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

4
rag/app/paper.py
View File

@ -99,11 +99,11 @@ class Pdf(PdfParser):
i += 1
txt = b["text"].lower().strip()
if re.match("(abstract|摘要)", txt):
if len(txt.split(" ")) > 32 or len(txt) > 64:
if len(txt.split()) > 32 or len(txt) > 64:
abstr = txt + self._line_tag(b, zoomin)
break
txt = self.boxes[i]["text"].lower().strip()
if len(txt.split(" ")) > 32 or len(txt) > 64:
if len(txt.split()) > 32 or len(txt) > 64:
abstr = txt + self._line_tag(self.boxes[i], zoomin)
i += 1
break

2
rag/app/picture.py
View File

@ -33,7 +33,7 @@ def chunk(filename, binary, tenant_id, lang, callback=None, **kwargs):
txt = "\n".join([t[0] for _, t in bxs if t[0]])
eng = lang.lower() == "english"
callback(0.4, "Finish OCR: (%s ...)" % txt[:12])
if (eng and len(txt.split(" ")) > 32) or len(txt) > 32:
if (eng and len(txt.split()) > 32) or len(txt) > 32:
tokenize(doc, txt, eng)
callback(0.8, "OCR results is too long to use CV LLM.")
return [doc]