Light GraphRAG (#4585)

### 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

View File

@ -144,7 +144,7 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
The abstract of the paper will be sliced as an entire chunk, and will not be sliced partly.
"""
if re.search(r"\.pdf$", filename, re.IGNORECASE):
if not kwargs.get("parser_config", {}).get("layout_recognize", True):
if kwargs.get("parser_config", {}).get("layout_recognize", "DeepDOC") == "Plain Text":
pdf_parser = PlainParser()
paper = {
"title": filename,