pengjunjie/ragflow
1
0
Fork 1
mirror of https://github.com/infiniflow/ragflow.git synced 2025-12-08 20:42:30 +08:00
Code Issues Packages Projects Releases Wiki Activity

Refine search query. (#5235)

Browse Source 
### What problem does this PR solve?

#5173
#5214

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
This commit is contained in:
Kevin Hu
2025-02-21 18:32:32 +08:00
committed by GitHub
parent 0151d42156
commit 3444cb15e3
2 changed files with 85 additions and 87 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
rag/nlp/__init__.py
View File

@ -17,7 +17,6 @@
import logging
import random
from collections import Counter
from typing import Optional
from rag.utils import num_tokens_from_string
from . import rag_tokenizer
@ -604,9 +603,6 @@ def naive_merge_docx(sections, chunk_token_num=128, delimiter="\n。；！？"):
return cks, images
def extract_between(text: str, start_tag: str, end_tag: str) -> Optional[str]:
def extract_between(text: str, start_tag: str, end_tag: str) -> list[str]:
pattern = re.escape(start_tag) + r"(.*?)" + re.escape(end_tag)
matches = re.findall(pattern, text, flags=re.DOTALL)
if matches:
return matches[-1].strip()
return None
return re.findall(pattern, text, flags=re.DOTALL)