website sync feature (#4429)

* perf: introduce BullMQ for website sync (#4403)

* perf: introduce BullMQ for website sync

* feat: new redis module

* fix: remove graceful shutdown

* perf: improve UI in dataset detail

- Updated the "change" icon SVG file.
- Modified i18n strings.
- Added new i18n string "immediate_sync".
- Improved UI in dataset detail page, including button icons and
background colors.

* refactor: Add chunkSettings to DatasetSchema

* perf: website sync ux

* env template

* fix: clean up website dataset when updating chunk settings (#4420)

* perf: check setting updated

* perf: worker currency

* feat: init script for website sync refactor (#4425)

* website feature doc

---------

Co-authored-by: a.e. <49438478+I-Info@users.noreply.github.com>

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

@@ -15,7 +15,6 @@ export type DatasetUpdateBody = {
   name?: string;
   avatar?: string;
   intro?: string;
-  status?: DatasetSchemaType['status'];
 
   agentModel?: string;
   vlmModel?: string;
@@ -26,6 +25,7 @@ export type DatasetUpdateBody = {
   apiServer?: DatasetSchemaType['apiServer'];
   yuqueServer?: DatasetSchemaType['yuqueServer'];
   feishuServer?: DatasetSchemaType['feishuServer'];
+  chunkSettings?: DatasetSchemaType['chunkSettings'];
 
   // sync schedule
   autoSync?: boolean;
@@ -141,7 +141,6 @@ export type PushDatasetDataChunkProps = {
 
 export type PostWebsiteSyncParams = {
   datasetId: string;
-  billId: string;
 };
 
 export type PushDatasetDataProps = {

packages/global/core/dataset/constants.ts

@@ -50,7 +50,8 @@ export const DatasetTypeMap = {
 
 export enum DatasetStatusEnum {
   active = 'active',
-  syncing = 'syncing'
+  syncing = 'syncing',
+  waiting = 'waiting'
 }
 export const DatasetStatusMap = {
   [DatasetStatusEnum.active]: {
@@ -58,6 +59,9 @@ export const DatasetStatusMap = {
   },
   [DatasetStatusEnum.syncing]: {
     label: i18nT('common:core.dataset.status.syncing')
+  },
+  [DatasetStatusEnum.waiting]: {
+    label: i18nT('common:core.dataset.status.waiting')
   }
 };
 

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

@@ -17,6 +17,20 @@ import { SourceMemberType } from 'support/user/type';
 import { DatasetDataIndexTypeEnum } from './data/constants';
 import { ChunkSettingModeEnum } from './constants';
 
+export type ChunkSettingsType = {
+  trainingType: DatasetCollectionDataProcessModeEnum;
+  autoIndexes?: boolean;
+  imageIndex?: boolean;
+
+  chunkSettingMode?: ChunkSettingModeEnum;
+  chunkSplitMode?: DataChunkSplitModeEnum;
+
+  chunkSize?: number;
+  indexSize?: number;
+  chunkSplitter?: string;
+  qaPrompt?: string;
+};
+
 export type DatasetSchemaType = {
   _id: string;
   parentId?: string;
@@ -29,7 +43,6 @@ export type DatasetSchemaType = {
   name: string;
   intro: string;
   type: `${DatasetTypeEnum}`;
-  status: `${DatasetStatusEnum}`;
 
   vectorModel: string;
   agentModel: string;
@@ -39,14 +52,16 @@ export type DatasetSchemaType = {
     url: string;
     selector: string;
   };
+
+  chunkSettings?: ChunkSettingsType;
+
   inheritPermission: boolean;
   apiServer?: APIFileServer;
   feishuServer?: FeishuServer;
   yuqueServer?: YuqueServer;
 
-  autoSync?: boolean;
-
   // abandon
+  autoSync?: boolean;
   externalReadUrl?: string;
   defaultPermission?: number;
 };
@@ -193,6 +208,7 @@ export type DatasetListItemType = {
 };
 
 export type DatasetItemType = Omit<DatasetSchemaType, 'vectorModel' | 'agentModel' | 'vlmModel'> & {
+  status: `${DatasetStatusEnum}`;
   vectorModel: EmbeddingModelItemType;
   agentModel: LLMModelItemType;
   vlmModel?: LLMModelItemType;