gmakstutis/ragflow
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Fix: missing parameters in by_plaintext method for PDF naive mode

Browse source
This commit is contained in:
lih 2025-11-20 14:30:45 +08:00
parent 3fe71ab7dd
commit ae22d053c7
1 changed files with 7 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

8
rag/app/naive.py
View file

@ -111,7 +111,13 @@ def by_tcadp(filename, binary=None, from_page=0, to_page=100000, lang="Chinese",
def by_plaintext(filename, binary=None, from_page=0, to_page=100000, callback=None, **kwargs): def by_plaintext(filename, binary=None, from_page=0, to_page=100000, callback=None, **kwargs):
if kwargs.get("layout_recognizer", "") == "Plain Text": parser_config = kwargs.get("parser_config", {})
layout_recognizer = parser_config.get("layout_recognize", "DeepDOC")
if isinstance(layout_recognizer, bool):
layout_recognizer = "DeepDOC" if layout_recognizer else "Plain Text"
if layout_recognizer == "Plain Text":
pdf_parser = PlainParser() pdf_parser = PlainParser()
else: else:
vision_model = LLMBundle(kwargs["tenant_id"], LLMType.IMAGE2TEXT, llm_name=kwargs.get("layout_recognizer", ""), lang=kwargs.get("lang", "Chinese")) vision_model = LLMBundle(kwargs["tenant_id"], LLMType.IMAGE2TEXT, llm_name=kwargs.get("layout_recognizer", ""), lang=kwargs.get("lang", "Chinese"))