myhloli f2a3a49541 fix(pdf_extract_kit):change unimernet base -> small пре 1 година
..
dict2md 98313d4a25 Merge branch 'dev' into content-list-not-drop пре 1 година
filter df14c61f6f update: Enhance the capability to detect garbled document issues пре 1 година
integrations b72d4ebd94 Feat/support rag (#510) пре 1 година
layout 03469909bb Feat/support footnote in figure (#532) пре 1 година
libs 37fbe998ac feat(ocr_mkcontent): support drop reason in none_with_reason modeEnable the `NONE_WITH_REASON` drop mode in `para_to_standard_format_v2` by updating the пре 1 година
model f2a3a49541 fix(pdf_extract_kit):change unimernet base -> small пре 1 година
para 58a003177c fix: resolve inaccuracy of drawing layout box caused by paragraphs combination #384 (#574) пре 1 година
pipe 23b621e05a feat(UNIPipe): change default drop_mode to NONE_WITH_REASON пре 1 година
post_proc 1b9d65b3d3 1、Trace类的key增加前置下划线 пре 1 година
pre_proc 03469909bb Feat/support footnote in figure (#532) пре 1 година
resources f2a3a49541 fix(pdf_extract_kit):change unimernet base -> small пре 1 година
rw 40e0827e60 Feat/impl cli (#264) пре 1 година
spark c9af3457f5 delete useless files пре 1 година
tools a4c72e2e33 fix: solve conflicts пре 1 година
__init__.py d5dbed7325 目录重构 пре 1 година
pdf_parse_by_ocr.py 959b8d82d8 renamed pipeline file name пре 1 година
pdf_parse_by_txt.py 959b8d82d8 renamed pipeline file name пре 1 година
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) пре 1 година
user_api.py 6062862c96 feat(pipeline): pass language parameter for parsing and markdown conversion пре 1 година