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

@@ -109,6 +109,26 @@ export const DatasetCollectionSyncResultMap = {
}
};
export enum DatasetCollectionDataProcessModeEnum {
chunk = 'chunk',
qa = 'qa',
auto = 'auto' // abandon
}
export const DatasetCollectionDataProcessModeMap = {
[DatasetCollectionDataProcessModeEnum.chunk]: {
label: i18nT('common:core.dataset.training.Chunk mode'),
tooltip: i18nT('common:core.dataset.import.Chunk Split Tip')
},
[DatasetCollectionDataProcessModeEnum.qa]: {
label: i18nT('common:core.dataset.training.QA mode'),
tooltip: i18nT('common:core.dataset.import.QA Import Tip')
},
[DatasetCollectionDataProcessModeEnum.auto]: {
label: i18nT('common:core.dataset.training.Auto mode'),
tooltip: i18nT('common:core.dataset.training.Auto mode Tip')
}
};
/* ------------ data -------------- */
/* ------------ training -------------- */
@@ -124,28 +144,11 @@ export enum ImportDataSourceEnum {
export enum TrainingModeEnum {
chunk = 'chunk',
qa = 'qa',
auto = 'auto',
qa = 'qa'
image = 'image'
}
export const TrainingTypeMap = {
[TrainingModeEnum.chunk]: {
label: i18nT('common:core.dataset.training.Chunk mode'),
tooltip: i18nT('common:core.dataset.import.Chunk Split Tip'),
openSource: true
},
[TrainingModeEnum.auto]: {
label: i18nT('common:core.dataset.training.Auto mode'),
tooltip: i18nT('common:core.dataset.training.Auto mode Tip'),
openSource: false
},
[TrainingModeEnum.qa]: {
label: i18nT('common:core.dataset.training.QA mode'),
tooltip: i18nT('common:core.dataset.import.QA Import Tip'),
openSource: true
}
};
/* ------------ search -------------- */
export enum DatasetSearchModeEnum {
embedding = 'embedding',