fix: dataset data list api adapt (#2878)

* fix: dataset data list api adapt

* update doc version

* perf: fedomain env

* add fedomain env

docSite/content/zh-cn/docs/development/openapi/dataset.md

@@ -1093,6 +1093,22 @@ A2:
 {{< tab tabName="请求示例" >}}
 {{< markdownify >}}
 
+**4.8.11+**
+
+```bash
+curl --location --request POST 'http://localhost:3000/api/core/dataset/data/v2/list' \
+--header 'Authorization: Bearer {{authorization}}' \
+--header 'Content-Type: application/json' \
+--data-raw '{
+    "offset": 0,
+    "pageSize": 10,
+    "collectionId":"65abd4ac9d1448617cba6171",
+    "searchText":""
+}'
+```
+
+**4.6.7+**
+
 ```bash
 curl --location --request POST 'http://localhost:3000/api/core/dataset/data/list' \
 --header 'Authorization: Bearer {{authorization}}' \
@@ -1112,10 +1128,13 @@ curl --location --request POST 'http://localhost:3000/api/core/dataset/data/list
 {{< markdownify >}}
 
 {{% alert icon=" " context="success" %}}
+
+- pageNum: 偏移量（选填）
 - pageNum: 页码（选填）
 - pageSize: 每页数量，最大30（选填）
 - collectionId: 集合的ID（必填）
 - searchText: 模糊搜索词（选填）
+  
 {{% /alert %}}
 
 {{< /markdownify >}}

docSite/content/zh-cn/docs/development/upgrading/4812.md

@@ -10,4 +10,5 @@ weight: 812
 ## 更新说明
 
 1. 新增 - 全局变量支持更多数据类型
-2. 修复 - 文件后缀判断，去除 query 影响。
+2. 新增 - FE_DOMAIN 环境变量，配置该环境变量后，上传文件/图片会补全后缀后得到完整地址。（可解决 docx 文件图片链接，有时会无法被模型识别问题）
+3. 修复 - 文件后缀判断，去除 query 影响。

files/docker/docker-compose-milvus.yml

@@ -154,6 +154,8 @@ services:
       - MILVUS_TOKEN=none
       # sandbox 地址
       - SANDBOX_URL=http://sandbox:3000
+      # 前端地址
+      - FE_DOMAIN=
       # 日志等级: debug, info, warn, error
       - LOG_LEVEL=info
       - STORE_LOG_LEVEL=warn

files/docker/docker-compose-pgvector.yml

@@ -111,6 +111,8 @@ services:
       - PG_URL=postgresql://username:password@pg:5432/postgres
       # sandbox 地址
       - SANDBOX_URL=http://sandbox:3000
+      # 前端地址
+      - FE_DOMAIN=
       # 日志等级: debug, info, warn, error
       - LOG_LEVEL=info
       - STORE_LOG_LEVEL=warn

files/docker/docker-compose-zilliz.yml

@@ -92,6 +92,8 @@ services:
       - MILVUS_TOKEN=zilliz_cloud_token
       # sandbox 地址
       - SANDBOX_URL=http://sandbox:3000
+      # 前端地址
+      - FE_DOMAIN=
       # 日志等级: debug, info, warn, error
       - LOG_LEVEL=info
       - STORE_LOG_LEVEL=warn

packages/service/common/file/image/controller.ts

@@ -5,10 +5,6 @@ import { ClientSession } from '../../../common/mongo';
 import { guessBase64ImageType } from '../utils';
 import { readFromSecondary } from '../../mongo/utils';
 
-export function getMongoImgUrl(id: string, extension: string) {
-  return `${imageBaseUrl}${id}.${extension}`;
-}
-
 export const maxImgSize = 1024 * 1024 * 12;
 const base64MimeRegex = /data:image\/([^\)]+);base64/;
 export async function uploadMongoImg({
@@ -39,7 +35,7 @@ export async function uploadMongoImg({
     shareId
   });
 
-  return getMongoImgUrl(String(_id), extension);
+  return `${process.env.FE_DOMAIN || ''}${imageBaseUrl}${String(_id)}.${extension}`;
 }
 
 export async function readMongoImg({ id }: { id: string }) {

projects/app/.env.template

@@ -31,7 +31,7 @@ SANDBOX_URL=http://localhost:3001
 # 商业版地址
 PRO_URL=
 # 页面的地址，用于自动补全相对路径资源的 domain
-# FE_DOMAIN=http://localhost:3000
+FE_DOMAIN=http://localhost:3000
 
 # 日志等级: debug, info, warn, error
 LOG_LEVEL=debug

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

@@ -3,20 +3,19 @@ import { MongoDatasetData } from '@fastgpt/service/core/dataset/data/schema';
 import { replaceRegChars } from '@fastgpt/global/common/string/tools';
 import { NextAPI } from '@/service/middleware/entry';
 import { ReadPermissionVal } from '@fastgpt/global/support/permission/constant';
+import { PagingData, RequestPaging } from '@/types';
 import { ApiRequestProps } from '@fastgpt/service/type/next';
 import { DatasetDataListItemType } from '@/global/core/dataset/type';
-import { PaginationProps, PaginationResponse } from '@fastgpt/web/common/fetch/type';
 
-export type GetDatasetDataListProps = PaginationProps & {
+export type GetDatasetDataListProps = RequestPaging & {
   searchText?: string;
   collectionId: string;
 };
-export type GetDatasetDataListRes = PaginationResponse<DatasetDataListItemType>;
 
 async function handler(
   req: ApiRequestProps<GetDatasetDataListProps>
-): Promise<GetDatasetDataListRes> {
-  let { offset, pageSize = 10, searchText = '', collectionId } = req.body;
+): Promise<PagingData<DatasetDataListItemType>> {
+  let { pageNum = 1, pageSize = 10, searchText = '', collectionId } = req.body;
 
   pageSize = Math.min(pageSize, 30);
 
@@ -41,17 +40,19 @@ async function handler(
       : {})
   };
 
-  const [list, total] = await Promise.all([
+  const [data, total] = await Promise.all([
     MongoDatasetData.find(match, '_id datasetId collectionId q a chunkIndex')
       .sort({ chunkIndex: 1, updateTime: -1 })
-      .skip(offset)
+      .skip((pageNum - 1) * pageSize)
       .limit(pageSize)
       .lean(),
     MongoDatasetData.countDocuments(match)
   ]);
 
   return {
-    list,
+    pageNum,
+    pageSize,
+    data,
     total
   };
 }

projects/app/src/pages/api/core/dataset/data/v2/list.ts

@@ -0,0 +1,59 @@
+import { authDatasetCollection } from '@fastgpt/service/support/permission/dataset/auth';
+import { MongoDatasetData } from '@fastgpt/service/core/dataset/data/schema';
+import { replaceRegChars } from '@fastgpt/global/common/string/tools';
+import { NextAPI } from '@/service/middleware/entry';
+import { ReadPermissionVal } from '@fastgpt/global/support/permission/constant';
+import { ApiRequestProps } from '@fastgpt/service/type/next';
+import { DatasetDataListItemType } from '@/global/core/dataset/type';
+import { PaginationProps, PaginationResponse } from '@fastgpt/web/common/fetch/type';
+
+export type GetDatasetDataListProps = PaginationProps & {
+  searchText?: string;
+  collectionId: string;
+};
+export type GetDatasetDataListRes = PaginationResponse<DatasetDataListItemType>;
+
+async function handler(
+  req: ApiRequestProps<GetDatasetDataListProps>
+): Promise<GetDatasetDataListRes> {
+  let { offset, pageSize = 10, searchText = '', collectionId } = req.body;
+
+  pageSize = Math.min(pageSize, 30);
+
+  // 凭证校验
+  const { teamId, collection } = await authDatasetCollection({
+    req,
+    authToken: true,
+    authApiKey: true,
+    collectionId,
+    per: ReadPermissionVal
+  });
+
+  const queryReg = new RegExp(`${replaceRegChars(searchText)}`, 'i');
+  const match = {
+    teamId,
+    datasetId: collection.datasetId._id,
+    collectionId,
+    ...(searchText.trim()
+      ? {
+          $or: [{ q: queryReg }, { a: queryReg }]
+        }
+      : {})
+  };
+
+  const [list, total] = await Promise.all([
+    MongoDatasetData.find(match, '_id datasetId collectionId q a chunkIndex')
+      .sort({ chunkIndex: 1, updateTime: -1 })
+      .skip(offset)
+      .limit(pageSize)
+      .lean(),
+    MongoDatasetData.countDocuments(match)
+  ]);
+
+  return {
+    list,
+    total
+  };
+}
+
+export default NextAPI(handler);

projects/app/src/web/core/dataset/api.ts

@@ -51,7 +51,7 @@ import type { UpdateDatasetCollectionParams } from '@/pages/api/core/dataset/col
 import type {
   GetDatasetDataListProps,
   GetDatasetDataListRes
-} from '@/pages/api/core/dataset/data/list';
+} from '@/pages/api/core/dataset/data/v2/list';
 import type { UpdateDatasetDataProps } from '@fastgpt/global/core/dataset/controller';
 import type { DatasetFolderCreateBody } from '@/pages/api/core/dataset/folder/create';
 import type { PaginationProps, PaginationResponse } from '@fastgpt/web/common/fetch/type';
@@ -159,7 +159,7 @@ export const getScrollCollectionList = (data: GetScrollCollectionsProps) =>
 /* =============================== data ==================================== */
 /* get dataset list */
 export const getDatasetDataList = (data: GetDatasetDataListProps) =>
-  POST<GetDatasetDataListRes>(`/core/dataset/data/list`, data);
+  POST<GetDatasetDataListRes>(`/core/dataset/data/v2/list`, data);
 
 export const getDatasetDataItemById = (id: string) =>
   GET<DatasetDataItemType>(`/core/dataset/data/detail`, { id });