myhloli 1279f2cd0f feat(model): add support for DocLayout-YOLO model преди 1 година
..
dict2md 644085760b fix(ocr_mkcontent): expand para_to_standard_format_v2 to handle list and index blocks преди 1 година
filter df14c61f6f update: Enhance the capability to detect garbled document issues преди 1 година
integrations b72d4ebd94 Feat/support rag (#510) преди 1 година
layout 03469909bb Feat/support footnote in figure (#532) преди 1 година
libs 1279f2cd0f feat(model): add support for DocLayout-YOLO model преди 1 година
model 1279f2cd0f feat(model): add support for DocLayout-YOLO model преди 1 година
para 8cc76c4921 refactor(para): improve paragraph splitting algorithm преди 1 година
pipe 1279f2cd0f feat(model): add support for DocLayout-YOLO model преди 1 година
post_proc 1b9d65b3d3 1、Trace类的key增加前置下划线 преди 1 година
pre_proc 1279f2cd0f feat(model): add support for DocLayout-YOLO model преди 1 година
resources 1279f2cd0f feat(model): add support for DocLayout-YOLO model преди 1 година
rw 40e0827e60 Feat/impl cli (#264) преди 1 година
spark c9af3457f5 delete useless files преди 1 година
tools 1279f2cd0f feat(model): add support for DocLayout-YOLO model преди 1 година
__init__.py d5dbed7325 目录重构 преди 1 година
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 преди 1 година
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 преди 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) преди 1 година
pdf_parse_union_core_v2.py 7e301b849b refactor(pdf): adjust span filling threshold in block construction преди 1 година
user_api.py 1279f2cd0f feat(model): add support for DocLayout-YOLO model преди 1 година