Skip to content

Commit e6a4fdf

Browse files
committed
feat(pptx): implement comprehensive PPTX parser with advanced extraction capabilities
- Introduced a complete solution for parsing PPTX files, extracting text, shapes, images, slides, and metadata. - Enhanced text extraction with formatting preservation and shape analysis. - Added support for image extraction with optional OCR processing. - Implemented slide-to-image conversion and comprehensive metadata extraction. - Improved file validation and error handling for robust parsing.
1 parent d99ed3a commit e6a4fdf

File tree

1 file changed

+868
-143
lines changed
  • packages/ragbits-document-search/src/ragbits/document_search/ingestion/parsers

1 file changed

+868
-143
lines changed

0 commit comments

Comments
 (0)