External dataset (#1519)

* perf: local file create collection * rename middleware * perf: remove code * feat: next14 * feat: external file dataset * collection tags field * external file dataset doc * fix: ts
2025-07-30 02:12:38 +00:00 · 2024-05-17 16:44:15 +08:00
parent 2d1ec9b3ad
commit 67c52992d7
102 changed files with 1839 additions and 1282 deletions
--- a/projects/app/src/pages/api/admin/initv481.ts
+++ b/projects/app/src/pages/api/admin/initv481.ts
@@ -3,7 +3,7 @@ import { jsonRes } from '@fastgpt/service/common/response';
 import { connectToDatabase } from '@/service/mongo';
 import { authCert } from '@fastgpt/service/support/permission/auth/common';
 import { PgClient } from '@fastgpt/service/common/vectorStore/pg';
-import { NextAPI } from '@/service/middle/entry';
+import { NextAPI } from '@/service/middleware/entry';
 import { PgDatasetTableName } from '@fastgpt/global/common/vectorStore/constants';
 import { connectionMongo } from '@fastgpt/service/common/mongo';
 import { addLog } from '@fastgpt/service/common/system/log';
--- a/projects/app/src/pages/api/common/file/previewContent.ts
+++ b/projects/app/src/pages/api/common/file/previewContent.ts
@@ -4,7 +4,7 @@
 import type { NextApiResponse } from 'next';
 import { jsonRes } from '@fastgpt/service/common/response';
 import { authFile } from '@fastgpt/service/support/permission/auth/file';
-import { NextAPI } from '@/service/middle/entry';
+import { NextAPI } from '@/service/middleware/entry';
 import { DatasetSourceReadTypeEnum } from '@fastgpt/global/core/dataset/constants';
 import { readDatasetSourceRawText } from '@fastgpt/service/core/dataset/read';
 import { ApiRequestProps } from '@fastgpt/service/type/next';
--- a/projects/app/src/pages/api/core/ai/token.ts
+++ b/projects/app/src/pages/api/core/ai/token.ts
@@ -1,5 +1,5 @@
 import type { ApiRequestProps, ApiResponseType } from '@fastgpt/service/type/next';
-import { NextAPI } from '@/service/middle/entry';
+import { NextAPI } from '@/service/middleware/entry';
 import { authCert } from '@fastgpt/service/support/permission/auth/common';
 import { ChatCompletionMessageParam } from '@fastgpt/global/core/ai/type';
 import { countGptMessagesTokens } from '@fastgpt/service/common/string/tiktoken';
--- a/projects/app/src/pages/api/core/app/create.ts
+++ b/projects/app/src/pages/api/core/app/create.ts
@@ -7,7 +7,7 @@ import { authUserNotVisitor } from '@fastgpt/service/support/permission/auth/use
 import { checkTeamAppLimit } from '@fastgpt/service/support/permission/teamLimit';
 import { mongoSessionRun } from '@fastgpt/service/common/mongo/sessionRun';
 import { MongoAppVersion } from '@fastgpt/service/core/app/versionSchema';
-import { NextAPI } from '@/service/middle/entry';
+import { NextAPI } from '@/service/middleware/entry';

 async function handler(req: NextApiRequest, res: NextApiResponse<any>) {
  const {
--- a/projects/app/src/pages/api/core/app/del.ts
+++ b/projects/app/src/pages/api/core/app/del.ts
@@ -6,7 +6,7 @@ import { authApp } from '@fastgpt/service/support/permission/auth/app';
 import { MongoChatItem } from '@fastgpt/service/core/chat/chatItemSchema';
 import { mongoSessionRun } from '@fastgpt/service/common/mongo/sessionRun';
 import { MongoAppVersion } from '@fastgpt/service/core/app/versionSchema';
-import { NextAPI } from '@/service/middle/entry';
+import { NextAPI } from '@/service/middleware/entry';

 async function handler(req: NextApiRequest, res: NextApiResponse<any>) {
  const { appId } = req.query as { appId: string };
--- a/projects/app/src/pages/api/core/app/detail.tsx
+++ b/projects/app/src/pages/api/core/app/detail.tsx
@@ -2,7 +2,7 @@ import type { NextApiRequest, NextApiResponse } from 'next';
 import { jsonRes } from '@fastgpt/service/common/response';
 import { connectToDatabase } from '@/service/mongo';
 import { authApp } from '@fastgpt/service/support/permission/auth/app';
-import { NextAPI } from '@/service/middle/entry';
+import { NextAPI } from '@/service/middleware/entry';

 /* 获取我的模型 */
 async function handler(req: NextApiRequest, res: NextApiResponse<any>) {
--- a/projects/app/src/pages/api/core/app/getChatLogs.ts
+++ b/projects/app/src/pages/api/core/app/getChatLogs.ts
@@ -7,7 +7,7 @@ import { addDays } from 'date-fns';
 import type { GetAppChatLogsParams } from '@/global/core/api/appReq.d';
 import { authApp } from '@fastgpt/service/support/permission/auth/app';
 import { ChatItemCollectionName } from '@fastgpt/service/core/chat/chatItemSchema';
-import { NextAPI } from '@/service/middle/entry';
+import { NextAPI } from '@/service/middleware/entry';

 async function handler(
  req: NextApiRequest,
--- a/projects/app/src/pages/api/core/app/list.ts
+++ b/projects/app/src/pages/api/core/app/list.ts
@@ -3,7 +3,7 @@ import { MongoApp } from '@fastgpt/service/core/app/schema';
 import { mongoRPermission } from '@fastgpt/global/support/permission/utils';
 import { AppListItemType } from '@fastgpt/global/core/app/type';
 import { authUserRole } from '@fastgpt/service/support/permission/auth/user';
-import { NextAPI } from '@/service/middle/entry';
+import { NextAPI } from '@/service/middleware/entry';

 async function handler(req: NextApiRequest, res: NextApiResponse<any>): Promise<AppListItemType[]> {
  // 凭证校验
--- a/projects/app/src/pages/api/core/app/update.ts
+++ b/projects/app/src/pages/api/core/app/update.ts
@@ -3,7 +3,7 @@ import { MongoApp } from '@fastgpt/service/core/app/schema';
 import type { AppUpdateParams } from '@/global/core/app/api';
 import { authApp } from '@fastgpt/service/support/permission/auth/app';
 import { beforeUpdateAppFormat } from '@fastgpt/service/core/app/controller';
-import { NextAPI } from '@/service/middle/entry';
+import { NextAPI } from '@/service/middleware/entry';

 /* 获取我的模型 */
 async function handler(req: NextApiRequest, res: NextApiResponse<any>) {
--- a/projects/app/src/pages/api/core/app/version/list.ts
+++ b/projects/app/src/pages/api/core/app/version/list.ts
@@ -1,5 +1,5 @@
 import type { NextApiRequest, NextApiResponse } from 'next';
-import { NextAPI } from '@/service/middle/entry';
+import { NextAPI } from '@/service/middleware/entry';
 import { MongoAppVersion } from '@fastgpt/service/core/app/versionSchema';
 import { PaginationProps, PaginationResponse } from '@fastgpt/web/common/fetch/type';
 import { AppVersionSchemaType } from '@fastgpt/global/core/app/version';
--- a/projects/app/src/pages/api/core/app/version/publish.ts
+++ b/projects/app/src/pages/api/core/app/version/publish.ts
@@ -1,5 +1,5 @@
 import type { NextApiRequest, NextApiResponse } from 'next';
-import { NextAPI } from '@/service/middle/entry';
+import { NextAPI } from '@/service/middleware/entry';
 import { authApp } from '@fastgpt/service/support/permission/auth/app';
 import { MongoAppVersion } from '@fastgpt/service/core/app/versionSchema';
 import { mongoSessionRun } from '@fastgpt/service/common/mongo/sessionRun';
--- a/projects/app/src/pages/api/core/app/version/revert.ts
+++ b/projects/app/src/pages/api/core/app/version/revert.ts
@@ -1,5 +1,5 @@
 import type { NextApiRequest, NextApiResponse } from 'next';
-import { NextAPI } from '@/service/middle/entry';
+import { NextAPI } from '@/service/middleware/entry';
 import { authApp } from '@fastgpt/service/support/permission/auth/app';
 import { MongoAppVersion } from '@fastgpt/service/core/app/versionSchema';
 import { mongoSessionRun } from '@fastgpt/service/common/mongo/sessionRun';
--- a/projects/app/src/pages/api/core/chat/init.ts
+++ b/projects/app/src/pages/api/core/chat/init.ts
@@ -9,7 +9,7 @@ import { getChatItems } from '@fastgpt/service/core/chat/controller';
 import { ChatErrEnum } from '@fastgpt/global/common/error/code/chat';
 import { DispatchNodeResponseKeyEnum } from '@fastgpt/global/core/workflow/runtime/constants';
 import { getAppLatestVersion } from '@fastgpt/service/core/app/controller';
-import { NextAPI } from '@/service/middle/entry';
+import { NextAPI } from '@/service/middleware/entry';

 async function handler(
  req: NextApiRequest,
--- a/projects/app/src/pages/api/core/dataset/allDataset.ts
+++ b/projects/app/src/pages/api/core/dataset/allDataset.ts
@@ -5,7 +5,7 @@ import type { DatasetSimpleItemType } from '@fastgpt/global/core/dataset/type.d'
 import { mongoRPermission } from '@fastgpt/global/support/permission/utils';
 import { authUserRole } from '@fastgpt/service/support/permission/auth/user';
 import { DatasetTypeEnum } from '@fastgpt/global/core/dataset/constants';
-import { NextAPI } from '@/service/middle/entry';
+import { NextAPI } from '@/service/middleware/entry';

 /* get all dataset by teamId or tmbId */
 async function handler(
--- a/projects/app/src/pages/api/core/dataset/collection/create/csvTable.ts
+++ b/projects/app/src/pages/api/core/dataset/collection/create/csvTable.ts
@@ -17,8 +17,6 @@ import { pushDataListToTrainingQueue } from '@fastgpt/service/core/dataset/train
 import { createTrainingUsage } from '@fastgpt/service/support/wallet/usage/controller';
 import { UsageSourceEnum } from '@fastgpt/global/support/wallet/usage/constants';
 import { getLLMModel, getVectorModel } from '@fastgpt/service/core/ai/model';
-import { parseCsvTable2Chunks } from '@fastgpt/service/core/dataset/training/utils';
-import { startTrainingQueue } from '@/service/core/dataset/training/utils';
 import { rawText2Chunks } from '@fastgpt/service/core/dataset/read';

 export default async function handler(req: NextApiRequest, res: NextApiResponse<any>) {
@@ -106,8 +104,6 @@ export default async function handler(req: NextApiRequest, res: NextApiResponse<
      return collectionId;
    });

-    startTrainingQueue(true);
-
    jsonRes(res);
  } catch (error) {
    jsonRes(res, {
--- a/projects/app/src/pages/api/core/dataset/collection/create/file.ts
+++ b/projects/app/src/pages/api/core/dataset/collection/create/file.ts
@@ -1,153 +0,0 @@
-import type { NextApiRequest, NextApiResponse } from 'next';
-import { jsonRes } from '@fastgpt/service/common/response';
-import { connectToDatabase } from '@/service/mongo';
-import { readFileContentFromMongo } from '@fastgpt/service/common/file/gridfs/controller';
-import { authDataset } from '@fastgpt/service/support/permission/auth/dataset';
-import { FileIdCreateDatasetCollectionParams } from '@fastgpt/global/core/dataset/api';
-import { createOneCollection } from '@fastgpt/service/core/dataset/collection/controller';
-import {
-  DatasetCollectionTypeEnum,
-  TrainingModeEnum
-} from '@fastgpt/global/core/dataset/constants';
-import { BucketNameEnum } from '@fastgpt/global/common/file/constants';
-import { mongoSessionRun } from '@fastgpt/service/common/mongo/sessionRun';
-import { MongoImage } from '@fastgpt/service/common/file/image/schema';
-import { splitText2Chunks } from '@fastgpt/global/common/string/textSplitter';
-import { checkDatasetLimit } from '@fastgpt/service/support/permission/teamLimit';
-import { predictDataLimitLength } from '@fastgpt/global/core/dataset/utils';
-import { pushDataListToTrainingQueue } from '@fastgpt/service/core/dataset/training/controller';
-import { createTrainingUsage } from '@fastgpt/service/support/wallet/usage/controller';
-import { UsageSourceEnum } from '@fastgpt/global/support/wallet/usage/constants';
-import { getLLMModel, getVectorModel } from '@fastgpt/service/core/ai/model';
-import { hashStr } from '@fastgpt/global/common/string/tools';
-import { startTrainingQueue } from '@/service/core/dataset/training/utils';
-import { MongoRawTextBuffer } from '@fastgpt/service/common/buffer/rawText/schema';
-import { rawText2Chunks } from '@fastgpt/service/core/dataset/read';
-
-export default async function handler(req: NextApiRequest, res: NextApiResponse<any>) {
-  const {
-    fileId,
-    trainingType = TrainingModeEnum.chunk,
-    chunkSize = 512,
-    chunkSplitter,
-    qaPrompt,
-    ...body
-  } = req.body as FileIdCreateDatasetCollectionParams;
-
-  try {
-    await connectToDatabase();
-
-    const { teamId, tmbId, dataset } = await authDataset({
-      req,
-      authToken: true,
-      authApiKey: true,
-      per: 'w',
-      datasetId: body.datasetId
-    });
-
-    // 1. read file
-    const { rawText, filename } = await readFileContentFromMongo({
-      teamId,
-      bucketName: BucketNameEnum.dataset,
-      fileId
-    });
-    // 2. split chunks
-    const chunks = rawText2Chunks({
-      rawText,
-      chunkLen: chunkSize,
-      overlapRatio: trainingType === TrainingModeEnum.chunk ? 0.2 : 0,
-      customReg: chunkSplitter ? [chunkSplitter] : []
-    });
-
-    // 3. auth limit
-    await checkDatasetLimit({
-      teamId,
-      insertLen: predictDataLimitLength(trainingType, chunks)
-    });
-
-    await mongoSessionRun(async (session) => {
-      // 4. create collection
-      const { _id: collectionId } = await createOneCollection({
-        ...body,
-        teamId,
-        tmbId,
-        type: DatasetCollectionTypeEnum.file,
-        name: filename,
-        fileId,
-        metadata: {
-          relatedImgId: fileId
-        },
-
-        // special metadata
-        trainingType,
-        chunkSize,
-        chunkSplitter,
-        qaPrompt,
-
-        hashRawText: hashStr(rawText),
-        rawTextLength: rawText.length,
-        session
-      });
-
-      // 5. create training bill
-      const { billId } = await createTrainingUsage({
-        teamId,
-        tmbId,
-        appName: filename,
-        billSource: UsageSourceEnum.training,
-        vectorModel: getVectorModel(dataset.vectorModel)?.name,
-        agentModel: getLLMModel(dataset.agentModel)?.name,
-        session
-      });
-
-      // 6. insert to training queue
-      await pushDataListToTrainingQueue({
-        teamId,
-        tmbId,
-        datasetId: dataset._id,
-        collectionId,
-        agentModel: dataset.agentModel,
-        vectorModel: dataset.vectorModel,
-        trainingMode: trainingType,
-        prompt: qaPrompt,
-        billId,
-        data: chunks.map((item, index) => ({
-          ...item,
-          chunkIndex: index
-        })),
-        session
-      });
-
-      // 7. remove related image ttl
-      await MongoImage.updateMany(
-        {
-          teamId,
-          'metadata.relatedId': fileId
-        },
-        {
-          // Remove expiredTime to avoid ttl expiration
-          $unset: {
-            expiredTime: 1
-          }
-        },
-        {
-          session
-        }
-      );
-
-      return collectionId;
-    });
-
-    // remove buffer
-    await MongoRawTextBuffer.deleteOne({ sourceId: fileId });
-
-    startTrainingQueue(true);
-
-    jsonRes(res);
-  } catch (error) {
-    jsonRes(res, {
-      code: 500,
-      error
-    });
-  }
-}
--- a/projects/app/src/pages/api/core/dataset/collection/create/fileId.ts
+++ b/projects/app/src/pages/api/core/dataset/collection/create/fileId.ts
@@ -0,0 +1,149 @@
+import type { NextApiResponse } from 'next';
+import { jsonRes } from '@fastgpt/service/common/response';
+import { connectToDatabase } from '@/service/mongo';
+import { readFileContentFromMongo } from '@fastgpt/service/common/file/gridfs/controller';
+import { authDataset } from '@fastgpt/service/support/permission/auth/dataset';
+import { FileIdCreateDatasetCollectionParams } from '@fastgpt/global/core/dataset/api';
+import { createOneCollection } from '@fastgpt/service/core/dataset/collection/controller';
+import {
+  DatasetCollectionTypeEnum,
+  TrainingModeEnum
+} from '@fastgpt/global/core/dataset/constants';
+import { BucketNameEnum } from '@fastgpt/global/common/file/constants';
+import { mongoSessionRun } from '@fastgpt/service/common/mongo/sessionRun';
+import { MongoImage } from '@fastgpt/service/common/file/image/schema';
+import { checkDatasetLimit } from '@fastgpt/service/support/permission/teamLimit';
+import { predictDataLimitLength } from '@fastgpt/global/core/dataset/utils';
+import { pushDataListToTrainingQueue } from '@fastgpt/service/core/dataset/training/controller';
+import { createTrainingUsage } from '@fastgpt/service/support/wallet/usage/controller';
+import { UsageSourceEnum } from '@fastgpt/global/support/wallet/usage/constants';
+import { getLLMModel, getVectorModel } from '@fastgpt/service/core/ai/model';
+import { hashStr } from '@fastgpt/global/common/string/tools';
+import { MongoRawTextBuffer } from '@fastgpt/service/common/buffer/rawText/schema';
+import { rawText2Chunks } from '@fastgpt/service/core/dataset/read';
+import { NextAPI } from '@/service/middleware/entry';
+import { ApiRequestProps } from '@fastgpt/service/type/next';
+
+async function handler(
+  req: ApiRequestProps<FileIdCreateDatasetCollectionParams>,
+  res: NextApiResponse<any>
+) {
+  const {
+    fileId,
+    trainingType = TrainingModeEnum.chunk,
+    chunkSize = 512,
+    chunkSplitter,
+    qaPrompt,
+    ...body
+  } = req.body;
+
+  await connectToDatabase();
+
+  const { teamId, tmbId, dataset } = await authDataset({
+    req,
+    authToken: true,
+    authApiKey: true,
+    per: 'w',
+    datasetId: body.datasetId
+  });
+
+  // 1. read file
+  const { rawText, filename } = await readFileContentFromMongo({
+    teamId,
+    bucketName: BucketNameEnum.dataset,
+    fileId
+  });
+  // 2. split chunks
+  const chunks = rawText2Chunks({
+    rawText,
+    chunkLen: chunkSize,
+    overlapRatio: trainingType === TrainingModeEnum.chunk ? 0.2 : 0,
+    customReg: chunkSplitter ? [chunkSplitter] : []
+  });
+
+  // 3. auth limit
+  await checkDatasetLimit({
+    teamId,
+    insertLen: predictDataLimitLength(trainingType, chunks)
+  });
+
+  await mongoSessionRun(async (session) => {
+    // 4. create collection
+    const { _id: collectionId } = await createOneCollection({
+      ...body,
+      teamId,
+      tmbId,
+      type: DatasetCollectionTypeEnum.file,
+      name: filename,
+      fileId,
+      metadata: {
+        relatedImgId: fileId
+      },
+
+      // special metadata
+      trainingType,
+      chunkSize,
+      chunkSplitter,
+      qaPrompt,
+
+      hashRawText: hashStr(rawText),
+      rawTextLength: rawText.length,
+      session
+    });
+
+    // 5. create training bill
+    const { billId } = await createTrainingUsage({
+      teamId,
+      tmbId,
+      appName: filename,
+      billSource: UsageSourceEnum.training,
+      vectorModel: getVectorModel(dataset.vectorModel)?.name,
+      agentModel: getLLMModel(dataset.agentModel)?.name,
+      session
+    });
+
+    // 6. insert to training queue
+    await pushDataListToTrainingQueue({
+      teamId,
+      tmbId,
+      datasetId: dataset._id,
+      collectionId,
+      agentModel: dataset.agentModel,
+      vectorModel: dataset.vectorModel,
+      trainingMode: trainingType,
+      prompt: qaPrompt,
+      billId,
+      data: chunks.map((item, index) => ({
+        ...item,
+        chunkIndex: index
+      })),
+      session
+    });
+
+    // 7. remove related image ttl
+    await MongoImage.updateMany(
+      {
+        teamId,
+        'metadata.relatedId': fileId
+      },
+      {
+        // Remove expiredTime to avoid ttl expiration
+        $unset: {
+          expiredTime: 1
+        }
+      },
+      {
+        session
+      }
+    );
+
+    return collectionId;
+  });
+
+  // remove buffer
+  await MongoRawTextBuffer.deleteOne({ sourceId: fileId });
+
+  jsonRes(res);
+}
+
+export default NextAPI(handler);
--- a/projects/app/src/pages/api/core/dataset/collection/create/localFile.ts
+++ b/projects/app/src/pages/api/core/dataset/collection/create/localFile.ts
@@ -0,0 +1,186 @@
+import type { NextApiRequest, NextApiResponse } from 'next';
+import { jsonRes } from '@fastgpt/service/common/response';
+import { uploadFile } from '@fastgpt/service/common/file/gridfs/controller';
+import { getUploadModel } from '@fastgpt/service/common/file/multer';
+import { authDataset } from '@fastgpt/service/support/permission/auth/dataset';
+import { FileCreateDatasetCollectionParams } from '@fastgpt/global/core/dataset/api';
+import { removeFilesByPaths } from '@fastgpt/service/common/file/utils';
+import { createOneCollection } from '@fastgpt/service/core/dataset/collection/controller';
+import {
+  DatasetCollectionTypeEnum,
+  TrainingModeEnum
+} from '@fastgpt/global/core/dataset/constants';
+import { getNanoid, hashStr } from '@fastgpt/global/common/string/tools';
+import { splitText2Chunks } from '@fastgpt/global/common/string/textSplitter';
+import { checkDatasetLimit } from '@fastgpt/service/support/permission/teamLimit';
+import { predictDataLimitLength } from '@fastgpt/global/core/dataset/utils';
+import { pushDataListToTrainingQueue } from '@fastgpt/service/core/dataset/training/controller';
+import { createTrainingUsage } from '@fastgpt/service/support/wallet/usage/controller';
+import { UsageSourceEnum } from '@fastgpt/global/support/wallet/usage/constants';
+import { getDatasetModel, getVectorModel } from '@fastgpt/service/core/ai/model';
+import { BucketNameEnum } from '@fastgpt/global/common/file/constants';
+import { mongoSessionRun } from '@fastgpt/service/common/mongo/sessionRun';
+import { MongoImage } from '@fastgpt/service/common/file/image/schema';
+import { readRawTextByLocalFile } from '@fastgpt/service/common/file/read/utils';
+import { NextAPI } from '@/service/middleware/entry';
+
+async function handler(req: NextApiRequest, res: NextApiResponse<any>) {
+  /**
+   * Creates the multer uploader
+   */
+  const upload = getUploadModel({
+    maxSize: (global.feConfigs?.uploadFileMaxSize || 500) * 1024 * 1024
+  });
+  let filePaths: string[] = [];
+
+  try {
+    const { file, data, bucketName } = await upload.doUpload<FileCreateDatasetCollectionParams>(
+      req,
+      res,
+      BucketNameEnum.dataset
+    );
+    filePaths = [file.path];
+
+    if (!file || !bucketName) {
+      throw new Error('file is empty');
+    }
+
+    const { teamId, tmbId, dataset } = await authDataset({
+      req,
+      authApiKey: true,
+      per: 'w',
+      datasetId: data.datasetId
+    });
+
+    const {
+      trainingType = TrainingModeEnum.chunk,
+      chunkSize = 512,
+      chunkSplitter,
+      qaPrompt
+    } = data;
+    const { fileMetadata, collectionMetadata, ...collectionData } = data;
+    const collectionName = file.originalname;
+
+    const relatedImgId = getNanoid();
+
+    // 1. read file
+    const { rawText } = await readRawTextByLocalFile({
+      teamId,
+      path: file.path,
+      metadata: {
+        ...fileMetadata,
+        relatedId: relatedImgId
+      }
+    });
+
+    // 2. upload file
+    const fileId = await uploadFile({
+      teamId,
+      tmbId,
+      bucketName,
+      path: file.path,
+      filename: file.originalname,
+      contentType: file.mimetype,
+      metadata: fileMetadata
+    });
+
+    // 3. delete tmp file
+    removeFilesByPaths(filePaths);
+
+    // 4. split raw text to chunks
+    const { chunks } = splitText2Chunks({
+      text: rawText,
+      chunkLen: chunkSize,
+      overlapRatio: trainingType === TrainingModeEnum.chunk ? 0.2 : 0,
+      customReg: chunkSplitter ? [chunkSplitter] : []
+    });
+
+    // 5. check dataset limit
+    await checkDatasetLimit({
+      teamId,
+      insertLen: predictDataLimitLength(trainingType, chunks)
+    });
+
+    // 6. create collection and training bill
+    const { collectionId, insertResults } = await mongoSessionRun(async (session) => {
+      const { _id: collectionId } = await createOneCollection({
+        ...collectionData,
+        name: collectionName,
+        teamId,
+        tmbId,
+        type: DatasetCollectionTypeEnum.file,
+        fileId,
+        rawTextLength: rawText.length,
+        hashRawText: hashStr(rawText),
+        metadata: {
+          ...collectionMetadata,
+          relatedImgId
+        },
+        session
+      });
+      const { billId } = await createTrainingUsage({
+        teamId,
+        tmbId,
+        appName: collectionName,
+        billSource: UsageSourceEnum.training,
+        vectorModel: getVectorModel(dataset.vectorModel)?.name,
+        agentModel: getDatasetModel(dataset.agentModel)?.name
+      });
+
+      // 7. push chunks to training queue
+      const insertResults = await pushDataListToTrainingQueue({
+        teamId,
+        tmbId,
+        datasetId: dataset._id,
+        collectionId,
+        agentModel: dataset.agentModel,
+        vectorModel: dataset.vectorModel,
+        trainingMode: trainingType,
+        prompt: qaPrompt,
+        billId,
+        data: chunks.map((text, index) => ({
+          q: text,
+          chunkIndex: index
+        }))
+      });
+
+      // 8. remove image expired time
+      await MongoImage.updateMany(
+        {
+          teamId,
+          'metadata.relatedId': relatedImgId
+        },
+        {
+          // Remove expiredTime to avoid ttl expiration
+          $unset: {
+            expiredTime: 1
+          }
+        },
+        {
+          session
+        }
+      );
+
+      return {
+        collectionId,
+        insertResults
+      };
+    });
+
+    jsonRes(res, {
+      data: { collectionId, results: insertResults }
+    });
+  } catch (error) {
+    removeFilesByPaths(filePaths);
+
+    return Promise.reject(error);
+  }
+}
+
+export const config = {
+  api: {
+    bodyParser: false
+  }
+};
+
+export default NextAPI(handler);
--- a/projects/app/src/pages/api/core/dataset/collection/detail.ts
+++ b/projects/app/src/pages/api/core/dataset/collection/detail.ts
@@ -8,6 +8,7 @@ import { authDatasetCollection } from '@fastgpt/service/support/permission/auth/
 import { DatasetCollectionItemType } from '@fastgpt/global/core/dataset/type';
 import { BucketNameEnum } from '@fastgpt/global/common/file/constants';
 import { getFileById } from '@fastgpt/service/common/file/gridfs/controller';
+import { getCollectionSourceData } from '@fastgpt/global/core/dataset/collection/utils';

 export default async function handler(req: NextApiRequest, res: NextApiResponse<any>) {
  try {
@@ -36,8 +37,7 @@ export default async function handler(req: NextApiRequest, res: NextApiResponse<
      data: {
        ...collection,
        canWrite,
-        sourceName: collection?.name,
-        sourceId: collection?.fileId || collection?.rawLink,
+        ...getCollectionSourceData(collection),
        file
      }
    });
--- a/projects/app/src/pages/api/core/dataset/collection/read.ts
+++ b/projects/app/src/pages/api/core/dataset/collection/read.ts
@@ -0,0 +1,66 @@
+import type { ApiRequestProps, ApiResponseType } from '@fastgpt/service/type/next';
+import { NextAPI } from '@/service/middleware/entry';
+import { authDatasetCollection } from '@fastgpt/service/support/permission/auth/dataset';
+import { DatasetCollectionTypeEnum } from '@fastgpt/global/core/dataset/constants';
+import { createFileToken } from '@fastgpt/service/support/permission/controller';
+import { BucketNameEnum, ReadFileBaseUrl } from '@fastgpt/global/common/file/constants';
+
+export type readCollectionSourceQuery = {
+  collectionId: string;
+};
+
+export type readCollectionSourceBody = {};
+
+export type readCollectionSourceResponse = {
+  type: 'url';
+  value: string;
+};
+
+async function handler(
+  req: ApiRequestProps<readCollectionSourceBody, readCollectionSourceQuery>,
+  res: ApiResponseType<any>
+): Promise<readCollectionSourceResponse> {
+  const { collection, teamId, tmbId } = await authDatasetCollection({
+    req,
+    authToken: true,
+    authApiKey: true,
+    collectionId: req.query.collectionId,
+    per: 'r'
+  });
+
+  const sourceUrl = await (async () => {
+    if (collection.type === DatasetCollectionTypeEnum.file && collection.fileId) {
+      const token = await createFileToken({
+        bucketName: BucketNameEnum.dataset,
+        teamId,
+        tmbId,
+        fileId: collection.fileId
+      });
+
+      return `${ReadFileBaseUrl}?token=${token}`;
+    }
+    if (collection.type === DatasetCollectionTypeEnum.link && collection.rawLink) {
+      return collection.rawLink;
+    }
+    if (collection.type === DatasetCollectionTypeEnum.externalFile) {
+      if (collection.externalFileId && collection.datasetId.externalReadUrl) {
+        return collection.datasetId.externalReadUrl.replace(
+          '{{fileId}}',
+          collection.externalFileId
+        );
+      }
+      if (collection.externalFileUrl) {
+        return collection.externalFileUrl;
+      }
+    }
+
+    return '';
+  })();
+
+  return {
+    type: 'url',
+    value: sourceUrl
+  };
+}
+
+export default NextAPI(handler);
--- a/projects/app/src/pages/api/core/dataset/data/delete.ts
+++ b/projects/app/src/pages/api/core/dataset/data/delete.ts
@@ -2,7 +2,7 @@ import type { NextApiRequest, NextApiResponse } from 'next';
 import { jsonRes } from '@fastgpt/service/common/response';
 import { authDatasetData } from '@/service/support/permission/auth/dataset';
 import { deleteDatasetData } from '@/service/core/dataset/data/controller';
-import { NextAPI } from '@/service/middle/entry';
+import { NextAPI } from '@/service/middleware/entry';

 async function handler(req: NextApiRequest, res: NextApiResponse<any>) {
  const { id: dataId } = req.query as {
--- a/projects/app/src/pages/api/core/dataset/data/detail.ts
+++ b/projects/app/src/pages/api/core/dataset/data/detail.ts
@@ -2,7 +2,7 @@ import type { NextApiRequest, NextApiResponse } from 'next';
 import { jsonRes } from '@fastgpt/service/common/response';
 import { connectToDatabase } from '@/service/mongo';
 import { authDatasetData } from '@/service/support/permission/auth/dataset';
-import { NextAPI } from '@/service/middle/entry';
+import { NextAPI } from '@/service/middleware/entry';

 export type Response = {
  id: string;
--- a/projects/app/src/pages/api/core/dataset/data/insertData.ts
+++ b/projects/app/src/pages/api/core/dataset/data/insertData.ts
@@ -15,7 +15,7 @@ import { pushGenerateVectorUsage } from '@/service/support/wallet/usage/push';
 import { InsertOneDatasetDataProps } from '@/global/core/dataset/api';
 import { simpleText } from '@fastgpt/global/common/string/tools';
 import { checkDatasetLimit } from '@fastgpt/service/support/permission/teamLimit';
-import { NextAPI } from '@/service/middle/entry';
+import { NextAPI } from '@/service/middleware/entry';

 async function handler(req: NextApiRequest, res: NextApiResponse<any>) {
  const { collectionId, q, a, indexes } = req.body as InsertOneDatasetDataProps;
--- a/projects/app/src/pages/api/core/dataset/data/list.ts
+++ b/projects/app/src/pages/api/core/dataset/data/list.ts
@@ -7,7 +7,7 @@ import { authDatasetCollection } from '@fastgpt/service/support/permission/auth/
 import { MongoDatasetData } from '@fastgpt/service/core/dataset/data/schema';
 import { PagingData } from '@/types';
 import { replaceRegChars } from '@fastgpt/global/common/string/tools';
-import { NextAPI } from '@/service/middle/entry';
+import { NextAPI } from '@/service/middleware/entry';

 async function handler(req: NextApiRequest, res: NextApiResponse<any>) {
  let {
--- a/projects/app/src/pages/api/core/dataset/data/pushData.ts
+++ b/projects/app/src/pages/api/core/dataset/data/pushData.ts
@@ -1,7 +1,6 @@
 /* push data to training queue */
 import type { NextApiRequest, NextApiResponse } from 'next';
 import { jsonRes } from '@fastgpt/service/common/response';
-import { connectToDatabase } from '@/service/mongo';
 import type {
  PushDatasetDataProps,
  PushDatasetDataResponse
@@ -10,7 +9,7 @@ import { authDatasetCollection } from '@fastgpt/service/support/permission/auth/
 import { checkDatasetLimit } from '@fastgpt/service/support/permission/teamLimit';
 import { predictDataLimitLength } from '@fastgpt/global/core/dataset/utils';
 import { pushDataListToTrainingQueue } from '@fastgpt/service/core/dataset/training/controller';
-import { NextAPI } from '@/service/middle/entry';
+import { NextAPI } from '@/service/middleware/entry';

 async function handler(req: NextApiRequest, res: NextApiResponse<any>) {
  const body = req.body as PushDatasetDataProps;
--- a/projects/app/src/pages/api/core/dataset/data/update.ts
+++ b/projects/app/src/pages/api/core/dataset/data/update.ts
@@ -6,7 +6,7 @@ import { authDatasetData } from '@/service/support/permission/auth/dataset';
 import { pushGenerateVectorUsage } from '@/service/support/wallet/usage/push';
 import { UpdateDatasetDataProps } from '@/global/core/dataset/api';
 import { checkDatasetLimit } from '@fastgpt/service/support/permission/teamLimit';
-import { NextAPI } from '@/service/middle/entry';
+import { NextAPI } from '@/service/middleware/entry';

 async function handler(req: NextApiRequest, res: NextApiResponse<any>) {
  const { id, q = '', a, indexes = [] } = req.body as UpdateDatasetDataProps;
--- a/projects/app/src/pages/api/core/dataset/exportAll.ts
+++ b/projects/app/src/pages/api/core/dataset/exportAll.ts
@@ -8,7 +8,7 @@ import {
  checkExportDatasetLimit,
  updateExportDatasetLimit
 } from '@fastgpt/service/support/user/utils';
-import { NextAPI } from '@/service/middle/entry';
+import { NextAPI } from '@/service/middleware/entry';

 async function handler(req: NextApiRequest, res: NextApiResponse<any>) {
  let { datasetId } = req.query as {
--- a/projects/app/src/pages/api/core/dataset/file/getPreviewChunks.ts
+++ b/projects/app/src/pages/api/core/dataset/file/getPreviewChunks.ts
@@ -3,7 +3,7 @@ import { authFile } from '@fastgpt/service/support/permission/auth/file';
 import { DatasetSourceReadTypeEnum } from '@fastgpt/global/core/dataset/constants';
 import { rawText2Chunks, readDatasetSourceRawText } from '@fastgpt/service/core/dataset/read';
 import { authCert } from '@fastgpt/service/support/permission/auth/common';
-import { NextAPI } from '@/service/middle/entry';
+import { NextAPI } from '@/service/middleware/entry';
 import { ApiRequestProps } from '@fastgpt/service/type/next';

 export type PostPreviewFilesChunksProps = {
--- a/projects/app/src/pages/api/core/dataset/file/getPreviewUrl.ts
+++ b/projects/app/src/pages/api/core/dataset/file/getPreviewUrl.ts
@@ -1,36 +0,0 @@
-import type { NextApiRequest, NextApiResponse } from 'next';
-import { jsonRes } from '@fastgpt/service/common/response';
-import { connectToDatabase } from '@/service/mongo';
-import { authDatasetFile } from '@fastgpt/service/support/permission/auth/dataset';
-import { createFileToken } from '@fastgpt/service/support/permission/controller';
-import { BucketNameEnum, ReadFileBaseUrl } from '@fastgpt/global/common/file/constants';
-
-export default async function handler(req: NextApiRequest, res: NextApiResponse<any>) {
-  try {
-    await connectToDatabase();
-
-    const { fileId } = req.query as { fileId: string };
-
-    if (!fileId) {
-      throw new Error('fileId is empty');
-    }
-
-    const { teamId, tmbId } = await authDatasetFile({ req, authToken: true, fileId, per: 'r' });
-
-    const token = await createFileToken({
-      bucketName: BucketNameEnum.dataset,
-      teamId,
-      tmbId,
-      fileId
-    });
-
-    jsonRes(res, {
-      data: `${ReadFileBaseUrl}?token=${token}`
-    });
-  } catch (error) {
-    jsonRes(res, {
-      code: 500,
-      error
-    });
-  }
-}
--- a/projects/app/src/pages/api/core/dataset/list.ts
+++ b/projects/app/src/pages/api/core/dataset/list.ts
@@ -6,7 +6,7 @@ import { MongoDataset } from '@fastgpt/service/core/dataset/schema';
 import { mongoRPermission } from '@fastgpt/global/support/permission/utils';
 import { authUserRole } from '@fastgpt/service/support/permission/auth/user';
 import { getVectorModel } from '@fastgpt/service/core/ai/model';
-import { NextAPI } from '@/service/middle/entry';
+import { NextAPI } from '@/service/middleware/entry';

 async function handler(req: NextApiRequest, res: NextApiResponse<any>) {
  const { parentId, type } = req.query as { parentId?: string; type?: DatasetTypeEnum };
--- a/projects/app/src/pages/api/core/dataset/searchTest.ts
+++ b/projects/app/src/pages/api/core/dataset/searchTest.ts
@@ -12,7 +12,7 @@ import {
  checkTeamAIPoints,
  checkTeamReRankPermission
 } from '@fastgpt/service/support/permission/teamLimit';
-import { NextAPI } from '@/service/middle/entry';
+import { NextAPI } from '@/service/middleware/entry';

 async function handler(req: NextApiRequest, res: NextApiResponse<any>) {
  const {
--- a/projects/app/src/pages/api/core/dataset/training/getDatasetTrainingQueue.ts
+++ b/projects/app/src/pages/api/core/dataset/training/getDatasetTrainingQueue.ts
@@ -1,5 +1,5 @@
 import type { ApiRequestProps, ApiResponseType } from '@fastgpt/service/type/next';
-import { NextAPI } from '@/service/middle/entry';
+import { NextAPI } from '@/service/middleware/entry';
 import { authDataset } from '@fastgpt/service/support/permission/auth/dataset';
 import { MongoDatasetData } from '@fastgpt/service/core/dataset/data/schema';
 import { MongoDatasetTraining } from '@fastgpt/service/core/dataset/training/schema';
--- a/projects/app/src/pages/api/core/dataset/training/rebuildEmbedding.ts
+++ b/projects/app/src/pages/api/core/dataset/training/rebuildEmbedding.ts
@@ -1,4 +1,4 @@
-import { NextAPI } from '@/service/middle/entry';
+import { NextAPI } from '@/service/middleware/entry';
 import { authDataset } from '@fastgpt/service/support/permission/auth/dataset';
 import { mongoSessionRun } from '@fastgpt/service/common/mongo/sessionRun';
 import { MongoDataset } from '@fastgpt/service/core/dataset/schema';
--- a/projects/app/src/pages/api/core/workflow/debug.ts
+++ b/projects/app/src/pages/api/core/workflow/debug.ts
@@ -7,7 +7,7 @@ import { authCert } from '@fastgpt/service/support/permission/auth/common';
 import { getUserChatInfoAndAuthTeamPoints } from '@/service/support/permission/auth/team';
 import { PostWorkflowDebugProps, PostWorkflowDebugResponse } from '@/global/core/workflow/api';
 import { authPluginCrud } from '@fastgpt/service/support/permission/auth/plugin';
-import { NextAPI } from '@/service/middle/entry';
+import { NextAPI } from '@/service/middleware/entry';

 async function handler(
  req: NextApiRequest,
--- a/projects/app/src/pages/api/support/user/team/limit/exportDatasetLimit.ts
+++ b/projects/app/src/pages/api/support/user/team/limit/exportDatasetLimit.ts
@@ -1,7 +1,7 @@
 import type { NextApiRequest, NextApiResponse } from 'next';
 import { authDataset } from '@fastgpt/service/support/permission/auth/dataset';
 import { checkExportDatasetLimit } from '@fastgpt/service/support/user/utils';
-import { NextAPI } from '@/service/middle/entry';
+import { NextAPI } from '@/service/middleware/entry';

 async function handler(req: NextApiRequest, res: NextApiResponse<any>) {
  const { datasetId } = req.query as {
--- a/projects/app/src/pages/api/v1/audio/transcriptions.ts
+++ b/projects/app/src/pages/api/v1/audio/transcriptions.ts
@@ -9,7 +9,7 @@ import { authChatCert } from '@/service/support/permission/auth/chat';
 import { MongoApp } from '@fastgpt/service/core/app/schema';
 import { getGuideModule, splitGuideModule } from '@fastgpt/global/core/workflow/utils';
 import { OutLinkChatAuthProps } from '@fastgpt/global/support/permission/chat';
-import { NextAPI } from '@/service/middle/entry';
+import { NextAPI } from '@/service/middleware/entry';

 const upload = getUploadModel({
  maxSize: 2
--- a/projects/app/src/pages/api/v1/chat/completions.ts
+++ b/projects/app/src/pages/api/v1/chat/completions.ts
@@ -44,7 +44,7 @@ import { DispatchNodeResponseKeyEnum } from '@fastgpt/global/core/workflow/runti

 import { dispatchWorkFlowV1 } from '@fastgpt/service/core/workflow/dispatchV1';
 import { setEntryEntries } from '@fastgpt/service/core/workflow/dispatchV1/utils';
-import { NextAPI } from '@/service/middle/entry';
+import { NextAPI } from '@/service/middleware/entry';
 import { getAppLatestVersion } from '@fastgpt/service/core/app/controller';

 type FastGptWebChatProps = {
--- a/projects/app/src/pages/dataset/detail/components/CollectionCard/Header.tsx
+++ b/projects/app/src/pages/dataset/detail/components/CollectionCard/Header.tsx
@@ -84,7 +84,7 @@ const Header = ({}: {}) => {
      ...props
    }: {
      name: string;
-      type: `${DatasetCollectionTypeEnum}`;
+      type: DatasetCollectionTypeEnum;
      callback?: (id: string) => void;
      trainingType?: TrainingModeEnum;
      rawLink?: string;
--- a/projects/app/src/pages/dataset/detail/components/DataCard.tsx
+++ b/projects/app/src/pages/dataset/detail/components/DataCard.tsx
@@ -38,16 +38,14 @@ import { TabEnum } from '..';
 import { useUserStore } from '@/web/support/user/useUserStore';
 import { TeamMemberRoleEnum } from '@fastgpt/global/support/user/team/constant';
 import { useSystemStore } from '@/web/common/system/useSystemStore';
-import {
-  DatasetCollectionTypeMap,
-  TrainingModeEnum,
-  TrainingTypeMap
-} from '@fastgpt/global/core/dataset/constants';
+import { DatasetCollectionTypeMap, TrainingTypeMap } from '@fastgpt/global/core/dataset/constants';
 import { formatTime2YMDHM } from '@fastgpt/global/common/string/time';
 import { formatFileSize } from '@fastgpt/global/common/file/tools';
-import { getFileAndOpen } from '@/web/core/dataset/utils';
+import { getCollectionSourceAndOpen } from '@/web/core/dataset/hooks/readCollectionSource';
 import MyTooltip from '@/components/MyTooltip';
 import { usePagination } from '@fastgpt/web/hooks/usePagination';
+import { getCollectionSourceData } from '@fastgpt/global/core/dataset/collection/utils';
+import { useI18n } from '@/web/context/I18n';

 const DataCard = () => {
  const BoxRef = useRef<HTMLDivElement>(null);
@@ -62,6 +60,7 @@ const DataCard = () => {
  };
  const { Loading, setIsLoading } = useLoading({ defaultLoading: true });
  const { t } = useTranslation();
+  const { datasetT } = useI18n();
  const [searchText, setSearchText] = useState('');
  const { toast } = useToast();
  const { openConfirm, ConfirmModal } = useConfirm({
@@ -69,6 +68,7 @@ const DataCard = () => {
    type: 'delete'
  });
  const { isOpen, onOpen, onClose } = useDisclosure();
+  const readSource = getCollectionSourceAndOpen(collectionId);

  const {
    data: datasetDataList,
@@ -169,7 +169,17 @@ const DataCard = () => {
              value: webSelector
            }
          ]
-        : [])
+        : []),
+      {
+        ...(collection.tags
+          ? [
+              {
+                label: datasetT('Collection tags'),
+                value: collection.tags?.join(', ') || '-'
+              }
+            ]
+          : [])
+      }
    ];
  }, [collection, t]);

@@ -196,13 +206,15 @@ const DataCard = () => {
          />
          <Flex className="textEllipsis" flex={'1 0 0'} mr={[3, 5]} alignItems={'center'}>
            <Box lineHeight={1.2}>
-              <RawSourceBox
-                sourceName={collection?.name}
-                sourceId={collection?.fileId || collection?.rawLink}
-                fontSize={['md', 'lg']}
-                color={'black'}
-                textDecoration={'none'}
-              />
+              {collection?._id && (
+                <RawSourceBox
+                  collectionId={collection._id}
+                  {...getCollectionSourceData(collection)}
+                  fontSize={['md', 'lg']}
+                  color={'black'}
+                  textDecoration={'none'}
+                />
+              )}
              <Box fontSize={'sm'} color={'myGray.500'}>
                {t('core.dataset.collection.id')}:{' '}
                <Box as={'span'} userSelect={'all'}>
@@ -412,10 +424,7 @@ const DataCard = () => {
              </Flex>
            ))}
            {collection?.sourceId && (
-              <Button
-                variant={'whitePrimary'}
-                onClick={() => collection.sourceId && getFileAndOpen(collection.sourceId)}
-              >
+              <Button variant={'whitePrimary'} onClick={readSource}>
                {t('core.dataset.collection.metadata.read source')}
              </Button>
            )}
--- a/projects/app/src/pages/dataset/detail/components/Import/commonProgress/Upload.tsx
+++ b/projects/app/src/pages/dataset/detail/components/Import/commonProgress/Upload.tsx
@@ -15,12 +15,12 @@ import { ImportDataSourceEnum } from '@fastgpt/global/core/dataset/constants';
 import { useTranslation } from 'next-i18next';
 import MyIcon from '@fastgpt/web/components/common/Icon';
 import { useRequest } from '@fastgpt/web/hooks/useRequest';
-import { useDatasetStore } from '@/web/core/dataset/store/dataset';
 import { useToast } from '@fastgpt/web/hooks/useToast';
 import { useRouter } from 'next/router';
 import { TabEnum } from '../../../index';
 import {
  postCreateDatasetCsvTableCollection,
+  postCreateDatasetExternalFileCollection,
  postCreateDatasetFileCollection,
  postCreateDatasetLinkCollection,
  postCreateDatasetTextCollection
@@ -95,6 +95,13 @@ const Upload = () => {
            ...commonParams,
            fileId: item.dbFileId
          });
+        } else if (importSource === ImportDataSourceEnum.externalFile && item.externalFileUrl) {
+          await postCreateDatasetExternalFileCollection({
+            ...commonParams,
+            externalFileUrl: item.externalFileUrl,
+            externalFileId: item.externalFileId,
+            filename: item.sourceName
+          });
        }

        setSources((state) =>
--- a/projects/app/src/pages/dataset/detail/components/Import/components/PreviewChunks.tsx
+++ b/projects/app/src/pages/dataset/detail/components/Import/components/PreviewChunks.tsx
@@ -44,7 +44,8 @@ const PreviewChunks = ({
      if (importSource === ImportDataSourceEnum.csvTable) {
        return getPreviewChunks({
          type: importType2ReadType(importSource),
-          sourceId: previewSource.dbFileId || previewSource.link || previewSource.sourceUrl || '',
+          sourceId:
+            previewSource.dbFileId || previewSource.link || previewSource.externalFileUrl || '',
          chunkSize,
          overlapRatio: chunkOverlapRatio,
          customSplitChar: processParamsForm.getValues('customSplitChar'),
@@ -55,7 +56,8 @@ const PreviewChunks = ({

      return getPreviewChunks({
        type: importType2ReadType(importSource),
-        sourceId: previewSource.dbFileId || previewSource.link || previewSource.sourceUrl || '',
+        sourceId:
+          previewSource.dbFileId || previewSource.link || previewSource.externalFileUrl || '',
        chunkSize,
        overlapRatio: chunkOverlapRatio,
        customSplitChar: processParamsForm.getValues('customSplitChar'),
--- a/projects/app/src/pages/dataset/detail/components/Import/components/PreviewRawText.tsx
+++ b/projects/app/src/pages/dataset/detail/components/Import/components/PreviewRawText.tsx
@@ -22,7 +22,7 @@ const PreviewRawText = ({
  const { importSource, processParamsForm } = useContextSelector(DatasetImportContext, (v) => v);

  const { data, isLoading } = useQuery(
-    ['previewSource', previewSource.dbFileId, previewSource.link, previewSource.sourceUrl],
+    ['previewSource', previewSource.dbFileId, previewSource.link, previewSource.externalFileUrl],
    () => {
      if (importSource === ImportDataSourceEnum.fileCustom && previewSource.rawText) {
        return {
@@ -39,7 +39,8 @@ const PreviewRawText = ({

      return getPreviewFileContent({
        type: importType2ReadType(importSource),
-        sourceId: previewSource.dbFileId || previewSource.link || previewSource.sourceUrl || '',
+        sourceId:
+          previewSource.dbFileId || previewSource.link || previewSource.externalFileUrl || '',
        isQAImport: false,
        selector: processParamsForm.getValues('webSelector')
      });
--- a/projects/app/src/pages/dataset/detail/components/Import/diffSource/ExternalFile.tsx
+++ b/projects/app/src/pages/dataset/detail/components/Import/diffSource/ExternalFile.tsx
@@ -50,16 +50,16 @@ const CustomLinkInput = () => {
  const { register, reset, handleSubmit, control } = useForm<{
    list: {
      sourceName: string;
-      sourceUrl: string;
-      externalId: string;
+      externalFileUrl: string;
+      externalFileId: string;
    }[];
  }>({
    defaultValues: {
      list: [
        {
          sourceName: '',
-          sourceUrl: '',
-          externalId: ''
+          externalFileUrl: '',
+          externalFileId: ''
        }
      ]
    }
@@ -80,8 +80,8 @@ const CustomLinkInput = () => {
      reset({
        list: sources.map((item) => ({
          sourceName: item.sourceName,
-          sourceUrl: item.sourceUrl || '',
-          externalId: item.externalId || ''
+          externalFileUrl: item.externalFileUrl || '',
+          externalFileId: item.externalFileId || ''
        }))
      });
    }
@@ -104,7 +104,7 @@ const CustomLinkInput = () => {
              <Tr key={item.id}>
                <Td>
                  <Input
-                    {...register(`list.${index}.sourceUrl`, {
+                    {...register(`list.${index}.externalFileUrl`, {
                      required: index !== list.length - 1,
                      onBlur(e) {
                        const val = (e.target.value || '') as string;
@@ -112,15 +112,15 @@ const CustomLinkInput = () => {
                          const sourceName = val.split('/').pop() || '';
                          update(index, {
                            ...list[index],
-                            sourceUrl: val,
+                            externalFileUrl: val,
                            sourceName: decodeURIComponent(sourceName)
                          });
                        }
                        if (val && index === list.length - 1) {
                          append({
                            sourceName: '',
-                            sourceUrl: '',
-                            externalId: ''
+                            externalFileUrl: '',
+                            externalFileId: ''
                          });
                        }
                      }
@@ -128,7 +128,7 @@ const CustomLinkInput = () => {
                  />
                </Td>
                <Td>
-                  <Input {...register(`list.${index}.externalId`)} />
+                  <Input {...register(`list.${index}.externalFileId`)} />
                </Td>
                <Td>
                  <Input {...register(`list.${index}.sourceName`)} />
@@ -154,26 +154,26 @@ const CustomLinkInput = () => {
          onClick={() => {
            append({
              sourceName: '',
-              sourceUrl: '',
-              externalId: ''
+              externalFileUrl: '',
+              externalFileId: ''
            });
          }}
        >
          {commonT('Add new')}
        </Button>
        <Button
-          isDisabled={list.filter((item) => !!item.sourceUrl).length === 0}
+          isDisabled={list.filter((item) => !!item.externalFileUrl).length === 0}
          onClick={handleSubmit((data) => {
            setSources(
              data.list
-                .filter((item) => !!item.sourceUrl)
+                .filter((item) => !!item.externalFileUrl)
                .map((item) => ({
                  id: getNanoid(32),
                  createStatus: 'waiting',
-                  sourceName: item.sourceName || item.sourceUrl,
-                  icon: getFileIcon(item.sourceUrl),
-                  externalId: item.externalId,
-                  sourceUrl: item.sourceUrl
+                  sourceName: item.sourceName || item.externalFileUrl,
+                  icon: getFileIcon(item.externalFileUrl),
+                  externalFileId: item.externalFileId,
+                  externalFileUrl: item.externalFileUrl
                }))
            );

--- a/projects/app/src/pages/dataset/detail/components/Info.tsx
+++ b/projects/app/src/pages/dataset/detail/components/Info.tsx
@@ -1,10 +1,9 @@
 import React, { useState, useMemo } from 'react';
 import { useRouter } from 'next/router';
-import { Box, Flex, Button, IconButton, Input, Textarea } from '@chakra-ui/react';
+import { Box, Flex, Button, IconButton, Input, Textarea, HStack } from '@chakra-ui/react';
 import { DeleteIcon } from '@chakra-ui/icons';
 import { delDatasetById } from '@/web/core/dataset/api';
 import { useSelectFile } from '@/web/common/file/hooks/useSelectFile';
-import { useDatasetStore } from '@/web/core/dataset/store/dataset';
 import { useConfirm } from '@fastgpt/web/hooks/useConfirm';
 import { useForm } from 'react-hook-form';
 import { compressImgFileAndUpload } from '@/web/common/file/controller';
@@ -24,6 +23,7 @@ import { useContextSelector } from 'use-context-selector';
 import { DatasetPageContext } from '@/web/core/dataset/context/datasetPageContext';
 import MyDivider from '@fastgpt/web/components/common/MyDivider/index';
 import { DatasetTypeEnum } from '@fastgpt/global/core/dataset/constants';
+import QuestionTip from '@fastgpt/web/components/common/MyTooltip/QuestionTip';

 const Info = ({ datasetId }: { datasetId: string }) => {
  const { t } = useTranslation();
@@ -191,9 +191,10 @@ const Info = ({ datasetId }: { datasetId: string }) => {
      {datasetDetail.type === DatasetTypeEnum.externalFile && (
        <>
          <Flex w={'100%'} alignItems={'center'}>
-            <Box fontSize={['sm', 'md']} flex={['0 0 90px', '0 0 160px']} w={0}>
-              {datasetT('External read url')}
-            </Box>
+            <HStack fontSize={['sm', 'md']} flex={['0 0 90px', '0 0 160px']} w={0}>
+              <Box>{datasetT('External read url')}</Box>
+              <QuestionTip label={datasetT('External read url tip')} />
+            </HStack>
            <Input
              flex={[1, '0 0 320px']}
              placeholder="https://test.com/read?fileId={{fileId}}"
--- a/projects/app/src/pages/dataset/detail/components/InputDataModal.tsx
+++ b/projects/app/src/pages/dataset/detail/components/InputDataModal.tsx
@@ -237,6 +237,7 @@ const InputDataModal = ({
            w={'210px'}
            className="textEllipsis3"
            whiteSpace={'pre-wrap'}
+            collectionId={collection._id}
            sourceName={collection.sourceName}
            sourceId={collection.sourceId}
            mb={6}
--- a/projects/app/src/pages/dataset/list/component/CreateModal.tsx
+++ b/projects/app/src/pages/dataset/list/component/CreateModal.tsx
@@ -116,13 +116,13 @@ const CreateModal = ({ onClose, parentId }: { onClose: () => void; parentId?: st
                      value: DatasetTypeEnum.websiteDataset,
                      icon: 'core/dataset/websiteDataset',
                      desc: datasetT('Website Dataset Desc')
+                    },
+                    {
+                      title: datasetT('External File'),
+                      value: DatasetTypeEnum.externalFile,
+                      icon: 'core/dataset/externalDataset',
+                      desc: datasetT('External file Dataset Desc')
                    }
-                    // {
-                    //   title: datasetT('External File'),
-                    //   value: DatasetTypeEnum.externalFile,
-                    //   icon: 'core/dataset/websiteDataset',
-                    //   desc: datasetT('External file Dataset Desc')
-                    // }
                  ]
                : [])
            ]}