myhloli fdcb49d327 refactor(para_split_v3): merge list and index block detection il y a 1 an
..
dict2md 1f1dd3538d feat(list&index block): detect and merge list and index blocks il y a 1 an
filter df14c61f6f update: Enhance the capability to detect garbled document issues il y a 1 an
integrations b72d4ebd94 Feat/support rag (#510) il y a 1 an
layout 03469909bb Feat/support footnote in figure (#532) il y a 1 an
libs 0a9a6d3e53 fix(magic_pdf): include List and Index block types in processing il y a 1 an
model 1f1dd3538d feat(list&index block): detect and merge list and index blocks il y a 1 an
para fdcb49d327 refactor(para_split_v3): merge list and index block detection il y a 1 an
pipe 23b621e05a feat(UNIPipe): change default drop_mode to NONE_WITH_REASON il y a 1 an
post_proc 1b9d65b3d3 1、Trace类的key增加前置下划线 il y a 1 an
pre_proc 1f1dd3538d feat(list&index block): detect and merge list and index blocks il y a 1 an
resources f2a3a49541 fix(pdf_extract_kit):change unimernet base -> small il y a 1 an
rw 40e0827e60 Feat/impl cli (#264) il y a 1 an
spark c9af3457f5 delete useless files il y a 1 an
tools b2790f6f45 refactor(drawing): simplify draw bbox functions and adjust debug config il y a 1 an
__init__.py d5dbed7325 目录重构 il y a 1 an
pdf_parse_by_ocr.py 1efebe421c refactor(pdf_parse_union): integrate LayoutLMv3 for block orderingReplace the heuristic-based block ordering algorithm with LayoutLMv3 model predictions toimprove the accuracy of block ordering on PDF pages. Additionally, refactor the span il y a 1 an
pdf_parse_by_txt.py 1efebe421c refactor(pdf_parse_union): integrate LayoutLMv3 for block orderingReplace the heuristic-based block ordering algorithm with LayoutLMv3 model predictions toimprove the accuracy of block ordering on PDF pages. Additionally, refactor the span il y a 1 an
pdf_parse_union_core.py 068fab7f81 fix(end_page_id):Fix the issue where end_page_id is corrected to len-1 when its input is 0. (#518) il y a 1 an
pdf_parse_union_core_v2.py 6f63e70e94 feat(pdf_parse_union_core_v2): reintegrate para_split_v3 and add page range support il y a 1 an
user_api.py 6062862c96 feat(pipeline): pass language parameter for parsing and markdown conversion il y a 1 an