docling/docling
Maksym Lysak 82126e3871 Fixed issues with duplicated paragraphs and incorrect lists in pptx
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
2024-10-23 15:00:47 +02:00
..
backend Fixed issues with duplicated paragraphs and incorrect lists in pptx 2024-10-23 15:00:47 +02:00
cli feat!: Docling v2 (#117) 2024-10-16 21:02:03 +02:00
datamodel Update all backends with proper filename in DocumentOrigin 2024-10-22 14:11:40 +02:00
models feat: add coverage_threshold to skip OCR for small images (#161) 2024-10-18 16:51:39 +02:00
pipeline Ensure all models work only on valid pages (#158) 2024-10-18 16:51:39 +02:00
utils feat!: Docling v2 (#117) 2024-10-16 21:02:03 +02:00
__init__.py Initial commit 2024-07-15 09:42:42 +02:00
document_converter.py Merge ASCIIDoc and Markdown backends in, fixes 2024-10-22 11:34:35 +02:00