From 667c5812d0369d0b4687d55b30a399381e4cbd66 Mon Sep 17 00:00:00 2001 From: Stephen Hu Date: Mon, 4 Aug 2025 13:35:58 +0800 Subject: [PATCH] Fix:Repeated images when parsing markdown files with images (#9196) ### What problem does this PR solve? https://github.com/infiniflow/ragflow/issues/9149 ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue) --- rag/nlp/__init__.py | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/rag/nlp/__init__.py b/rag/nlp/__init__.py index 605601824..5c9d42d34 100644 --- a/rag/nlp/__init__.py +++ b/rag/nlp/__init__.py @@ -634,6 +634,17 @@ def concat_img(img1, img2): return img2 if not img1 and not img2: return None + + if img1 is img2: + return img1 + + if isinstance(img1, Image.Image) and isinstance(img2, Image.Image): + pixel_data1 = img1.tobytes() + pixel_data2 = img2.tobytes() + if pixel_data1 == pixel_data2: + img2.close() + return img1 + width1, height1 = img1.size width2, height2 = img2.size @@ -643,7 +654,8 @@ def concat_img(img1, img2): new_image.paste(img1, (0, 0)) new_image.paste(img2, (0, height1)) - + img1.close() + img2.close() return new_image