ignore linked images when image id is none (#7890)

2025-12-11 11:56:53 +08:00 · 2024-09-02 19:37:05 +08:00
parent 35f13c7327
commit 6f33351eb3
1 changed files with 3 additions and 1 deletions
--- a/api/core/rag/extractor/word_extractor.py
+++ b/api/core/rag/extractor/word_extractor.py
@@ -170,6 +170,8 @@ class WordExtractor(BaseExtractor):
            if run.element.xpath('.//a:blip'):
                for blip in run.element.xpath('.//a:blip'):
                    image_id = blip.get("{http://schemas.openxmlformats.org/officeDocument/2006/relationships}embed")
+                    if not image_id:
+                        continue
                    image_part = paragraph.part.rels[image_id].target_part

                    if image_part in image_map: