4.7-production (#1053)

* 4.7-alpha3 (#62)

* doc

* Optimize possible null Pointers and parts of Ux

* fix: mulity index training error

* feat: doc and rename question guide

* fix ios speech input (#59)

* fix: prompt editor variables nowrap (#61)

* change openapi import in http module with curl import (#60)

* chore(ui): dataset import modal ui (#58)

* chore(ui): dataset import modal ui

* use component

* fix height

* 4.7 (#63)

* fix: claude3 image type verification failed (#1038) (#1040)

* perf: curl import modal

* doc img

* perf: adapt cohere rerank

* perf: code

* perf: input style

* doc

---------

Co-authored-by: xiaotian <dimsky@163.com>

* fix: ts

* docker deploy

* perf: prompt call

* doc

* ts

* finish ui

* perf: outlink detail ux

* perf: user schema

* fix: plugin update

* feat: get current time plugin

* fix: ts

* perf: fetch anamation

* perf: mark ux

* doc

* perf: select app ux

* fix: split text custom string conflict

* peref: inform readed

* doc

* memo flow component

* perf: version

* faq

* feat: flow max runtimes

* feat: similarity tip

* feat: auto detect file encoding

* Supports asymmetric vector model

* fix: ts

* perf: max w

* move code

* perf: hide whisper

* fix: ts

* feat: system msg modal

* perf: catch error

* perf: inform tip

* fix: inform

---------

Co-authored-by: heheer <71265218+newfish-cmyk@users.noreply.github.com>
Co-authored-by: xiaotian <dimsky@163.com>

packages/global/common/string/textSplitter.ts

@@ -30,7 +30,10 @@ export const splitText2Chunks = (props: {
 
   // The larger maxLen is, the next sentence is less likely to trigger splitting
   const stepReges: { reg: RegExp; maxLen: number }[] = [
-    ...customReg.map((text) => ({ reg: new RegExp(`(${text})`, 'g'), maxLen: chunkLen * 1.4 })),
+    ...customReg.map((text) => ({
+      reg: new RegExp(`(${text.replace(/[.*+?^${}()|[\]\\]/g, '\\$&')})`, 'g'),
+      maxLen: chunkLen * 1.4
+    })),
     { reg: /^(#\s[^\n]+)\n/gm, maxLen: chunkLen * 1.2 },
     { reg: /^(##\s[^\n]+)\n/gm, maxLen: chunkLen * 1.2 },
     { reg: /^(###\s[^\n]+)\n/gm, maxLen: chunkLen * 1.2 },