perf: retry to load image；perf: default index check (#4004)

c121914yu · c121914yu · commit d05259deddd1 · 2025-03-06T18:28:09.000+08:00
* perf: retry to load image

* perf: default index check
diff --git a/docSite/content/zh-cn/docs/development/openapi/dataset.md b/docSite/content/zh-cn/docs/development/openapi/dataset.md
@@ -1063,10 +1063,12 @@ curl --location --request DELETE 'http://localhost:3000/api/core/dataset/collect
 
 | 字段 | 类型 | 说明 | 必填 |
 | --- | --- | --- | --- |
-| defaultIndex | Boolean | 是否为默认索引 | ✅ |
-| dataId | String | 关联的向量ID | ✅ |
+| type | String | 可选索引类型：default-默认索引; custom-自定义索引; summary-总结索引; question-问题索引; image-图片索引 | |
+| dataId | String | 关联的向量ID，变更数据时候传入该 ID，会进行差量更新，而不是全量更新 |  |
 | text | String | 文本内容 | ✅ |
 
+`type` 不填则默认为 `custom` 索引，还会基于 q/a 组成一个默认索引。如果传入了默认索引，则不会额外创建。
+
 ### 为集合批量添加添加数据
 
 注意，每次最多推送 200 组数据。
@@ -1298,8 +1300,7 @@ curl --location --request GET 'http://localhost:3000/api/core/dataset/data/detai
         "chunkIndex": 0,
         "indexes": [
             {
-                "defaultIndex": true,
-                "type": "chunk",
+                "type": "default",
                 "dataId": "3720083",
                 "text": "N o . 2 0 2 2 1 2中 国 信 息 通 信 研 究 院京东探索研究院2022年 9月人工智能生成内容（AIGC）白皮书(2022 年)版权声明本白皮书版权属于中国信息通信研究院和京东探索研究院，并受法律保护。转载、摘编或利用其它方式使用本白皮书文字或者观点的，应注明“来源：中国信息通信研究院和京东探索研究院”。违反上述声明者，编者将追究其相关法律责任。前 言习近平总书记曾指出，“数字技术正以新理念、新业态、新模式全面融入人类经济、政治、文化、社会、生态文明建设各领域和全过程”。在当前数字世界和物理世界加速融合的大背景下，人工智能生成内容（Artificial Intelligence Generated Content，简称 AIGC）正在悄然引导着一场深刻的变革，重塑甚至颠覆数字内容的生产方式和消费模式，将极大地丰富人们的数字生活，是未来全面迈向数字文明新时代不可或缺的支撑力量。",
                 "_id": "65abd4b29d1448617cba61dc"
@@ -1334,13 +1335,19 @@ curl --location --request PUT 'http://localhost:3000/api/core/dataset/data/updat
     "q":"测试111",
     "a":"sss",
     "indexes":[
+        {
+            "dataId": "xxxx",
+            "type": "default",
+            "text": "默认索引"
+        },
         {
             "dataId": "xxx",
-            "defaultIndex":false,
-            "text":"自定义索引1"
+            "type": "custom",
+            "text": "旧的自定义索引1"
         },
         {
-            "text":"修改后的自定义索引2。（会删除原来的自定义索引2，并插入新的自定义索引2）"
+            "type":"custom",
+            "text":"新增的自定义索引"
         }
     ]
 }'
diff --git a/packages/global/common/string/markdown.ts b/packages/global/common/string/markdown.ts
@@ -168,7 +168,7 @@ export const markdownProcess = async ({
   return simpleMarkdownText(imageProcess);
 };
 
-export const matchMdImgTextAndUpload = (text: string) => {
+export const matchMdImg = (text: string) => {
   const base64Regex = /!\[([^\]]*)\]\((data:image\/[^;]+;base64[^)]+)\)/g;
   const imageList: ImageType[] = [];
 
diff --git a/packages/service/common/file/image/controller.ts b/packages/service/common/file/image/controller.ts
@@ -6,6 +6,7 @@ import { guessBase64ImageType } from '../utils';
 import { readFromSecondary } from '../../mongo/utils';
 import { addHours } from 'date-fns';
 import { imageFileType } from '@fastgpt/global/common/file/constants';
+import { retryFn } from '@fastgpt/global/common/system/utils';
 
 export const maxImgSize = 1024 * 1024 * 12;
 const base64MimeRegex = /data:image\/([^\)]+);base64/;
@@ -40,13 +41,15 @@ export async function uploadMongoImg({
     return Promise.reject(`Invalid image file type: ${mime}`);
   }
 
-  const { _id } = await MongoImage.create({
-    teamId,
-    binary,
-    metadata: Object.assign({ mime }, metadata),
-    shareId,
-    expiredTime: forever ? undefined : addHours(new Date(), 1)
-  });
+  const { _id } = await retryFn(() =>
+    MongoImage.create({
+      teamId,
+      binary,
+      metadata: Object.assign({ mime }, metadata),
+      shareId,
+      expiredTime: forever ? undefined : addHours(new Date(), 1)
+    })
+  );
 
   return `${process.env.NEXT_PUBLIC_BASE_URL || ''}${imageBaseUrl}${String(_id)}.${extension}`;
 }
diff --git a/packages/service/common/file/image/utils.ts b/packages/service/common/file/image/utils.ts
@@ -2,23 +2,30 @@ import axios from 'axios';
 import { addLog } from '../../system/log';
 import { serverRequestBaseUrl } from '../../api/serverRequest';
 import { getFileContentTypeFromHeader, guessBase64ImageType } from '../utils';
+import { retryFn } from '@fastgpt/global/common/system/utils';
 
 export const getImageBase64 = async (url: string) => {
   addLog.debug(`Load image to base64: ${url}`);
 
   try {
-    const response = await axios.get(url, {
-      baseURL: serverRequestBaseUrl,
-      responseType: 'arraybuffer',
-      proxy: false
-    });
+    const response = await retryFn(() =>
+      axios.get(url, {
+        baseURL: serverRequestBaseUrl,
+        responseType: 'arraybuffer',
+        proxy: false
+      })
+    );
 
     const base64 = Buffer.from(response.data, 'binary').toString('base64');
     const imageType =
       getFileContentTypeFromHeader(response.headers['content-type']) ||
       guessBase64ImageType(base64);
 
-    return `data:${imageType};base64,${base64}`;
+    return {
+      completeBase64: `data:${imageType};base64,${base64}`,
+      base64,
+      mime: imageType
+    };
   } catch (error) {
     addLog.debug(`Load image to base64 failed: ${url}`);
     console.log(error);
diff --git a/packages/service/common/file/read/utils.ts b/packages/service/common/file/read/utils.ts
@@ -6,11 +6,12 @@ import type { ImageType, ReadFileResponse } from '../../../worker/readFile/type'
 import axios from 'axios';
 import { addLog } from '../../system/log';
 import { batchRun } from '@fastgpt/global/common/system/utils';
-import { htmlTable2Md, matchMdImgTextAndUpload } from '@fastgpt/global/common/string/markdown';
+import { htmlTable2Md, matchMdImg } from '@fastgpt/global/common/string/markdown';
 import { createPdfParseUsage } from '../../../support/wallet/usage/controller';
 import { getErrText } from '@fastgpt/global/common/error/utils';
 import { delay } from '@fastgpt/global/common/system/utils';
 import { getNanoid } from '@fastgpt/global/common/string/tools';
+import { getImageBase64 } from '../image/utils';
 
 export type readRawTextByLocalFileParams = {
   teamId: string;
@@ -99,7 +100,7 @@ export const readRawContentByFileBuffer = async ({
     addLog.info(`Custom file parsing is complete, time: ${Date.now() - start}ms`);
 
     const rawText = response.markdown;
-    const { text, imageList } = matchMdImgTextAndUpload(rawText);
+    const { text, imageList } = matchMdImg(rawText);
 
     createPdfParseUsage({
       teamId,
@@ -120,31 +121,33 @@ export const readRawContentByFileBuffer = async ({
     const parseTextImage = async (text: string) => {
       // Extract image links and convert to base64
       const imageList: { id: string; url: string }[] = [];
-      const processedText = text.replace(/!\[.*?\]\((http[^)]+)\)/g, (match, url) => {
-        const id = getNanoid();
+      let processedText = text.replace(/!\[.*?\]\((http[^)]+)\)/g, (match, url) => {
+        const id = `IMAGE_${getNanoid()}_IMAGE`;
         imageList.push({
           id,
           url
         });
         return `![](${id})`;
       });
 
+      // Get base64 from image url
       let resultImageList: ImageType[] = [];
-      await Promise.all(
-        imageList.map(async (item) => {
+      await batchRun(
+        imageList,
+        async (item) => {
           try {
-            const response = await axios.get(item.url, { responseType: 'arraybuffer' });
-            const mime = response.headers['content-type'] || 'image/jpeg';
-            const base64 = response.data.toString('base64');
+            const { base64, mime } = await getImageBase64(item.url);
             resultImageList.push({
               uuid: item.id,
               mime,
               base64
             });
           } catch (error) {
+            processedText = processedText.replace(item.id, item.url);
             addLog.warn(`Failed to get image from ${item.url}: ${getErrText(error)}`);
           }
-        })
+        },
+        5
       );
 
       return {
@@ -312,14 +315,14 @@ export const readRawContentByFileBuffer = async ({
           return await uploadMongoImg({
             base64Img: `data:${item.mime};base64,${item.base64}`,
             teamId,
-            // expiredTime: addHours(new Date(), 1),
             metadata: {
               ...metadata,
               mime: item.mime
             }
           });
         } catch (error) {
-          return '';
+          addLog.warn('Upload file image error', { error });
+          return 'Upload load image error';
         }
       })();
       rawText = rawText.replace(item.uuid, src);
diff --git a/packages/service/core/chat/utils.ts b/packages/service/core/chat/utils.ts
@@ -165,7 +165,7 @@ export const loadRequestMessages = async ({
             try {
               // If imgUrl is a local path, load image from local, and set url to base64
               if (imgUrl.startsWith('/') || process.env.MULTIPLE_DATA_TO_BASE64 === 'true') {
-                const base64 = await getImageBase64(imgUrl);
+                const { completeBase64: base64 } = await getImageBase64(imgUrl);
 
                 return {
                   ...item,
diff --git a/packages/service/worker/htmlStr2Md/utils.ts b/packages/service/worker/htmlStr2Md/utils.ts
@@ -1,6 +1,6 @@
 import TurndownService from 'turndown';
 import { ImageType } from '../readFile/type';
-import { matchMdImgTextAndUpload } from '@fastgpt/global/common/string/markdown';
+import { matchMdImg } from '@fastgpt/global/common/string/markdown';
 import { getNanoid } from '@fastgpt/global/common/string/tools';
 // @ts-ignore
 const turndownPluginGfm = require('joplin-turndown-plugin-gfm');
@@ -46,7 +46,7 @@ export const html2md = (
     // Base64 img to id, otherwise it will occupy memory when going to md
     const { processedHtml, images } = processBase64Images(html);
     const md = turndownService.turndown(processedHtml);
-    const { text, imageList } = matchMdImgTextAndUpload(md);
+    const { text, imageList } = matchMdImg(md);
 
     return {
       rawText: text,
diff --git a/projects/app/src/pageComponents/dataset/detail/InputDataModal.tsx b/projects/app/src/pageComponents/dataset/detail/InputDataModal.tsx
@@ -1,5 +1,5 @@
 import React, { useCallback, useEffect, useMemo, useRef, useState } from 'react';
-import { Box, Flex, Button, Textarea, useTheme } from '@chakra-ui/react';
+import { Box, Flex, Button, Textarea } from '@chakra-ui/react';
 import {
   FieldArrayWithId,
   UseFieldArrayRemove,
@@ -19,8 +19,7 @@ import MyModal from '@fastgpt/web/components/common/MyModal';
 import MyTooltip from '@fastgpt/web/components/common/MyTooltip';
 import { useQuery } from '@tanstack/react-query';
 import { useTranslation } from 'next-i18next';
-import { useRequest, useRequest2 } from '@fastgpt/web/hooks/useRequest';
-import { useConfirm } from '@fastgpt/web/hooks/useConfirm';
+import { useRequest2 } from '@fastgpt/web/hooks/useRequest';
 import { getSourceNameIcon } from '@fastgpt/global/core/dataset/utils';
 import { DatasetDataIndexItemType } from '@fastgpt/global/core/dataset/type';
 import DeleteIcon from '@fastgpt/web/components/common/Icon/delete';
@@ -30,10 +29,12 @@ import MyBox from '@fastgpt/web/components/common/MyBox';
 import { getErrText } from '@fastgpt/global/common/error/utils';
 import { useSystemStore } from '@/web/common/system/useSystemStore';
 import QuestionTip from '@fastgpt/web/components/common/MyTooltip/QuestionTip';
-import { useSystem } from '@fastgpt/web/hooks/useSystem';
 import LightRowTabs from '@fastgpt/web/components/common/Tabs/LightRowTabs';
 import styles from './styles.module.scss';
-import { getDatasetIndexMapData } from '@fastgpt/global/core/dataset/data/constants';
+import {
+  DatasetDataIndexTypeEnum,
+  getDatasetIndexMapData
+} from '@fastgpt/global/core/dataset/data/constants';
 
 export type InputDataType = {
   q: string;
@@ -62,11 +63,10 @@ const InputDataModal = ({
   onSuccess: (data: InputDataType & { dataId: string }) => void;
 }) => {
   const { t } = useTranslation();
-  const theme = useTheme();
   const { toast } = useToast();
   const [currentTab, setCurrentTab] = useState(TabEnum.content);
   const { embeddingModelList, defaultModels } = useSystemStore();
-  const { isPc } = useSystem();
+
   const { register, handleSubmit, reset, control } = useForm<InputDataType>();
   const {
     fields: indexes,
@@ -112,11 +112,6 @@ const InputDataModal = ({
     }
   ];
 
-  const { ConfirmModal, openConfirm } = useConfirm({
-    content: t('common:dataset.data.Delete Tip'),
-    type: 'delete'
-  });
-
   const { data: collection = defaultCollectionDetail } = useQuery(
     ['loadCollectionId', collectionId],
     () => {
@@ -163,8 +158,8 @@ const InputDataModal = ({
   }, [collection.dataset.vectorModel, defaultModels.embedding, embeddingModelList]);
 
   // import new data
-  const { mutate: sureImportData, isLoading: isImporting } = useRequest({
-    mutationFn: async (e: InputDataType) => {
+  const { runAsync: sureImportData, loading: isImporting } = useRequest2(
+    async (e: InputDataType) => {
       if (!e.q) {
         setCurrentTab(TabEnum.content);
         return Promise.reject(t('common:dataset.data.input is empty'));
@@ -181,31 +176,29 @@ const InputDataModal = ({
         collectionId: collection._id,
         q: e.q,
         a: e.a,
-        // remove dataId
-        indexes:
-          e.indexes?.map((index) => ({
-            ...index,
-            dataId: undefined
-          })) || []
+        // Contains no default index
+        indexes: e.indexes
       });
 
       return {
         ...data,
         dataId
       };
     },
-    successToast: t('common:dataset.data.Input Success Tip'),
-    onSuccess(e) {
-      reset({
-        ...e,
-        q: '',
-        a: '',
-        indexes: []
-      });
-      onSuccess(e);
-    },
-    errorToast: t('common:common.error.unKnow')
-  });
+    {
+      successToast: t('common:dataset.data.Input Success Tip'),
+      onSuccess(e) {
+        reset({
+          ...e,
+          q: '',
+          a: '',
+          indexes: []
+        });
+        onSuccess(e);
+      },
+      errorToast: t('common:common.error.unKnow')
+    }
+  );
 
   // update
   const { runAsync: onUpdateData, loading: isUpdating } = useRequest2(
@@ -239,6 +232,7 @@ const InputDataModal = ({
     () => getSourceNameIcon({ sourceName: collection.sourceName, sourceId: collection.sourceId }),
     [collection]
   );
+
   return (
     <MyModal
       isOpen={true}
@@ -291,9 +285,8 @@ const InputDataModal = ({
               p={0}
               onClick={() =>
                 appendIndexes({
-                  type: 'custom',
-                  text: '',
-                  dataId: `${Date.now()}`
+                  type: DatasetDataIndexTypeEnum.custom,
+                  text: ''
                 })
               }
             >
@@ -331,7 +324,6 @@ const InputDataModal = ({
           </MyTooltip>
         </Flex>
       </MyBox>
-      <ConfirmModal />
     </MyModal>
   );
 };
diff --git a/projects/app/src/service/core/dataset/data/controller.ts b/projects/app/src/service/core/dataset/data/controller.ts
