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

Light GraphRAG (#4585)

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

#4543

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
This commit is contained in:
Kevin Hu
2025-01-22 19:43:14 +08:00
committed by GitHub
parent 1a367664f1
commit dd0ebbea35
55 changed files with 5461 additions and 4000 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
rag/app/naive.py
View File

@ -202,7 +202,7 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
is_english = lang.lower() == "english" # is_english(cks)
parser_config = kwargs.get(
"parser_config", {
"chunk_token_num": 128, "delimiter": "\n!?。；！？", "layout_recognize": True})
"chunk_token_num": 128, "delimiter": "\n!?。；！？", "layout_recognize": "DeepDOC"})
doc = {
"docnm_kwd": filename,
"title_tks": rag_tokenizer.tokenize(re.sub(r"\.[a-zA-Z]+$", "", filename))
@ -231,8 +231,11 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
return res
elif re.search(r"\.pdf$", filename, re.IGNORECASE):
pdf_parser = Pdf() if parser_config.get("layout_recognize", True) else PlainParser()
sections, tables = pdf_parser(filename if not binary else binary, from_page=from_page, to_page=to_page, callback=callback)
pdf_parser = Pdf()
if parser_config.get("layout_recognize", "DeepDOC") == "Plain Text":
pdf_parser = PlainParser()
sections, tables = pdf_parser(filename if not binary else binary, from_page=from_page, to_page=to_page,
callback=callback)
res = tokenize_table(tables, doc, is_english)
elif re.search(r"\.xlsx?$", filename, re.IGNORECASE):