New pic (#4858)

* 更新数据集相关类型，添加图像文件ID和预览URL支持；优化数据集导入功能，新增图像数据集处理组件；修复部分国际化文本；更新文件上传逻辑以支持新功能。

* 与原先代码的差别

* 新增 V4.9.10 更新说明，支持 PG 设置`systemEnv.hnswMaxScanTuples`参数，优化 LLM stream 调用超时，修复全文检索多知识库排序问题。同时更新数据集索引，移除 datasetId 字段以简化查询。

* 更换成fileId_image逻辑，并增加训练队列匹配的逻辑

* 新增图片集合判断逻辑，优化预览URL生成流程，确保仅在数据集为图片集合时生成预览URL，并添加相关日志输出以便调试。

* Refactor Docker Compose configuration to comment out exposed ports for production environments, update image versions for pgvector, fastgpt, and mcp_server, and enhance Redis service with a health check. Additionally, standardize dataset collection labels in constants and improve internationalization strings across multiple languages.

* Enhance TrainingStates component by adding internationalization support for the imageParse training mode and update defaultCounts to include imageParse mode in trainingDetail API.

* Enhance dataset import context by adding additional steps for image dataset import process and improve internationalization strings for modal buttons in the useEditTitle hook.

* Update DatasetImportContext to conditionally render MyStep component based on data source type, improving the import process for non-image datasets.

* Refactor image dataset handling by improving internationalization strings, enhancing error messages, and streamlining the preview URL generation process.

* 图片上传到新建的 dataset_collection_images 表，逻辑跟随更改

* 修改了除了controller的其他部分问题

* 把图片数据集的逻辑整合到controller里面

* 补充i18n

* 补充i18n

* resolve评论：主要是上传逻辑的更改和组件复用

* 图片名称的图标显示

* 修改编译报错的命名问题

* 删除不需要的collectionid部分

* 多余文件的处理和改动一个删除按钮

* 除了loading和统一的imageId,其他都resolve掉的

* 处理图标报错

* 复用了MyPhotoView并采用全部替换的方式将imageFileId变成imageId

* 去除不必要文件修改

* 报错和字段修改

* 增加上传成功后删除临时文件的逻辑以及回退一些修改

* 删除path字段，将图片保存到gridfs内，并修改增删等操作的代码

* 修正编译错误

---------

Co-authored-by: archer <[email protected]>

Author: ctrlz526

packages/global/common/file/icon.ts

@@ -6,7 +6,8 @@ export const fileImgs = [
   { suffix: '(doc|docs)', src: 'file/fill/doc' },
   { suffix: 'txt', src: 'file/fill/txt' },
   { suffix: 'md', src: 'file/fill/markdown' },
-  { suffix: 'html', src: 'file/fill/html' }
+  { suffix: 'html', src: 'file/fill/html' },
+  { suffix: '(jpg|jpeg|png|gif|bmp|webp|svg|ico|tiff|tif)', src: 'image' }
 
   // { suffix: '.', src: '/imgs/files/file.svg' }
 ];

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

@@ -58,6 +58,7 @@ export type CreateDatasetCollectionParams = DatasetCollectionStoreDataType & {
   hashRawText?: string;
 
   tags?: string[];
+  imageIdList?: string[];
 
   createTime?: Date;
   updateTime?: Date;
@@ -127,6 +128,7 @@ export type PgSearchRawType = {
 export type PushDatasetDataChunkProps = {
   q: string; // embedding content
   a?: string; // bonus content
+  imageId?: string; //file id preview
   chunkIndex?: number;
   indexes?: Omit<DatasetDataIndexItemType, 'dataId'>[];
 };
@@ -151,4 +153,5 @@ export type PushDatasetDataProps = {
 };
 export type PushDatasetDataResponse = {
   insertLen: number;
+  message?: string;
 };

packages/global/core/dataset/constants.ts

@@ -77,7 +77,8 @@ export enum DatasetCollectionTypeEnum {
   file = 'file',
   link = 'link', // one link
   externalFile = 'externalFile',
-  apiFile = 'apiFile'
+  apiFile = 'apiFile',
+  images = 'images'
 }
 export const DatasetCollectionTypeMap = {
   [DatasetCollectionTypeEnum.folder]: {
@@ -97,6 +98,9 @@ export const DatasetCollectionTypeMap = {
   },
   [DatasetCollectionTypeEnum.apiFile]: {
     name: i18nT('common:core.dataset.apiFile')
+  },
+  [DatasetCollectionTypeEnum.images]: {
+    name: i18nT('dataset:core.dataset.Image collection')
   }
 };
 
@@ -120,6 +124,7 @@ export const DatasetCollectionSyncResultMap = {
 export enum DatasetCollectionDataProcessModeEnum {
   chunk = 'chunk',
   qa = 'qa',
+  imageParse = 'imageParse',
   backup = 'backup',
 
   auto = 'auto' // abandon
@@ -133,6 +138,10 @@ export const DatasetCollectionDataProcessModeMap = {
     label: i18nT('common:core.dataset.training.QA mode'),
     tooltip: i18nT('common:core.dataset.import.QA Import Tip')
   },
+  [DatasetCollectionDataProcessModeEnum.imageParse]: {
+    label: i18nT('dataset:training.Image mode'),
+    tooltip: i18nT('common:core.dataset.import.Chunk Split Tip')
+  },
   [DatasetCollectionDataProcessModeEnum.backup]: {
     label: i18nT('dataset:backup_mode'),
     tooltip: i18nT('dataset:backup_mode')
@@ -172,14 +181,16 @@ export enum ImportDataSourceEnum {
   fileCustom = 'fileCustom',
   externalFile = 'externalFile',
   apiDataset = 'apiDataset',
-  reTraining = 'reTraining'
+  reTraining = 'reTraining',
+  imageDataset = 'imageDataset'
 }
 
 export enum TrainingModeEnum {
   chunk = 'chunk',
   qa = 'qa',
   auto = 'auto',
-  image = 'image'
+  image = 'image',
+  imageParse = 'imageParse'
 }
 
 /* ------------ search -------------- */

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

@@ -8,6 +8,7 @@ export type CreateDatasetDataProps = {
   chunkIndex?: number;
   q: string;
   a?: string;
+  imageId?: string;
   indexes?: Omit<DatasetDataIndexItemType, 'dataId'>[];
 };
 
@@ -19,6 +20,7 @@ export type UpdateDatasetDataProps = {
   indexes?: (Omit<DatasetDataIndexItemType, 'dataId'> & {
     dataId?: string; // pg data id
   })[];
+  imageId?: string;
 };
 
 export type PatchIndexesProps =

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

@@ -0,0 +1,19 @@
+export type DatasetImageSchema = {
+  _id: string;
+  teamId: string;
+  datasetId: string;
+  collectionId?: string;
+  name: string;
+  contentType: string;
+  size: number;
+  metadata?: Record<string, any>;
+  expiredTime?: Date;
+  createdAt: Date;
+  updatedAt: Date;
+};
+
+// API请求参数类型
+export type UploadDatasetImageProps = {
+  datasetId: string;
+  collectionId?: string;
+};

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

@@ -143,6 +143,7 @@ export type DatasetDataSchemaType = {
   updateTime: Date;
   q: string; // large chunks or question
   a: string; // answer or custom content
+  imageId?: string;
   history?: {
     q: string;
     a: string;
@@ -179,6 +180,7 @@ export type DatasetTrainingSchemaType = {
   dataId?: string;
   q: string;
   a: string;
+  imageId?: string;
   chunkIndex: number;
   indexSize?: number;
   weight: number;
@@ -254,10 +256,10 @@ export type DatasetDataItemType = {
   sourceId?: string;
   q: string;
   a: string;
+  imageId?: string;
   chunkIndex: number;
   indexes: DatasetDataIndexItemType[];
   isOwner: boolean;
-  // permission: DatasetPermission;
 };
 
 /* --------------- file ---------------------- */

packages/global/core/dataset/utils.ts

@@ -1,4 +1,8 @@
-import { TrainingModeEnum, DatasetCollectionTypeEnum } from './constants';
+import {
+  TrainingModeEnum,
+  DatasetCollectionTypeEnum,
+  DatasetCollectionDataProcessModeEnum
+} from './constants';
 import { getFileIcon } from '../../common/file/icon';
 import { strIsLink } from '../../common/string/tools';
 
@@ -15,6 +19,9 @@ export function getCollectionIcon(
   if (type === DatasetCollectionTypeEnum.virtual) {
     return 'file/fill/manual';
   }
+  if (type === DatasetCollectionTypeEnum.images) {
+    return 'image';
+  }
   return getFileIcon(name);
 }
 export function getSourceNameIcon({

packages/service/core/ai/model.ts

@@ -20,6 +20,10 @@ export const getVlmModel = (model?: string) => {
     ?.find((item) => item.model === model || item.name === model);
 };
 
+export const getVlmModelList = () => {
+  return Array.from(global.llmModelMap.values())?.filter((item) => item.vision) || [];
+};
+
 export const getDefaultEmbeddingModel = () => global?.systemDefaultModel.embedding!;
 export const getEmbeddingModel = (model?: string) => {
   if (!model) return getDefaultEmbeddingModel();