4.6.7-alpha commit (#743)

Co-authored-by: Archer <545436317@qq.com>
Co-authored-by: heheer <71265218+newfish-cmyk@users.noreply.github.com>

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

@@ -1,5 +1,5 @@
 import { DatasetDataIndexItemType, DatasetSchemaType } from './type';
-import { TrainingModeEnum, DatasetCollectionTypeEnum } from './constant';
+import { TrainingModeEnum, DatasetCollectionTypeEnum } from './constants';
 import type { LLMModelItemType } from '../ai/model.d';
 
 /* ================= dataset ===================== */
@@ -17,27 +17,25 @@ export type DatasetUpdateBody = {
 
 /* ================= collection ===================== */
 export type DatasetCollectionChunkMetadataType = {
+  parentId?: string;
   trainingType?: `${TrainingModeEnum}`;
   chunkSize?: number;
   chunkSplitter?: string;
   qaPrompt?: string;
+  metadata?: Record<string, any>;
 };
 export type CreateDatasetCollectionParams = DatasetCollectionChunkMetadataType & {
   datasetId: string;
-  parentId?: string;
   name: string;
   type: `${DatasetCollectionTypeEnum}`;
   fileId?: string;
   rawLink?: string;
   rawTextLength?: number;
   hashRawText?: string;
-  metadata?: Record<string, any>;
 };
 
 export type ApiCreateDatasetCollectionParams = DatasetCollectionChunkMetadataType & {
   datasetId: string;
-  parentId?: string;
-  metadata?: Record<string, any>;
 };
 export type TextCreateDatasetCollectionParams = ApiCreateDatasetCollectionParams & {
   name: string;
@@ -45,16 +43,24 @@ export type TextCreateDatasetCollectionParams = ApiCreateDatasetCollectionParams
 };
 export type LinkCreateDatasetCollectionParams = ApiCreateDatasetCollectionParams & {
   link: string;
-  chunkSplitter?: string;
+};
+export type FileCreateDatasetCollectionParams = ApiCreateDatasetCollectionParams & {
+  name: string;
+  rawTextLength: number;
+  hashRawText: string;
+  trainingType: `${TrainingModeEnum}`;
+  chunkSize: number;
+  chunkSplitter: string;
+  qaPrompt: string;
+
+  fileMetadata?: Record<string, any>;
+  collectionMetadata?: Record<string, any>;
 };
 
 /* ================= data ===================== */
 export type PgSearchRawType = {
   id: string;
-  team_id: string;
-  tmb_id: string;
   collection_id: string;
-  data_id: string;
   score: number;
 };
 export type PushDatasetDataChunkProps = {

packages/global/core/dataset/constants.ts

@@ -6,7 +6,7 @@ export enum DatasetTypeEnum {
 }
 export const DatasetTypeMap = {
   [DatasetTypeEnum.folder]: {
-    icon: 'core/dataset/folderDataset',
+    icon: 'common/folderFill',
     label: 'core.dataset.Folder Dataset',
     collectionLabel: 'common.Folder'
   },
@@ -104,10 +104,12 @@ export enum TrainingModeEnum {
 
 export const TrainingTypeMap = {
   [TrainingModeEnum.chunk]: {
-    label: 'core.dataset.training.type chunk'
+    label: 'core.dataset.training.Chunk mode',
+    tooltip: 'core.dataset.import.Chunk Split Tip'
   },
   [TrainingModeEnum.qa]: {
-    label: 'core.dataset.training.type qa'
+    label: 'core.dataset.training.QA mode',
+    tooltip: 'core.dataset.import.QA Import Tip'
   }
 };
 
@@ -168,4 +170,8 @@ export const SearchScoreTypeMap = {
   }
 };
 
-export const FolderAvatarSrc = '/imgs/files/folder.svg';
+export const FolderIcon = 'file/fill/folder';
+export const FolderImgUrl = '/imgs/files/folder.svg';
+
+export const CustomCollectionIcon = 'common/linkBlue';
+export const LinkCollectionIcon = 'common/linkBlue';

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

@@ -8,7 +8,7 @@ import {
   DatasetTypeEnum,
   SearchScoreTypeEnum,
   TrainingModeEnum
-} from './constant';
+} from './constants';
 
 /* schema */
 export type DatasetSchemaType = {
@@ -55,6 +55,8 @@ export type DatasetCollectionSchemaType = {
   hashRawText?: string;
   metadata?: {
     webPageSelector?: string;
+    relatedImgId?: string; // The id of the associated image collections
+
     [key: string]: any;
   };
 };

packages/global/core/dataset/utils.ts

@@ -1,4 +1,4 @@
-import { TrainingModeEnum, DatasetCollectionTypeEnum, DatasetDataIndexTypeEnum } from './constant';
+import { TrainingModeEnum, DatasetCollectionTypeEnum, DatasetDataIndexTypeEnum } from './constants';
 import { getFileIcon } from '../../common/file/icon';
 import { strIsLink } from '../../common/string/tools';
 
@@ -7,18 +7,13 @@ export function getCollectionIcon(
   name = ''
 ) {
   if (type === DatasetCollectionTypeEnum.folder) {
-    return '/imgs/files/folder.svg';
+    return 'common/folderFill';
   }
   if (type === DatasetCollectionTypeEnum.link) {
-    return '/imgs/files/link.svg';
+    return 'common/linkBlue';
   }
   if (type === DatasetCollectionTypeEnum.virtual) {
-    if (name === '手动录入') {
-      return '/imgs/files/manual.svg';
-    } else if (name === '手动标注') {
-      return '/imgs/files/mark.svg';
-    }
-    return '/imgs/files/collection.svg';
+    return 'file/fill/manual';
   }
   return getFileIcon(name);
 }
@@ -30,19 +25,14 @@ export function getSourceNameIcon({
   sourceId?: string;
 }) {
   if (strIsLink(sourceId)) {
-    return '/imgs/files/link.svg';
+    return 'common/linkBlue';
   }
   const fileIcon = getFileIcon(sourceName, '');
   if (fileIcon) {
     return fileIcon;
   }
 
-  if (sourceName === '手动录入') {
-    return '/imgs/files/manual.svg';
-  } else if (sourceName === '手动标注') {
-    return '/imgs/files/mark.svg';
-  }
-  return '/imgs/files/collection.svg';
+  return 'file/fill/manual';
 }
 
 export function getDefaultIndex(props?: { q?: string; a?: string; dataId?: string }) {