Commit History
Rework logging (#3358)
22fe41e
make titles in markdown not be splited with following content (#2971)
fa11d40
Kevin Hu
commited on
Fix docx images (#2756)
edccacf
lidp
commited on
remove unused import (#2679)
3d5f9ea
yqkcn
commited on
Add get_txt function (#2639)
82adb1c
yqkcn
Kevin Hu
commited on
make excel parsing configurable (#2517)
58ecd6d
Kevin Hu
commited on
fix duplicated llm name betweeen different suppliers (#2477)
bf00d96
Kevin Hu
commited on
Format file format from Windows/dos to Unix (#1949)
aeb6dbc
fix mind map bug (#1934)
77dc93a
Kevin Hu
commited on
add sql to naive parser (#1908)
ef2a724
Kevin Hu
commited on
Fix a "TypeError: expected string or buffer bug" in docx files extracted using Knowledge Graph.#1859 (#1865)
df1b4ac
Kung Quang
commited on
add support for eml file parser (#1768)
6ed07a9
be better chunks before graphrag (#1811)
930d161
Kevin Hu
commited on
Add graphrag (#1793)
6054f54
Kevin Hu
commited on
Fix: Embedding err when docx contains unsupported images (#1720)
b37fedc
Fix docx parser line bug (#1715)
dda4c86
H
Kevin Hu
commited on
Support table for markdown file in general parser (#1278)
5bfd79c
Support displaying images in the chunks of docx files when using general parser (#1253)
4adcb3c
refine code to prevent exception (#1231)
0de1478
KevinHuSh
commited on
feat: support json file (#1217)
77b7e10
Add support for HTML file (#973)
858916d
fix #917 #915 (#946)
c61bcde
KevinHuSh
commited on
Split Excel file into different chunks (#847)
366c531
GYH
commited on
Support for code files parse (#789)
c46aa24
dashi6174
commited on
refine text decode (#657)
b5b25b4
KevinHuSh
commited on
refine code (#595)
cfd6ece
KevinHuSh
commited on
Update version info (#564)
54ec234
fix bug of table in docx (#510)
977d825
KevinHuSh
commited on
Add `.doc` file parser. (#497)
ee82924
enlarge docker memory usage (#501)
3cefaa0
KevinHuSh
commited on
remove doc from supported processing types (#488)
ae35e13
KevinHuSh
commited on
feat: support markdown files (#483)
7ccbb61
Shaun
commited on
add redis to accelerate access of minio (#482)
b9d91e7
KevinHuSh
commited on
Fit a lot of encodings for text file. (#458)
d54aa01
KevinHuSh
commited on
fix gb2312 encoding issue (#394)
7e1a9f0
KevinHuSh
commited on
Add more information on vm map count setting (#241)
1cc01e0
KevinHuSh
commited on
fix docker compose issue (#238)
0cfb2df
KevinHuSh
commited on
READEME refined (#156)
f1ccc7f
KevinHuSh
commited on
apply pep8 formalize (#155)
79ada0b
KevinHuSh
commited on
add use layout or not option (#145)
b085dec
KevinHuSh
commited on
Add 'One' chunk method (#137)
1ed30a6
KevinHuSh
commited on
refine for English corpus (#135)
08bab63
KevinHuSh
commited on
refine manul parser (#131)
7d85666
KevinHuSh
commited on
layout refine (#115)
c127ae4
KevinHuSh
commited on
refine pdf parser, add time zone to userinfo (#112)
e34cb81
KevinHuSh
commited on
fix task cancling bug (#98)
279ca43
KevinHuSh
commited on
change callback strategy, add timezone to docker (#96)
b83edb4
KevinHuSh
commited on
fix position extraction bug (#93)
4e03dc3
KevinHuSh
commited on
fix table desc bugs, add positions to chunks (#91)
64a0633
KevinHuSh
commited on