Browse Source

enable 3 char words to finegrind tokenize (#2210)

### What problem does this PR solve?


### Type of change


- [x] Performance Improvement
tags/v0.11.0
Kevin Hu 1 year ago
parent
commit
6d232f1bdb
No account linked to committer's email address
1 changed files with 1 additions and 1 deletions
  1. 1
    1
      rag/nlp/query.py

+ 1
- 1
rag/nlp/query.py View File

@@ -83,7 +83,7 @@ class EsQueryer:
), tks

def need_fine_grained_tokenize(tk):
if len(tk) < 4:
if len(tk) < 3:
return False
if re.match(r"[0-9a-z\.\+#_\*-]+$", tk):
return False

Loading…
Cancel
Save