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

Edit chunk shall update instead of insert it (#3709)

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

Edit chunk shall update instead of insert it. Close #3679 

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
This commit is contained in:
Zhichang Yu
2024-11-28 13:00:38 +08:00
committed by GitHub
parent 9f57534843
commit bc701d7b4c
19 changed files with 51 additions and 46 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
rag/nlp/__init__.py
View File

@ -325,12 +325,12 @@ def remove_contents_table(sections, eng=False):
sections.pop(i)
if i >= len(sections):
break
prefix = get(i)[:3] if not eng else " ".join(get(i).split(" ")[:2])
prefix = get(i)[:3] if not eng else " ".join(get(i).split()[:2])
while not prefix:
sections.pop(i)
if i >= len(sections):
break
prefix = get(i)[:3] if not eng else " ".join(get(i).split(" ")[:2])
prefix = get(i)[:3] if not eng else " ".join(get(i).split()[:2])
sections.pop(i)
if i >= len(sections) or not prefix:
break
@ -389,7 +389,7 @@ def title_frequency(bull, sections):
def not_title(txt):
if re.match(r"第[零一二三四五六七八九十百0-9]+条", txt):
return False
if len(txt.split(" ")) > 12 or (txt.find(" ") < 0 and len(txt) >= 32):
if len(txt.split()) > 12 or (txt.find(" ") < 0 and len(txt) >= 32):
return True
return re.search(r"[,;，。；！!]", txt)