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

@@ -1,5 +1,10 @@
import { DatasetDataIndexItemType, DatasetSchemaType } from './type';
import { DatasetCollectionTypeEnum, DatasetCollectionDataProcessModeEnum } from './constants';
import {
DatasetCollectionTypeEnum,
DatasetCollectionDataProcessModeEnum,
ChunkSettingModeEnum,
DataChunkSplitModeEnum
} from './constants';
import type { LLMModelItemType } from '../ai/model.d';
import { ParentIdType } from 'common/parentFolder/type';
@@ -33,7 +38,13 @@ export type DatasetCollectionChunkMetadataType = {
trainingType?: DatasetCollectionDataProcessModeEnum;
imageIndex?: boolean;
autoIndexes?: boolean;
chunkSettingMode?: ChunkSettingModeEnum;
chunkSplitMode?: DataChunkSplitModeEnum;
chunkSize?: number;
indexSize?: number;
chunkSplitter?: string;
qaPrompt?: string;
metadata?: Record<string, any>;