feat: improve PDF image extraction with caption-based labeling and fallback matching

Browse Source

- Enhance pdf_image_extractor with caption text extraction near images/tables
- Add figure/table type correction based on caption content
- Implement sequential numbering fallback for unmatched items
- Improve figure linking in pages with manifest ID matching and fallback strategies
- Remove docling dependency, add dev dependency group

...

This commit is contained in:

Rain&Bus

2026-06-09 14:07:21 +08:00

parent 32978b3fc5

commit 18f44ac244

4 changed files with 343 additions and 1593 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

uv.lock

Generated

+12 -1495

File diff suppressed because it is too large Load Diff