feat: chunk index independent config (#4271)

* sync collection

* remove lock

* feat: chunk index independent config

* feat: add max chunksize to split chunk function

* remove log

* update doc

* remove

* remove log
This commit is contained in:
Archer
2025-03-21 16:44:25 +08:00
committed by archer
parent 222ff0d49a
commit e812ad6e84
47 changed files with 784 additions and 443 deletions

View File

@@ -60,15 +60,11 @@ export const defaultCollectionDetail: DatasetCollectionItemType = {
createTime: new Date(),
trainingType: DatasetCollectionDataProcessModeEnum.chunk,
chunkSize: 0,
indexSize: 512,
permission: new DatasetPermission(),
indexAmount: 0
};
export enum ChunkSettingModeEnum {
auto = 'auto',
custom = 'custom'
}
export const datasetTypeCourseMap: Record<`${DatasetTypeEnum}`, string> = {
[DatasetTypeEnum.folder]: '',
[DatasetTypeEnum.dataset]: '',

View File

@@ -1,6 +1,6 @@
import type { PushDatasetDataChunkProps } from '@fastgpt/global/core/dataset/api';
import { TrainingModeEnum } from '@fastgpt/global/core/dataset/constants';
import { ChunkSettingModeEnum } from './constants';
import { ChunkSettingModeEnum } from '@fastgpt/global/core/dataset/constants';
import { UseFormReturn } from 'react-hook-form';
import { APIFileItem } from '@fastgpt/global/core/dataset/apiDataset';
@@ -41,7 +41,7 @@ export type ImportSourceParamsType = UseFormReturn<
{
chunkSize: number;
chunkOverlapRatio: number;
customSplitChar: string;
chunkSplitter: string;
prompt: string;
mode: TrainingModeEnum;
way: ChunkSettingModeEnum;