v4.6-3 (#471)

packages/global/core/dataset/api.d.ts

@@ -0,0 +1,20 @@
+import { DatasetDataIndexItemType } from './type';
+
+/* ================= dataset ===================== */
+
+/* ================= collection ===================== */
+
+/* ================= data ===================== */
+export type PgSearchRawType = {
+  id: string;
+  team_id: string;
+  tmb_id: string;
+  collection_id: string;
+  data_id: string;
+  score: number;
+};
+export type PushDatasetDataChunkProps = {
+  q: string; // embedding content
+  a?: string; // bonus content
+  indexes?: Omit<DatasetDataIndexItemType, 'dataId'>[];
+};

packages/global/core/dataset/constant.ts

@@ -36,29 +36,54 @@ export const DatasetCollectionTypeMap = {
   }
 };
 
-export enum TrainingModeEnum {
-  'qa' = 'qa',
-  'index' = 'index'
+export enum DatasetDataIndexTypeEnum {
+  chunk = 'chunk',
+  qa = 'qa',
+  summary = 'summary',
+  hypothetical = 'hypothetical',
+  custom = 'custom'
 }
-export const TrainingTypeMap = {
-  [TrainingModeEnum.qa]: 'qa',
-  [TrainingModeEnum.index]: 'index'
-};
-
-export enum DatasetSpecialIdEnum {
-  manual = 'manual',
-  mark = 'mark'
-}
-export const datasetSpecialIdMap = {
-  [DatasetSpecialIdEnum.manual]: {
-    name: 'kb.Manual Data',
-    sourceName: 'kb.Manual Input'
+export const DatasetDataIndexTypeMap = {
+  [DatasetDataIndexTypeEnum.chunk]: {
+    name: 'dataset.data.indexes.chunk'
   },
-  [DatasetSpecialIdEnum.mark]: {
-    name: 'kb.Mark Data',
-    sourceName: 'kb.Manual Mark'
+  [DatasetDataIndexTypeEnum.summary]: {
+    name: 'dataset.data.indexes.summary'
+  },
+  [DatasetDataIndexTypeEnum.hypothetical]: {
+    name: 'dataset.data.indexes.hypothetical'
+  },
+  [DatasetDataIndexTypeEnum.qa]: {
+    name: 'dataset.data.indexes.qa'
+  },
+  [DatasetDataIndexTypeEnum.custom]: {
+    name: 'dataset.data.indexes.custom'
   }
 };
-export const datasetSpecialIds: string[] = [DatasetSpecialIdEnum.manual, DatasetSpecialIdEnum.mark];
+
+export enum TrainingModeEnum {
+  'chunk' = 'chunk',
+  'qa' = 'qa'
+  // 'hypothetical' = 'hypothetical',
+  // 'summary' = 'summary',
+  // 'multipleIndex' = 'multipleIndex'
+}
+export const TrainingTypeMap = {
+  [TrainingModeEnum.chunk]: {
+    name: 'chunk'
+  },
+  [TrainingModeEnum.qa]: {
+    name: 'qa'
+  }
+  // [TrainingModeEnum.hypothetical]: {
+  //   name: 'hypothetical'
+  // },
+  // [TrainingModeEnum.summary]: {
+  //   name: 'summary'
+  // },
+  // [TrainingModeEnum.multipleIndex]: {
+  //   name: 'multipleIndex'
+  // }
+};
 
 export const FolderAvatarSrc = '/imgs/files/folder.svg';

packages/global/core/dataset/controller.d.ts

@@ -0,0 +1,27 @@
+import type { DatasetDataIndexItemType, DatasetDataSchemaType } from './type';
+
+export type CreateDatasetDataProps = {
+  teamId: string;
+  tmbId: string;
+  datasetId: string;
+  collectionId: string;
+  q: string;
+  a?: string;
+  indexes?: Omit<DatasetDataIndexItemType, 'dataId'>[];
+};
+
+export type UpdateDatasetDataProps = {
+  dataId: string;
+  q?: string;
+  a?: string;
+  indexes?: (Omit<DatasetDataIndexItemType, 'dataId'> & {
+    dataId?: string; // pg data id
+  })[];
+};
+
+export type PatchIndexesProps = {
+  type: 'create' | 'update' | 'delete';
+  index: Omit<DatasetDataIndexItemType, 'dataId'> & {
+    dataId?: string;
+  };
+};

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

@@ -1,6 +1,14 @@
+import type { VectorModelItemType } from '../../core/ai/model.d';
 import { PermissionTypeEnum } from '../../support/permission/constant';
-import { DatasetCollectionTypeEnum, DatasetTypeEnum, TrainingModeEnum } from './constant';
+import { PushDatasetDataChunkProps } from './api';
+import {
+  DatasetCollectionTypeEnum,
+  DatasetDataIndexTypeEnum,
+  DatasetTypeEnum,
+  TrainingModeEnum
+} from './constant';
 
+/* schema */
 export type DatasetSchemaType = {
   _id: string;
   parentId: string;
@@ -33,13 +41,33 @@ export type DatasetCollectionSchemaType = {
   };
 };
 
+export type DatasetDataIndexItemType = {
+  defaultIndex: boolean;
+  dataId: string; // pg data id
+  type: `${DatasetDataIndexTypeEnum}`;
+  text: string;
+};
+export type DatasetDataSchemaType = {
+  _id: string;
+  userId: string;
+  teamId: string;
+  tmbId: string;
+  datasetId: string;
+  collectionId: string;
+  datasetId: string;
+  collectionId: string;
+  q: string; // large chunks or question
+  a: string; // answer or custom content
+  indexes: DatasetDataIndexItemType[];
+};
+
 export type DatasetTrainingSchemaType = {
   _id: string;
   userId: string;
   teamId: string;
   tmbId: string;
   datasetId: string;
-  datasetCollectionId: string;
+  collectionId: string;
   billId: string;
   expireAt: Date;
   lockTime: Date;
@@ -48,6 +76,7 @@ export type DatasetTrainingSchemaType = {
   prompt: string;
   q: string;
   a: string;
+  indexes: Omit<DatasetDataIndexItemType, 'dataId'>[];
 };
 
 export type CollectionWithDatasetType = Omit<DatasetCollectionSchemaType, 'datasetId'> & {
@@ -55,41 +84,31 @@ export type CollectionWithDatasetType = Omit<DatasetCollectionSchemaType, 'datas
 };
 
 /* ================= dataset ===================== */
-
-/* ================= collection ===================== */
-export type DatasetCollectionItemType = DatasetCollectionSchemaType & {
+export type DatasetItemType = Omit<DatasetSchemaType, 'vectorModel'> & {
+  vectorModel: VectorModelItemType;
+  isOwner: boolean;
   canWrite: boolean;
 };
 
+/* ================= collection ===================== */
+export type DatasetCollectionItemType = CollectionWithDatasetType & {
+  canWrite: boolean;
+  sourceName: string;
+  sourceId?: string;
+};
+
 /* ================= data ===================== */
-export type PgRawDataItemType = {
-  id: string;
-  q: string;
-  a: string;
-  team_id: string;
-  tmb_id: string;
-  dataset_id: string;
-  collection_id: string;
-};
-export type PgDataItemType = {
-  id: string;
-  q: string;
-  a: string;
-  teamId: string;
-  tmbId: string;
-  datasetId: string;
-  collectionId: string;
-};
-export type DatasetChunkItemType = {
-  q: string;
-  a: string;
-};
-export type DatasetDataItemType = DatasetChunkItemType & {
+export type DatasetDataItemType = {
   id: string;
   datasetId: string;
   collectionId: string;
   sourceName: string;
   sourceId?: string;
+  q: string;
+  a: string;
+  indexes: DatasetDataIndexItemType[];
+  isOwner: boolean;
+  canWrite: boolean;
 };
 
 /* --------------- file ---------------------- */
@@ -109,9 +128,6 @@ export type DatasetFileSchema = {
 };
 
 /* ============= search =============== */
-export type SearchDataResultItemType = PgRawDataItemType & {
-  score: number;
-};
 export type SearchDataResponseItemType = DatasetDataItemType & {
   score: number;
 };

packages/global/core/dataset/utils.ts

@@ -1,4 +1,4 @@
-import { DatasetCollectionTypeEnum } from './constant';
+import { DatasetCollectionTypeEnum, DatasetDataIndexTypeEnum } from './constant';
 import { getFileIcon } from '../../common/file/icon';
 import { strIsLink } from '../../common/string/tools';
 
@@ -44,3 +44,14 @@ export function getSourceNameIcon({
   }
   return '/imgs/files/collection.svg';
 }
+
+export function getDefaultIndex(props?: { q?: string; a?: string; dataId?: string }) {
+  const { q = '', a, dataId } = props || {};
+  const qaStr = `${q}\n${a}`.trim();
+  return {
+    defaultIndex: true,
+    type: a ? DatasetDataIndexTypeEnum.qa : DatasetDataIndexTypeEnum.chunk,
+    text: a ? qaStr : q,
+    dataId
+  };
+}