeMap[type]) return '';
return TrainingTypeMap[type].label;
};