mirror of
https://github.com/infiniflow/ragflow.git
synced 2026-06-29 23:41:12 +08:00
Fix: Correct PDF chunking parameter name in naive (#13357)
### What problem does this PR solve? Fix: Correct PDF chunking parameter name in naive #13325 ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue)
This commit is contained in:
@@ -252,7 +252,7 @@ PARSERS = {
|
||||
"deepdoc": by_deepdoc,
|
||||
"mineru": by_mineru,
|
||||
"docling": by_docling,
|
||||
"tcadp": by_tcadp,
|
||||
"tcadp parser": by_tcadp,
|
||||
"paddleocr": by_paddleocr,
|
||||
"plaintext": by_plaintext, # default
|
||||
}
|
||||
@@ -854,7 +854,7 @@ def chunk(filename, binary=None, from_page=0, to_page=100000, lang="Chinese", ca
|
||||
urls = extract_links_from_pdf(binary)
|
||||
|
||||
if isinstance(layout_recognizer, bool):
|
||||
layout_recognizer = "DeepDOC" if layout_recognizer else "Plain Text"
|
||||
layout_recognizer = "DeepDOC" if layout_recognizer else "PlainText"
|
||||
|
||||
name = layout_recognizer.strip().lower()
|
||||
parser = PARSERS.get(name, by_plaintext)
|
||||
|
||||
Reference in New Issue
Block a user