Commit graph

2 commits

Author SHA1 Message Date
EricXiao
7fae75d020 make advanced pdf loader optional
Signed-off-by: EricXiao <taoiaox@gmail.com>
2025-09-22 15:07:58 +08:00
EricXiao
6107cb47ca Implement Advanced PDF Loader with unstructured library support
- Added AdvancedPdfLoader class for enhanced PDF processing using the unstructured library.
- Integrated fallback mechanism to PyPdfLoader in case of unstructured library import failure or exceptions.
- Updated supported loaders to include AdvancedPdfLoader.
- Added unit tests for AdvancedPdfLoader to ensure functionality and error handling.
- Updated poetry.lock and pyproject.toml to include new dependencies and versions.

Signed-off-by: EricXiao <taoiaox@gmail.com>
2025-09-20 17:03:00 +08:00