zlei6/ragflow
1
0
Fork 0
mirror of https://github.com/infiniflow/ragflow.git synced 2026-06-29 15:31:05 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix VLM PDF parser only parse first 12 pages, and default page range for PDF files align with backend (#16394)

Browse Source 
1. Fix VLM parser only parse first 12 pages
2. Fix frontend default pages 1 - 100000, keep aligned with backend.
This commit is contained in:
Wang Qi
2026-06-26 20:15:25 +08:00
committed by GitHub
parent a57a841a11
commit 3a829fb6dd
2 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
deepdoc/parser/pdf_parser.py
View File

@@ -2053,7 +2053,7 @@ class VisionParser(RAGFlowPdfParser):
all_docs = []
for idx, img_binary in enumerate(self.page_images or []):
pdf_page_num = idx # 0-based
pdf_page_num = from_page + idx # 0-based
if pdf_page_num < start_page or pdf_page_num >= end_page:
continue