Add more Acronyms on SentenceSplitter (#2022)

Co-authored-by: Marcus Schiesser <marcus.schiesser@googlemail.com>

.changeset/stupid-boats-leave.md

@@ -0,0 +1,5 @@
+---
+"@llamaindex/core": patch
+---
+
+Add more Acronyms on SentenceSplitter

packages/core/src/node-parser/utils.ts

@@ -39,11 +39,45 @@ let sentenceTokenizer: SentenceTokenizer | null = null;
 export const splitBySentenceTokenizer = (): TextSplitterFn => {
   if (!sentenceTokenizer) {
     sentenceTokenizer = new SentenceTokenizer([
+      // TODO: This should be improved. Take a look at: https://github.com/run-llama/LlamaIndexTS/issues/2019
+      // English
       "i.e.",
       "etc.",
       "vs.",
       "Inc.",
       "A.S.A.P.",
+      "Mr.",
+      "Mrs.",
+      "Ms.",
+      "Dr.",
+      "Prof.",
+      "Sr.",
+      "Jr.",
+      // Spanish
+      "Sr.",
+      "Sres.",
+      "Srs.",
+      "Sra.",
+      "Sras.",
+      "Srta.",
+      "Srtas.",
+      "Dr.",
+      "Drs.",
+      "Dra.",
+      "Dras.",
+      "Prof.",
+      "Profs.",
+      "Profa.",
+      "Profas.",
+      "Ing.",
+      "Lic.",
+      "Arq.",
+      "Ab.",
+      "Abs.",
+      "Tel.",
+      "a.m.",
+      "p.m.",
+      "Art.",
     ]);
   }
   const tokenizer = sentenceTokenizer;