myhloli fcf24242d1 chore: remove useless files há 1 ano atrás
..
dict2md 98313d4a25 Merge branch 'dev' into content-list-not-drop há 1 ano atrás
filter df14c61f6f update: Enhance the capability to detect garbled document issues há 1 ano atrás
integrations b72d4ebd94 Feat/support rag (#510) há 1 ano atrás
layout 03469909bb Feat/support footnote in figure (#532) há 1 ano atrás
libs 564c4ce1e3 refactor(magic_pdf): improve line sorting and block indexing há 1 ano atrás
model fcf24242d1 chore: remove useless files há 1 ano atrás
para 58a003177c fix: resolve inaccuracy of drawing layout box caused by paragraphs combination #384 (#574) há 1 ano atrás
pipe 23b621e05a feat(UNIPipe): change default drop_mode to NONE_WITH_REASON há 1 ano atrás
post_proc 1b9d65b3d3 1、Trace类的key增加前置下划线 há 1 ano atrás
pre_proc 34f8965007 refactor(draw_bbox): add line sorting visualization há 1 ano atrás
resources f2a3a49541 fix(pdf_extract_kit):change unimernet base -> small há 1 ano atrás
rw 40e0827e60 Feat/impl cli (#264) há 1 ano atrás
spark c9af3457f5 delete useless files há 1 ano atrás
tools b2790f6f45 refactor(drawing): simplify draw bbox functions and adjust debug config há 1 ano atrás
__init__.py d5dbed7325 目录重构 há 1 ano atrás
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 há 1 ano atrás
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 há 1 ano atrás
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) há 1 ano atrás
pdf_parse_union_core_v2.py 564c4ce1e3 refactor(magic_pdf): improve line sorting and block indexing há 1 ano atrás
user_api.py 6062862c96 feat(pipeline): pass language parameter for parsing and markdown conversion há 1 ano atrás