From 550e65bb2281ef9e514241a493153e2b992e282b Mon Sep 17 00:00:00 2001 From: yzz Date: Tue, 5 Aug 2025 17:48:18 +0800 Subject: [PATCH] Fix: PlainParser using fix in presentation (#9239) ### What problem does this PR solve? tiny fix about the using of `deepdoc.pdf_parser.PlainParser` in `rag.app.presentation.chunk`, I referred to other ways of using this class. So tiny the fix is, a issue seems unnecessary. ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue) --- rag/app/presentation.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/rag/app/presentation.py b/rag/app/presentation.py index d451deb8d..148e73c26 100644 --- a/rag/app/presentation.py +++ b/rag/app/presentation.py @@ -135,7 +135,8 @@ def chunk(filename, binary=None, from_page=0, to_page=100000, sections = pdf_parser(filename, binary, from_page=from_page, to_page=to_page, callback=callback) elif layout_recognizer == "Plain Text": pdf_parser = PlainParser() - sections, _ = pdf_parser(filename, binary, from_page=from_page, to_page=to_page, callback=callback) + sections, _ = pdf_parser(filename if not binary else binary, from_page=from_page, to_page=to_page, + callback=callback) else: vision_model = LLMBundle(kwargs["tenant_id"], LLMType.IMAGE2TEXT, llm_name=layout_recognizer, lang=lang) pdf_parser = VisionParser(vision_model=vision_model, **kwargs)