V4.8.18 feature (#3565)

* feat: org CRUD (#3380)

* feat: add org schema

* feat: org manage UI

* feat: OrgInfoModal

* feat: org tree view

* feat: org management

* fix: init root org

* feat: org permission for app

* feat: org support for dataset

* fix: disable org role control

* styles: opt type signatures

* fix: remove unused permission

* feat: delete org collaborator

* perf: Team org ui (#3499)

* perf: org ui

* perf: org ui

* feat: org auth for app & dataset (#3498)

* feat: auth org resource permission

* feat: org auth support for app & dataset

* perf: org permission check (#3500)

* i18n (#3501)

* name

* i18n

* feat: support dataset changeOwner (#3483)

* feat: support dataset changeOwner

* chore: update dataset change owner api

* feat: permission manage UI for org (#3503)

* perf: password check;perf: image upload check;perf: sso login check (#3509)

* perf: password check

* perf: image upload check

* perf: sso login check

* force show update notification modal & fix login page text (#3512)

* fix login page English text

* update notification modal

* perf: notify account (#3515)

* perf(plugin): improve searXNG empty result handling and documentation (#3507)

* perf(plugin): improve searXNG empty result handling and documentation

* 修改了文档和代码部分无搜索的结果的反馈

* refactor: org pathId (#3516)

* optimize payment process (#3517)

* feat: support wecom sso (#3518)

* feat: support wecom sso

* chore: remove unused wecom js-sdk dependency

* fix qrcode script (#3520)

* fix qrcode script

* i18n

* perf: full text collection and search code;perf: rename function (#3519)

* perf: full text collection and search code

* perf: rename function

* perf: notify modal

* remove invalid code

* perf: sso login

* perf: pay process

* 4.8.18 test (#3524)

* perf: remove local token

* perf: index

* perf: file encoding;perf: leave team code;@c121914yu perf: full text search code (#3528)

* perf: text encoding

* perf: leave team code

* perf: full text search code

* fix: http status

* perf: embedding search and vector avatar

* perf: async read file (#3531)

* refactor: team permission  manager (#3535)

* perf: classify org, group and member

* refactor: team per manager

* fix: missing functions

* 4.8.18 test (#3543)

* perf: login check

* doc

* perf: llm model config

* perf: team clb config

* fix: MemberModal UI (#3553)

* fix: adapt MemberModal title and icon

* fix: adapt member modal

* fix: search input placeholder

* fix: add button text

* perf: org permission (#3556)

* docs:用户答疑的官方文档补充 (#3540)

* docs:用户答疑的官方文档补充

* 问题回答的内容修补

* share link random avatar (#3541)

* share link random avatar

* fix

* delete unused code

* share page avatar (#3558)

* feat: init 4818

* share page avatar

* feat: tmp upgrade code (#3559)

* feat: tmp upgrade code

* fulltext search test

* update action

* full text tmp code (#3561)

* full text tmp code

* fix: init

* fix: init

* remove tmp code

* remove tmp code

* 4818-alpha

* 4.8.18 test (#3562)

* full text tmp code

* fix: init

* upgrade code

* account log

* account log

* perf: dockerfile

* upgrade code

* chore: update docs app template submission (#3564)

---------

Co-authored-by: a.e. <49438478+I-Info@users.noreply.github.com>
Co-authored-by: Finley Ge <32237950+FinleyGe@users.noreply.github.com>
Co-authored-by: heheer <heheer@sealos.io>
Co-authored-by: Jiangween <145003935+Jiangween@users.noreply.github.com>

packages/service/worker/htmlStr2Md/utils.ts

@@ -1,9 +1,27 @@
 import TurndownService from 'turndown';
 import { ImageType } from '../readFile/type';
 import { matchMdImgTextAndUpload } from '@fastgpt/global/common/string/markdown';
+import { getNanoid } from '@fastgpt/global/common/string/tools';
 // @ts-ignore
 const turndownPluginGfm = require('joplin-turndown-plugin-gfm');
 
+const processBase64Images = (htmlContent: string) => {
+  const base64Regex = /src="data:([^;]+);base64,([^"]+)"/g;
+  const images: ImageType[] = [];
+
+  const processedHtml = htmlContent.replace(base64Regex, (match, mime, base64Data) => {
+    const uuid = `IMAGE_${getNanoid(12)}_IMAGE`;
+    images.push({
+      uuid,
+      base64: base64Data,
+      mime
+    });
+    return `src="${uuid}"`;
+  });
+
+  return { processedHtml, images };
+};
+
 export const html2md = (
   html: string
 ): {
@@ -25,11 +43,14 @@ export const html2md = (
     turndownService.remove(['i', 'script', 'iframe', 'style']);
     turndownService.use(turndownPluginGfm.gfm);
 
-    const { text, imageList } = matchMdImgTextAndUpload(html);
+    // 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);
 
     return {
-      rawText: turndownService.turndown(text),
-      imageList
+      rawText: text,
+      imageList: [...images, ...imageList]
     };
   } catch (error) {
     console.log('html 2 markdown error', error);