perf: image index (#5071)

* doc

* perf: img cite prompt

* perf: image index

* perf: add api key to retrain api

projects/app/src/pageComponents/dataset/detail/Import/Context.tsx

@@ -49,7 +49,7 @@ export const defaultFormData: ImportFormType = {
 
   imageIndex: false,
   autoIndexes: false,
-  indexPrefixTitle: true,
+  indexPrefixTitle: false,
 
   chunkSettingMode: ChunkSettingModeEnum.auto,
   chunkSplitMode: DataChunkSplitModeEnum.paragraph,

projects/app/src/pages/api/core/dataset/collection/trainingDetail.ts

@@ -43,9 +43,10 @@ async function handler(
 
   const { collection } = await authDatasetCollection({
     req,
+    collectionId,
+    per: ReadPermissionVal,
     authToken: true,
-    collectionId: collectionId as string,
-    per: ReadPermissionVal
+    authApiKey: true
   });
 
   const match = {

projects/app/src/pages/api/core/dataset/data/getQuoteData.ts

@@ -9,6 +9,7 @@ import { type ApiRequestProps } from '@fastgpt/service/type/next';
 import { MongoDatasetCollection } from '@fastgpt/service/core/dataset/collection/schema';
 import { ChatErrEnum } from '@fastgpt/global/common/error/code/chat';
 import { i18nT } from '@fastgpt/web/i18n/utils';
+import { formatDatasetDataValue } from '@fastgpt/service/core/dataset/data/controller';
 
 export type GetQuoteDataResponse = {
   collection: DatasetCollectionSchemaType;
@@ -78,8 +79,13 @@ async function handler(req: ApiRequestProps<GetQuoteDataProps>): Promise<GetQuot
 
       return {
         collection,
-        q: datasetData.q,
-        a: datasetData.a
+        ...formatDatasetDataValue({
+          teamId: datasetData.teamId,
+          datasetId: datasetData.datasetId,
+          q: datasetData.q,
+          a: datasetData.a,
+          imageId: datasetData.imageId
+        })
       };
     } else {
       const { datasetData, collection } = await authDatasetData({
@@ -91,8 +97,13 @@ async function handler(req: ApiRequestProps<GetQuoteDataProps>): Promise<GetQuot
       });
       return {
         collection,
-        q: datasetData.q,
-        a: datasetData.a
+        ...formatDatasetDataValue({
+          teamId: datasetData.teamId,
+          datasetId: datasetData.datasetId,
+          q: datasetData.q,
+          a: datasetData.a,
+          imageId: datasetData.imageId
+        })
       };
     }
   })();

projects/app/src/pages/api/core/dataset/image/[imageId].ts

@@ -1,14 +1,9 @@
-import type { NextApiRequest, NextApiResponse } from 'next';
+import type { NextApiResponse } from 'next';
 import { jsonRes } from '@fastgpt/service/common/response';
-import { getDownloadStream, getFileById } from '@fastgpt/service/common/file/gridfs/controller';
-import { BucketNameEnum } from '@fastgpt/global/common/file/constants';
-import { CommonErrEnum } from '@fastgpt/global/common/error/code/common';
 import type { ApiRequestProps } from '@fastgpt/service/type/next';
 import { authDatasetImagePreviewUrl } from '@fastgpt/service/core/dataset/image/utils';
 import { getDatasetImageReadData } from '@fastgpt/service/core/dataset/image/controller';
 
-const previewableExtensions = ['jpg', 'jpeg', 'png', 'gif', 'bmp', 'webp'];
-
 export default async function handler(
   req: ApiRequestProps<
     {},

projects/app/src/pages/api/core/dataset/training/getTrainingDataDetail.ts

@@ -32,6 +32,7 @@ async function handler(
   const { teamId } = await authDatasetCollection({
     req,
     authToken: true,
+    authApiKey: true,
     collectionId,
     per: ReadPermissionVal
   });

projects/app/src/pages/api/core/dataset/training/getTrainingError.ts

@@ -21,6 +21,7 @@ async function handler(req: ApiRequestProps<getTrainingErrorBody, {}>) {
   const { collection } = await authDatasetCollection({
     req,
     authToken: true,
+    authApiKey: true,
     collectionId,
     per: ReadPermissionVal
   });

projects/app/src/pages/api/file/datasetImg/[token].ts

@@ -0,0 +1,53 @@
+import type { NextApiResponse } from 'next';
+import { jsonRes } from '@fastgpt/service/common/response';
+import type { ApiRequestProps } from '@fastgpt/service/type/next';
+import { authDatasetImagePreviewUrl } from '@fastgpt/service/core/dataset/image/utils';
+import { getDatasetImageReadData } from '@fastgpt/service/core/dataset/image/controller';
+
+export default async function handler(
+  req: ApiRequestProps<
+    {},
+    {
+      token: string;
+    }
+  >,
+  res: NextApiResponse<any>
+) {
+  try {
+    const { token } = req.query;
+
+    if (!token) {
+      return jsonRes(res, {
+        code: 401,
+        error: 'ImageId not found'
+      });
+    }
+
+    const formatToken = token.replace(/\.jpeg$/, '');
+
+    // Verify token and permissions
+    const { imageId } = await authDatasetImagePreviewUrl(formatToken);
+
+    const { fileInfo, stream } = await getDatasetImageReadData(imageId);
+
+    // Set response headers
+    res.setHeader('Content-Type', fileInfo.contentType);
+    res.setHeader('Cache-Control', 'public, max-age=31536000');
+    res.setHeader('Content-Length', fileInfo.length);
+
+    stream.pipe(res);
+    stream.on('error', (error) => {
+      if (!res.headersSent) {
+        res.status(500).end();
+      }
+    });
+    stream.on('end', () => {
+      res.end();
+    });
+  } catch (error) {
+    return jsonRes(res, {
+      code: 500,
+      error
+    });
+  }
+}

projects/app/src/service/core/dataset/data/controller.ts

@@ -173,10 +173,12 @@ export async function insertData2Dataset({
   indexes,
   indexPrefix,
   embeddingModel,
+  imageDescMap,
   session
 }: CreateDatasetDataProps & {
   embeddingModel: string;
   indexSize?: number;
+  imageDescMap?: Record<string, string>;
   session?: ClientSession;
 }) {
   if (!q || !datasetId || !collectionId || !embeddingModel) {
@@ -234,9 +236,10 @@ export async function insertData2Dataset({
         tmbId,
         datasetId,
         collectionId,
-        imageId,
         q,
         a,
+        imageId,
+        imageDescMap,
         chunkIndex,
         indexes: results.map((item) => item.index)
       }

projects/app/src/service/core/dataset/queues/generateVector.ts

@@ -279,6 +279,7 @@ const insertData = async ({ trainingData }: { trainingData: TrainingDataType })
       q: trainingData.q,
       a: trainingData.a,
       imageId: trainingData.imageId,
+      imageDescMap: trainingData.imageDescMap,
       chunkIndex: trainingData.chunkIndex,
       indexSize:
         trainingData.indexSize ||