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