Yongteng Lei 5acc407240 Feat: MinerU supports VLM-Transfomers backend (#10809) ... ### What problem does this PR solve? MinerU supports VLM-Transfomers backend. Set `MINERU_BACKEND="pipeline"` to choose the backend. (Options: pipeline | vlm-transformers, default is pipeline) ### Type of change - [x] New Feature (non-breaking change which adds functionality) --------- Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>		2025-10-27 17:04:13 +08:00
..
resume	Fix: resolve regex library warnings (#7782)	2025-05-22 10:06:28 +08:00
__init__.py	Feat: advanced markdown parsing (#9607)	2025-08-21 09:36:18 +08:00
docling_parser.py	Feat: add Docling parser (#10759)	2025-10-23 19:44:25 +08:00
docx_parser.py	Refactor parser code (#9042)	2025-07-25 12:04:07 +08:00
excel_parser.py	Fix: Excel2HTML can't support XLS（Excel 97-2003） (#10660)	2025-10-21 09:52:59 +08:00
figure_parser.py	Fix:wrong param in manual chunk (#10710)	2025-10-21 20:10:54 +08:00
html_parser.py	Fix: set default chunk_token_num in html_parser (#10118)	2025-09-17 09:36:31 +08:00
json_parser.py	Feat: parsing supports jsonl or ldjson format (#9087)	2025-07-30 09:48:20 +08:00
markdown_parser.py	Feat: add support for multi-column PDF parsing (#10475)	2025-10-11 18:46:09 +08:00
mineru_parser.py	Feat: MinerU supports VLM-Transfomers backend (#10809)	2025-10-27 17:04:13 +08:00
pdf_parser.py	Don't release full image (#10654)	2025-10-23 23:02:27 +08:00
ppt_parser.py	fix "TypeError: '<' not supported between instances of 'Emu' and 'Non… (#9209)	2025-08-04 16:07:03 +08:00
tcadp_parser.py	Feat: add TCADP Parser (#10775)	2025-10-27 15:14:58 +08:00
txt_parser.py
utils.py