fix dataset quick create modal (#5951)

* fix: text split * remove test * perf: create dataset modal * remove log * fix dataset quick create modal (#5949) * fix dataset quick create modal * fix ui * doc * fix: text width --------- Co-authored-by: heheer <heheer@sealos.io>
2025-11-28 01:04:42 +08:00 · 2025-11-18 18:31:28 +08:00
parent 3f47b58a73
commit 6adee71c7a
14 changed files with 379 additions and 150 deletions
--- a/document/content/docs/upgrading/4-14/4142.mdx
+++ b/document/content/docs/upgrading/4-14/4142.mdx
@@ -21,6 +21,7 @@ description: 'FastGPT V4.14.2 更新说明'
 1. 简易应用模板未正常转化。
 2. 工具调用中，包含两个以上连续用户选择时候，第二个用户选择异常。
 3. 门户中，团队应用类型错误。
+4. 应用作为 MCP 导出，被其他应用使用时，全局变量不需要填写。 

 ## 插件

--- a/document/data/doc-last-modified.json
+++ b/document/data/doc-last-modified.json
@@ -116,7 +116,7 @@
  "document/content/docs/upgrading/4-13/4132.mdx": "2025-10-21T11:46:53+08:00",
  "document/content/docs/upgrading/4-14/4140.mdx": "2025-11-06T15:43:00+08:00",
  "document/content/docs/upgrading/4-14/4141.mdx": "2025-11-12T12:19:02+08:00",
-  "document/content/docs/upgrading/4-14/4142.mdx": "2025-11-17T19:34:52+08:00",
+  "document/content/docs/upgrading/4-14/4142.mdx": "2025-11-17T21:02:39+08:00",
  "document/content/docs/upgrading/4-8/40.mdx": "2025-08-02T19:38:37+08:00",
  "document/content/docs/upgrading/4-8/41.mdx": "2025-08-02T19:38:37+08:00",
  "document/content/docs/upgrading/4-8/42.mdx": "2025-08-02T19:38:37+08:00",
--- a/packages/web/i18n/en/app.json
+++ b/packages/web/i18n/en/app.json
@@ -129,6 +129,7 @@
  "dataset": "dataset",
  "dataset.Select_dataset_model_tip": "Only knowledge bases with the same index model can be selected",
  "dataset.create_dataset_tips": "For more advanced operations, please go to",
+  "dataset_create_failed": "Knowledge base creation failed",
  "dataset_create_success": "The knowledge base was created successfully and files are being indexed in the background.",
  "dataset_empty_tips": "You don’t have a knowledge base yet, create one first.",
  "dataset_search_tool_description": "Call the \"Semantic Search\" and \"Full-text Search\" capabilities to find reference content that may be related to the problem from the \"Knowledge Base\". \nPrioritize calling this tool to assist in answering user questions.",
--- a/packages/web/i18n/zh-CN/app.json
+++ b/packages/web/i18n/zh-CN/app.json
@@ -132,6 +132,7 @@
  "dataset": "知识库",
  "dataset.Select_dataset_model_tip": "仅能选择同一个索引模型的知识库",
  "dataset.create_dataset_tips": "更多高级操作请前往",
+  "dataset_create_failed": "知识库创建失败",
  "dataset_create_success": "知识库创建成功，正在后台索引文件",
  "dataset_empty_tips": "你还没有知识库，先创建一个吧",
  "dataset_search_tool_description": "调用“语义检索”和“全文检索”能力，从“知识库”中查找可能与问题相关的参考内容。优先调用该工具来辅助回答用户的问题。",
--- a/packages/web/i18n/zh-Hant/app.json
+++ b/packages/web/i18n/zh-Hant/app.json
@@ -128,6 +128,7 @@
  "dataset": "知識庫",
  "dataset.Select_dataset_model_tip": "僅能選擇同一個索引模型的知識庫",
  "dataset.create_dataset_tips": "更多高級操作請前往",
+  "dataset_create_failed": "知識庫創建失敗",
  "dataset_create_success": "知識庫創建成功，正在後台索引文件",
  "dataset_empty_tips": "你還沒有知識庫，先創建一個吧",
  "dataset_search_tool_description": "呼叫「語意搜尋」和「全文搜尋」功能，從「知識庫」中尋找可能與問題相關的參考內容。優先呼叫這個工具來協助回答使用者的問題。",
--- a/projects/app/src/components/Layout/navbar.tsx
+++ b/projects/app/src/components/Layout/navbar.tsx
@@ -110,8 +110,8 @@ const Navbar = ({ unread }: { unread: number }) => {
    [lastChatAppId, lastPane, t, userInfo?.username]
  );

-  const isSecondNavbarPage = useMemo(() => {
-    return ['/plugin'].includes(router.pathname);
+  const isDashboardPage = useMemo(() => {
+    return router.pathname.startsWith('/dashboard');
  }, [router.pathname]);

  return (
@@ -123,7 +123,7 @@ const Navbar = ({ unread }: { unread: number }) => {
      w={'100%'}
      userSelect={'none'}
      pb={2}
-      bg={isSecondNavbarPage ? 'white' : 'transparent'}
+      bg={isDashboardPage ? 'white' : 'transparent'}
    >
      {/* logo */}
      <Box flex={'0 0 auto'} mb={3}>
@@ -147,7 +147,7 @@ const Navbar = ({ unread }: { unread: number }) => {
                : {
                    bg: 'transparent',
                    _hover: {
-                      bg: isSecondNavbarPage ? 'white' : 'rgba(255,255,255,0.9)'
+                      bg: isDashboardPage ? 'white' : 'rgba(255,255,255,0.9)'
                    }
                  })}
              {...(item.link !== router.asPath
--- a/projects/app/src/components/core/app/DatasetSelectModal.tsx
+++ b/projects/app/src/components/core/app/DatasetSelectModal.tsx
@@ -27,7 +27,8 @@ import SearchInput from '@fastgpt/web/components/common/Input/SearchInput';
 import { useDatasetSelect } from '@/components/core/dataset/SelectModal';
 import FolderPath from '@/components/common/folder/Path';
 import EmptyTip from '@fastgpt/web/components/common/EmptyTip';
-import QuickCreateDatasetModal from '@/pageComponents/app/detail/components/QuickCreateModal';
+import QuickCreateDatasetModal from '@/pageComponents/app/detail/components/QuickCreateDatasetModal';
+import { useUserStore } from '@/web/support/user/useUserStore';

 // Dataset selection modal component
 export const DatasetSelectModal = ({
@@ -47,6 +48,7 @@ export const DatasetSelectModal = ({
  const [selectedDatasets, setSelectedDatasets] =
    useState<SelectedDatasetType[]>(defaultSelectedDatasets);
  const { toast } = useToast();
+  const { userInfo } = useUserStore();

  // Use server-side search, following the logic of the dataset list page
  const {
@@ -154,9 +156,11 @@ export const DatasetSelectModal = ({
      <Flex h="100%" direction="column" flex={1} overflow="hidden" minH={0}>
        <ModalBody flex={1} h={0} overflow="hidden">
          {isRootEmpty ? (
-            <VStack mt={8}>
+            <VStack h={'full'} justifyContent={'center'}>
              <EmptyTip text={t('app:dataset_empty_tips')} py={4} />
-              <Button onClick={onOpenQuickCreate}>{t('common:Create')}</Button>
+              {userInfo?.team?.permission.hasDatasetCreatePer && (
+                <Button onClick={onOpenQuickCreate}>{t('common:Create')}</Button>
+              )}
            </VStack>
          ) : (
            <>
@@ -427,7 +431,7 @@ export const DatasetSelectModal = ({
        {/* Modal footer button area */}
        <ModalFooter>
          <HStack spacing={4} w="full" align="center">
-            {!isRootEmpty && (
+            {!isRootEmpty && userInfo?.team?.permission.hasDatasetCreatePer && (
              <Button
                leftIcon={<MyIcon name="common/addLight" w={4} />}
                variant={'transparentBase'}
--- a/projects/app/src/pageComponents/app/detail/SimpleApp/components/ToolSelectModal.tsx
+++ b/projects/app/src/pageComponents/app/detail/SimpleApp/components/ToolSelectModal.tsx
@@ -408,17 +408,15 @@ const RenderList = React.memo(function RenderList({
                      borderRadius={'sm'}
                      flexShrink={0}
                    />
-                    <Box
-                      px={3}
-                      color={'myGray.900'}
-                      fontWeight={'500'}
-                      fontSize={'sm'}
-                      maxW={'180px'}
-                      whiteSpace={'nowrap'}
-                      overflow={'hidden'}
-                      textOverflow={'ellipsis'}
-                    >
-                      {t(parseI18nString(template.name, i18n.language))}
+                    <Box flex={'1 0 0'} ml={3}>
+                      <Box
+                        color={'myGray.900'}
+                        fontWeight={'500'}
+                        fontSize={'sm'}
+                        className="textEllipsis"
+                      >
+                        {t(parseI18nString(template.name, i18n.language))}
+                      </Box>
                    </Box>
                    <Box flex={1} />

--- a/projects/app/src/pageComponents/app/detail/components/QuickCreateDatasetModal.tsx
+++ b/projects/app/src/pageComponents/app/detail/components/QuickCreateDatasetModal.tsx
@@ -1,4 +1,4 @@
-import React, { useState } from 'react';
+import React, { useState, useMemo } from 'react';
 import { useTranslation } from 'next-i18next';
 import { useForm } from 'react-hook-form';
 import {
@@ -18,21 +18,10 @@ import MyTooltip from '@fastgpt/web/components/common/MyTooltip';
 import MyIcon from '@fastgpt/web/components/common/Icon';
 import { useUploadAvatar } from '@fastgpt/web/common/file/hooks/useUploadAvatar';
 import { useRequest2 } from '@fastgpt/web/hooks/useRequest';
-import {
-  postCreateDataset,
-  getDatasetById,
-  postCreateDatasetFileCollection
-} from '@/web/core/dataset/api';
+import { postCreateDatasetWithFiles, getDatasetById } from '@/web/core/dataset/api';
 import { getUploadAvatarPresignedUrl } from '@/web/common/file/api';
 import { uploadFile2DB } from '@/web/common/file/controller';
 import { useSystemStore } from '@/web/common/system/useSystemStore';
-import {
-  ChunkSettingModeEnum,
-  ChunkTriggerConfigTypeEnum,
-  DataChunkSplitModeEnum,
-  DatasetCollectionDataProcessModeEnum,
-  DatasetTypeEnum
-} from '@fastgpt/global/core/dataset/constants';
 import { getWebDefaultEmbeddingModel, getWebDefaultLLMModel } from '@/web/common/system/utils';
 import { BucketNameEnum } from '@fastgpt/global/common/file/constants';
 import { getErrText } from '@fastgpt/global/common/error/utils';
@@ -66,6 +55,11 @@ const QuickCreateDatasetModal = ({

  const [selectFiles, setSelectFiles] = useState<ImportSourceItemType[]>([]);

+  const successFiles = useMemo(
+    () => selectFiles.filter((item) => item.dbFileId && !item.errorMsg),
+    [selectFiles]
+  );
+
  const { register, handleSubmit, watch, setValue } = useForm({
    defaultValues: {
      parentId,
@@ -83,103 +77,106 @@ const QuickCreateDatasetModal = ({
      }
    });

-  const handleSelectFiles = (files: SelectFileItemType[]) => {
-    setSelectFiles((state) => [
-      ...state,
-      ...files.map<ImportSourceItemType>((selectFile) => {
-        const { fileId, file } = selectFile;
+  const { runAsync: handleSelectFiles, loading: uploading } = useRequest2(
+    async (files: SelectFileItemType[]) => {
+      await Promise.all(
+        files.map(async ({ fileId, file }) => {
+          try {
+            const { fileId: uploadFileId } = await uploadFile2DB({
+              file,
+              bucketName: BucketNameEnum.dataset,
+              data: { datasetId: '' },
+              percentListen: (percent) => {
+                setSelectFiles((state) =>
+                  state.map((item) =>
+                    item.id === fileId
+                      ? {
+                          ...item,
+                          uploadedFileRate: item.uploadedFileRate
+                            ? Math.max(percent, item.uploadedFileRate)
+                            : percent
+                        }
+                      : item
+                  )
+                );
+              }
+            });

-        return {
-          id: fileId,
-          createStatus: 'waiting',
-          file,
-          sourceName: file.name,
-          sourceSize: formatFileSize(file.size),
-          icon: getFileIcon(file.name),
-          uploadedFileRate: 0
-        };
-      })
-    ]);
-  };
-
-  const uploadSingleFile = async (fileItem: ImportSourceItemType, datasetId: string) => {
-    try {
-      if (!fileItem.file) return;
-      setSelectFiles((prev) =>
-        prev.map((item) => (item.id === fileItem.id ? { ...item, uploadedFileRate: 0 } : item))
+            setSelectFiles((state) =>
+              state.map((item) =>
+                item.id === fileId
+                  ? {
+                      ...item,
+                      dbFileId: uploadFileId,
+                      isUploading: false,
+                      uploadedFileRate: 100
+                    }
+                  : item
+              )
+            );
+          } catch (error) {
+            setSelectFiles((state) =>
+              state.map((item) =>
+                item.id === fileId
+                  ? {
+                      ...item,
+                      isUploading: false,
+                      errorMsg: getErrText(error)
+                    }
+                  : item
+              )
+            );
+          }
+        })
      );
+    },
+    {
+      manual: true,
+      onBefore([files]) {
+        setSelectFiles((state) => [
+          ...state,
+          ...files.map<ImportSourceItemType>((selectFile) => {
+            const { fileId, file } = selectFile;

-      const { fileId } = await uploadFile2DB({
-        file: fileItem.file,
-        bucketName: BucketNameEnum.dataset,
-        data: { datasetId },
-        percentListen: (percent) => {
-          setSelectFiles((prev) =>
-            prev.map((item) =>
-              item.id === fileItem.id
-                ? { ...item, uploadedFileRate: Math.max(percent, item.uploadedFileRate || 0) }
-                : item
-            )
-          );
-        }
-      });
-
-      await postCreateDatasetFileCollection({
-        datasetId,
-        fileId,
-        trainingType: DatasetCollectionDataProcessModeEnum.chunk,
-        chunkTriggerType: ChunkTriggerConfigTypeEnum.minSize,
-        chunkTriggerMinSize: 1000,
-        chunkSettingMode: ChunkSettingModeEnum.auto,
-        chunkSplitMode: DataChunkSplitModeEnum.paragraph,
-        chunkSize: 1024,
-        indexSize: 512,
-        customPdfParse: false
-      });
-
-      setSelectFiles((prev) =>
-        prev.map((item) =>
-          item.id === fileItem.id ? { ...item, dbFileId: fileId, uploadedFileRate: 100 } : item
-        )
-      );
-    } catch (error) {
-      setSelectFiles((prev) =>
-        prev.map((item) =>
-          item.id === fileItem.id ? { ...item, errorMsg: getErrText(error) } : item
-        )
-      );
+            return {
+              id: fileId,
+              createStatus: 'waiting',
+              file,
+              sourceName: file.name,
+              sourceSize: formatFileSize(file.size),
+              icon: getFileIcon(file.name),
+              isUploading: true,
+              uploadedFileRate: 0
+            };
+          })
+        ]);
+      }
    }
-  };
+  );

  const { runAsync: onCreate, loading: isCreating } = useRequest2(
    async (data) => {
-      const datasetId = await postCreateDataset({
-        name: data.name.trim(),
-        avatar: data.avatar,
-        intro: '',
-        parentId,
-        type: DatasetTypeEnum.dataset,
-        vectorModel: defaultVectorModel,
-        agentModel: defaultAgentModel,
-        vlmModel: defaultVLLM
+      return await postCreateDatasetWithFiles({
+        datasetParams: {
+          name: data.name.trim(),
+          avatar: data.avatar,
+          parentId,
+          vectorModel: defaultVectorModel,
+          agentModel: defaultAgentModel,
+          vlmModel: defaultVLLM
+        },
+        files: selectFiles
+          .filter((item) => item.dbFileId && !item.errorMsg)
+          .map((item) => ({
+            fileId: item.dbFileId!,
+            name: item.sourceName
+          }))
      });
-
-      if (selectFiles.length > 0) {
-        await Promise.all(selectFiles.map((file) => uploadSingleFile(file, datasetId)));
-      }
-
-      const datasetDetail = await getDatasetById(datasetId);
-
-      return {
-        datasetId,
-        name: datasetDetail.name,
-        avatar: datasetDetail.avatar,
-        vectorModel: datasetDetail.vectorModel
-      };
    },
    {
      manual: true,
      successToast: t('app:dataset_create_success'),
+      errorToast: t('app:dataset_create_failed'),
      onSuccess: (result) => {
        onSuccess(result);
        onClose();
@@ -198,18 +195,19 @@ const QuickCreateDatasetModal = ({
    >
      <ModalBody py={6} minH={'500px'}>
        <Box mb={6}>
-          <FormLabel mb={2}>{t('common:app_icon_and_name')}</FormLabel>
+          <FormLabel mb={2}>{t('common:input_name')}</FormLabel>
          <Flex alignItems={'center'}>
            <MyTooltip label={t('common:set_avatar')}>
-              <Avatar
-                src={avatar}
-                w={9}
-                h={9}
-                mr={4}
-                borderRadius={'8px'}
-                cursor={'pointer'}
-                onClick={handleAvatarSelectorOpen}
-              />
+              <Box w={9} h={9} mr={4}>
+                <Avatar
+                  src={avatar}
+                  w={'full'}
+                  h={'full'}
+                  borderRadius={'8px'}
+                  cursor={'pointer'}
+                  onClick={handleAvatarSelectorOpen}
+                />
+              </Box>
            </MyTooltip>
            <FormControl flex={1}>
              <Input
@@ -288,7 +286,7 @@ const QuickCreateDatasetModal = ({
                    ) : null}
                  </Flex>
                  <Flex w={1 / 5} justifyContent={'end'}>
-                    {!item.uploadedFileRate && (
+                    {!item.isUploading && (
                      <Flex alignItems={'center'} justifyContent={'center'} w={6} h={6}>
                        <MyIcon
                          name={'delete'}
@@ -331,7 +329,7 @@ const QuickCreateDatasetModal = ({
          </Button>
          <Button
            isLoading={isCreating}
-            isDisabled={selectFiles.length === 0}
+            isDisabled={successFiles.length === 0 || uploading}
            onClick={handleSubmit(onCreate)}
          >
            {t('common:Create')}
--- a/projects/app/src/pageComponents/dataset/detail/Form/CollectionChunkForm.tsx
+++ b/projects/app/src/pageComponents/dataset/detail/Form/CollectionChunkForm.tsx
@@ -349,7 +349,7 @@ const CollectionChunkForm = ({ form }: { form: UseFormReturn<CollectionChunkForm
              desc: t('dataset:custom_data_process_params_desc'),
              value: ChunkSettingModeEnum.custom,
              children: chunkSettingMode === ChunkSettingModeEnum.custom && (
-                <Box mt={5}>
+                <Box>
                  <Box>
                    <RadioGroup<DataChunkSplitModeEnum>
                      list={[
@@ -377,8 +377,8 @@ const CollectionChunkForm = ({ form }: { form: UseFormReturn<CollectionChunkForm

                    {chunkSplitMode === DataChunkSplitModeEnum.paragraph && (
                      <>
-                        <Box mt={3}>
-                          <Box fontSize={'sm'}>{t('dataset:llm_paragraph_mode')}</Box>
+                        <Box mt={3} fontSize={'sm'}>
+                          <Box mb={1}>{t('dataset:llm_paragraph_mode')}</Box>
                          <MySelect<ParagraphChunkAIModeEnum>
                            size={'sm'}
                            bg={'myGray.50'}
@@ -406,7 +406,7 @@ const CollectionChunkForm = ({ form }: { form: UseFormReturn<CollectionChunkForm
                          />
                        </Box>
                        <Box mt={2} fontSize={'sm'}>
-                          <Box>{t('dataset:paragraph_max_deep')}</Box>
+                          <Box mb={1}>{t('dataset:paragraph_max_deep')}</Box>
                          <MyNumberInput
                            size={'sm'}
                            bg={'myGray.50'}
@@ -419,7 +419,7 @@ const CollectionChunkForm = ({ form }: { form: UseFormReturn<CollectionChunkForm
                          />
                        </Box>
                        <Box mt={2} fontSize={'sm'}>
-                          <Box>{t('dataset:max_chunk_size')}</Box>
+                          <Box mb={1}>{t('dataset:max_chunk_size')}</Box>
                          <Box
                            css={{
                              '& > span': {
@@ -478,7 +478,7 @@ const CollectionChunkForm = ({ form }: { form: UseFormReturn<CollectionChunkForm

                    {chunkSplitMode === DataChunkSplitModeEnum.char && (
                      <Box mt={3} fontSize={'sm'}>
-                        <Box>{t('dataset:custom_split_char')}</Box>
+                        <Box mb={1}>{t('dataset:custom_split_char')}</Box>
                        <HStack>
                          <Box flex={'1 0 0'}>
                            <MySelect<string>
--- a/projects/app/src/pages/api/common/file/upload.ts
+++ b/projects/app/src/pages/api/common/file/upload.ts
@@ -13,12 +13,14 @@ import { authDataset } from '@fastgpt/service/support/permission/dataset/auth';
 import { type OutLinkChatAuthProps } from '@fastgpt/global/support/permission/chat';
 import { WritePermissionVal } from '@fastgpt/global/support/permission/constant';
 import { createFileToken } from '@fastgpt/service/support/permission/auth/file';
+import { authUserPer } from '@fastgpt/service/support/permission/user/auth';
+import { TeamDatasetCreatePermissionVal } from '@fastgpt/global/support/permission/user/constant';

 export type UploadChatFileProps = {
  appId: string;
 } & OutLinkChatAuthProps;
 export type UploadDatasetFileProps = {
-  datasetId: string;
+  datasetId?: string;
 };

 const authUploadLimit = (tmbId: string) => {
@@ -58,18 +60,32 @@ async function handler(req: NextApiRequest, res: NextApiResponse<any>) {
        };
      }
      if (bucketName === 'dataset') {
-        const chatData = data as UploadDatasetFileProps;
-        const authData = await authDataset({
-          datasetId: chatData.datasetId,
-          per: WritePermissionVal,
-          req,
-          authToken: true,
-          authApiKey: true
-        });
-        return {
-          teamId: authData.teamId,
-          uid: authData.tmbId
-        };
+        const datasetData = data as UploadDatasetFileProps;
+
+        if (datasetData.datasetId) {
+          const authData = await authDataset({
+            datasetId: datasetData.datasetId,
+            per: WritePermissionVal,
+            req,
+            authToken: true,
+            authApiKey: true
+          });
+          return {
+            teamId: authData.teamId,
+            uid: authData.tmbId
+          };
+        } else {
+          const authData = await authUserPer({
+            req,
+            authToken: true,
+            authApiKey: true,
+            per: TeamDatasetCreatePermissionVal
+          });
+          return {
+            teamId: authData.teamId,
+            uid: authData.tmbId
+          };
+        }
      }
      return Promise.reject('bucketName is empty');
    })();
--- a/projects/app/src/pages/api/core/dataset/createWithFiles.ts
+++ b/projects/app/src/pages/api/core/dataset/createWithFiles.ts
@@ -0,0 +1,203 @@
+import { NextAPI } from '@/service/middleware/entry';
+import { parseParentIdInMongo } from '@fastgpt/global/common/parentFolder/utils';
+import {
+  DatasetTypeEnum,
+  DatasetCollectionTypeEnum,
+  DatasetCollectionDataProcessModeEnum,
+  ChunkTriggerConfigTypeEnum,
+  ChunkSettingModeEnum,
+  DataChunkSplitModeEnum
+} from '@fastgpt/global/core/dataset/constants';
+import {
+  OwnerRoleVal,
+  PerResourceTypeEnum,
+  WritePermissionVal
+} from '@fastgpt/global/support/permission/constant';
+import { TeamDatasetCreatePermissionVal } from '@fastgpt/global/support/permission/user/constant';
+import { pushTrack } from '@fastgpt/service/common/middle/tracks/utils';
+import { mongoSessionRun } from '@fastgpt/service/common/mongo/sessionRun';
+import {
+  getDefaultEmbeddingModel,
+  getDefaultLLMModel,
+  getDefaultVLMModel,
+  getEmbeddingModel
+} from '@fastgpt/service/core/ai/model';
+import { MongoDataset } from '@fastgpt/service/core/dataset/schema';
+import { authDataset } from '@fastgpt/service/support/permission/dataset/auth';
+import { checkTeamDatasetLimit } from '@fastgpt/service/support/permission/teamLimit';
+import { authUserPer } from '@fastgpt/service/support/permission/user/auth';
+import type { ApiRequestProps } from '@fastgpt/service/type/next';
+import { addAuditLog } from '@fastgpt/service/support/user/audit/util';
+import { AuditEventEnum } from '@fastgpt/global/support/user/audit/constants';
+import { getI18nDatasetType } from '@fastgpt/service/support/user/audit/util';
+import { MongoResourcePermission } from '@fastgpt/service/support/permission/schema';
+import { getS3AvatarSource } from '@fastgpt/service/common/s3/sources/avatar';
+import { createCollectionAndInsertData } from '@fastgpt/service/core/dataset/collection/controller';
+import { getFileById, delFileByFileIdList } 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 { EmbeddingModelItemType } from '@fastgpt/global/core/ai/model.d';
+
+export type DatasetCreateWithFilesQuery = {};
+export type DatasetCreateWithFilesBody = {
+  datasetParams: {
+    name: string;
+    avatar: string;
+    parentId?: string;
+    vectorModel?: string;
+    agentModel?: string;
+    vlmModel?: string;
+  };
+  files: {
+    fileId: string;
+    name: string;
+  }[];
+};
+export type DatasetCreateWithFilesResponse = {
+  datasetId: string;
+  name: string;
+  avatar: string;
+  vectorModel: EmbeddingModelItemType;
+};
+
+async function handler(
+  req: ApiRequestProps<DatasetCreateWithFilesBody, DatasetCreateWithFilesQuery>
+): Promise<DatasetCreateWithFilesResponse> {
+  const { datasetParams, files } = req.body;
+  const {
+    parentId,
+    name,
+    avatar,
+    vectorModel = getDefaultEmbeddingModel()?.model,
+    agentModel = getDefaultLLMModel()?.model,
+    vlmModel = getDefaultVLMModel()?.model
+  } = datasetParams;
+
+  const { teamId, tmbId, userId } = parentId
+    ? await authDataset({
+        req,
+        datasetId: parentId,
+        authToken: true,
+        authApiKey: true,
+        per: WritePermissionVal
+      })
+    : await authUserPer({
+        req,
+        authToken: true,
+        authApiKey: true,
+        per: TeamDatasetCreatePermissionVal
+      });
+
+  // check limit
+  await checkTeamDatasetLimit(teamId);
+
+  try {
+    const result = await mongoSessionRun(async (session) => {
+      // 1. Create dataset
+      const [dataset] = await MongoDataset.create(
+        [
+          {
+            ...parseParentIdInMongo(parentId),
+            name,
+            teamId,
+            tmbId,
+            vectorModel,
+            agentModel,
+            vlmModel,
+            avatar,
+            intro: '',
+            type: DatasetTypeEnum.dataset
+          }
+        ],
+        { session, ordered: true }
+      );
+
+      // 2. Create permission
+      await MongoResourcePermission.insertOne({
+        teamId,
+        tmbId,
+        resourceId: dataset._id,
+        permission: OwnerRoleVal,
+        resourceType: PerResourceTypeEnum.dataset
+      });
+
+      // 3. Refresh avatar
+      await getS3AvatarSource().refreshAvatar(avatar, undefined, session);
+
+      // 4. Create collections for each file
+      for (const file of files) {
+        const gridFile = await getFileById({
+          bucketName: BucketNameEnum.dataset,
+          fileId: file.fileId
+        });
+
+        if (!gridFile) {
+          return Promise.reject(CommonErrEnum.fileNotFound);
+        }
+
+        await createCollectionAndInsertData({
+          dataset,
+          createCollectionParams: {
+            datasetId: dataset._id,
+            teamId,
+            tmbId,
+            type: DatasetCollectionTypeEnum.file,
+            name: file.name || gridFile.filename,
+            fileId: file.fileId,
+            metadata: {
+              relatedImgId: file.fileId
+            },
+            trainingType: DatasetCollectionDataProcessModeEnum.chunk,
+            chunkTriggerType: ChunkTriggerConfigTypeEnum.minSize,
+            chunkTriggerMinSize: 1000,
+            chunkSettingMode: ChunkSettingModeEnum.auto,
+            chunkSplitMode: DataChunkSplitModeEnum.paragraph,
+            chunkSize: 1024,
+            indexSize: 512,
+            customPdfParse: false
+          },
+          session
+        });
+      }
+
+      return {
+        datasetId: dataset._id,
+        name: dataset.name,
+        avatar: dataset.avatar,
+        vectorModel: getEmbeddingModel(dataset.vectorModel)
+      };
+    });
+
+    // Track and audit log
+    pushTrack.createDataset({
+      type: DatasetTypeEnum.dataset,
+      teamId,
+      tmbId,
+      uid: userId
+    });
+
+    (async () => {
+      addAuditLog({
+        tmbId,
+        teamId,
+        event: AuditEventEnum.CREATE_DATASET,
+        params: {
+          datasetName: name,
+          datasetType: getI18nDatasetType(DatasetTypeEnum.dataset)
+        }
+      });
+    })();
+
+    return result;
+  } catch (error) {
+    const fileIds = files.map((file) => file.fileId);
+    await delFileByFileIdList({
+      bucketName: BucketNameEnum.dataset,
+      fileIdList: fileIds
+    });
+
+    return Promise.reject(error);
+  }
+}
+
+export default NextAPI(handler);
--- a/projects/app/src/pages/api/core/dataset/detail.ts
+++ b/projects/app/src/pages/api/core/dataset/detail.ts
@@ -6,7 +6,6 @@ import { type DatasetItemType } from '@fastgpt/global/core/dataset/type';
 import { type ApiRequestProps } from '@fastgpt/service/type/next';
 import { CommonErrEnum } from '@fastgpt/global/common/error/code/common';
 import { getDatasetSyncDatasetStatus } from '@fastgpt/service/core/dataset/datasetSync';
-import { DatasetStatusEnum, DatasetTypeEnum } from '@fastgpt/global/core/dataset/constants';
 import { filterApiDatasetServerPublicData } from '@fastgpt/global/core/dataset/apiDataset/utils';

 type Query = {
--- a/projects/app/src/web/core/dataset/api.ts
+++ b/projects/app/src/web/core/dataset/api.ts
@@ -79,6 +79,10 @@ import type {
  GetApiDatasetPathResponse
 } from '@/pages/api/core/dataset/apiDataset/getPathNames';
 import type { DelCollectionBody } from '@/pages/api/core/dataset/collection/delete';
+import type {
+  DatasetCreateWithFilesBody,
+  DatasetCreateWithFilesResponse
+} from '@/pages/api/core/dataset/createWithFiles';

 /* ======================== dataset ======================= */
 export const getDatasets = (data: GetDatasetListBody) =>
@@ -100,6 +104,9 @@ export const getDatasetById = (id: string) => GET<DatasetItemType>(`/core/datase
 export const postCreateDataset = (data: CreateDatasetParams) =>
  POST<string>(`/core/dataset/create`, data);

+export const postCreateDatasetWithFiles = (data: DatasetCreateWithFilesBody) =>
+  POST<DatasetCreateWithFilesResponse>(`/core/dataset/createWithFiles`, data);
+
 export const putDatasetById = (data: DatasetUpdateBody) => PUT<void>(`/core/dataset/update`, data);

 export const delDatasetById = (id: string) => DELETE(`/core/dataset/delete?id=${id}`);