AI/dify
1
0
Fork 0
mirror of https://git.mirrors.martin98.com/https://github.com/langgenius/dify.git synced 2025-08-11 13:49:03 +08:00
Code Issues Packages Projects Releases Wiki Activity

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

Browse Source
This commit is contained in:
Jyong 2024-09-02 19:37:05 +08:00 committed by GitHub
parent 35f13c7327
commit 6f33351eb3
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 3 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
api/core/rag/extractor/word_extractor.py
View File

@ -170,6 +170,8 @@ class WordExtractor(BaseExtractor):
if run.element.xpath('.//a:blip'): if run.element.xpath('.//a:blip'):
for blip in 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") 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 image_part = paragraph.part.rels[image_id].target_part
if image_part in image_map: if image_part in image_map:
@ -256,6 +258,6 @@ class WordExtractor(BaseExtractor):
content.append(parsed_paragraph) content.append(parsed_paragraph)
elif isinstance(element.tag, str) and element.tag.endswith('tbl'): # table elif isinstance(element.tag, str) and element.tag.endswith('tbl'): # table
table = tables.pop(0) table = tables.pop(0)
content.append(self._table_to_markdown(table,image_map)) content.append(self._table_to_markdown(table, image_map))
return '\n'.join(content) return '\n'.join(content)