yyy d714ac8b76 Release: Release 0.7.1 verison, update dev (#527) 1 anno fa
..
dict2md d714ac8b76 Release: Release 0.7.1 verison, update dev (#527) 1 anno fa
filter df14c61f6f update: Enhance the capability to detect garbled document issues 1 anno fa
integrations b72d4ebd94 Feat/support rag (#510) 1 anno fa
layout d5dbed7325 目录重构 1 anno fa
libs d714ac8b76 Release: Release 0.7.1 verison, update dev (#527) 1 anno fa
model d714ac8b76 Release: Release 0.7.1 verison, update dev (#527) 1 anno fa
para 65c3ac66ae <fix>(para_split_v2): index out of range issue of span_text first char (#396) 1 anno fa
pipe 0f91fcf61f feat(cli&analyze&pipeline): add start_page and end_page args for pagination (#507) 1 anno fa
post_proc 1b9d65b3d3 1、Trace类的key增加前置下划线 1 anno fa
pre_proc 9067cd31ca fix(detect_all_bboxes): remove small overlapping blocks by merging (#501) 1 anno fa
resources d714ac8b76 Release: Release 0.7.1 verison, update dev (#527) 1 anno fa
rw 40e0827e60 Feat/impl cli (#264) 1 anno fa
spark c9af3457f5 delete useless files 1 anno fa
tools b72d4ebd94 Feat/support rag (#510) 1 anno fa
__init__.py d5dbed7325 目录重构 1 anno fa
pdf_parse_by_ocr.py 959b8d82d8 renamed pipeline file name 1 anno fa
pdf_parse_by_txt.py 959b8d82d8 renamed pipeline file name 1 anno fa
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) 1 anno fa
user_api.py 0f91fcf61f feat(cli&analyze&pipeline): add start_page and end_page args for pagination (#507) 1 anno fa