Update rag/nlp/query.py (#7816)

### What problem does this PR solve?
Fix tokenizer resulting in low recall

![37743d3a49](https://github.com/user-attachments/assets/1394757e-8fcb-4f87-96af-a92716144884)

![4aba633a17](https://github.com/user-attachments/assets/a1828e32-3e17-4394-a633-ba3f09bd506d)

![image](https://github.com/user-attachments/assets/61308f32-2a4f-44d5-a034-d65bbec554ef)



### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Refactoring

---------

Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>

rag/nlp/query.py

@@ -71,7 +71,19 @@ class FulltextQueryer:
             txt = otxt
         return txt
 
+    @staticmethod
+    def add_space_between_eng_zh(txt):
+        # (ENG/ENG+NUM) + ZH
+        txt = re.sub(r'([A-Za-z]+[0-9]+)([\u4e00-\u9fa5]+)', r'\1 \2', txt)
+        # ENG + ZH
+        txt = re.sub(r'([A-Za-z])([\u4e00-\u9fa5]+)', r'\1 \2', txt)
+        # ZH + (ENG/ENG+NUM)
+        txt = re.sub(r'([\u4e00-\u9fa5]+)([A-Za-z]+[0-9]+)', r'\1 \2', txt)
+        txt = re.sub(r'([\u4e00-\u9fa5]+)([A-Za-z])', r'\1 \2', txt)
+        return txt
+
     def question(self, txt, tbl="qa", min_match: float = 0.6):
+        txt = FulltextQueryer.add_space_between_eng_zh(txt)
         txt = re.sub(
             r"[ :|\r\n\t,，。？?/`!！&^%%()\[\]{}<>]+",
             " ",