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

Feat: add more chunking method (#11413)

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

Feat: add more chunking method #11311

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
This commit is contained in:
Billy Bao
2025-11-20 19:07:17 +08:00
committed by GitHub
parent c8ab9079b3
commit d3d2ccc76c
6 changed files with 66 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
rag/app/manual.py
View File

@ -213,6 +213,7 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
lang = lang,
callback = callback,
pdf_cls = Pdf,
parse_method = "manual",
**kwargs
)
@ -225,7 +226,7 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
elif len(section) != 3:
raise ValueError(f"Unexpected section length: {len(section)} (value={section!r})")
txt, sec_id, poss = section
txt, layoutno, poss = section
if isinstance(poss, str):
poss = pdf_parser.extract_positions(poss)
first = poss[0] # tuple: ([pn], x1, x2, y1, y2)
@ -235,7 +236,7 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
pn = pn[0] # [pn] -> pn
poss[0] = (pn, *first[1:])
return (txt, sec_id, poss)
return (txt, layoutno, poss)
sections = [_normalize_section(sec) for sec in sections]