KevinHuSh
|
f3477202fe
|
refine citation (#161)
|
1 anno fa |
KevinHuSh
|
fd7fcb5baf
|
apply pep8 formalize (#155)
|
1 anno fa |
KevinHuSh
|
da21320b88
|
fix plainPdf bugs (#152)
|
1 anno fa |
KevinHuSh
|
71fe314955
|
refine page ranges (#147)
|
1 anno fa |
KevinHuSh
|
f6aee7f230
|
add use layout or not option (#145)
* add use layout or not option
* trival
|
1 anno fa |
KevinHuSh
|
6999598101
|
refine for English corpus (#135)
|
1 anno fa |
KevinHuSh
|
602038ac49
|
fix task cancling bug (#98)
|
1 anno fa |
KevinHuSh
|
8a57f2afd5
|
change callback strategy, add timezone to docker (#96)
|
1 anno fa |
KevinHuSh
|
7bfaf0df29
|
fix position extraction bug (#93)
* fix position extraction bug
* remove delimiter for naive parser
|
1 anno fa |
KevinHuSh
|
685b4d8a95
|
fix table desc bugs, add positions to chunks (#91)
|
1 anno fa |
KevinHuSh
|
8a726fb04b
|
solve task execution issues (#90)
|
1 anno fa |
KevinHuSh
|
7fd1eca582
|
init README of deepdoc, add picture processer. (#71)
* init README of deepdoc, add picture processer.
* add resume parsing
|
1 anno fa |
KevinHuSh
|
cacd36c5e1
|
use onnx models, new deepdoc (#68)
|
1 anno fa |
KevinHuSh
|
a8294f2168
|
Refine resume parts and fix bugs in retrival using sql (#66)
|
1 anno fa |
KevinHuSh
|
c5ea37cd30
|
Add resume parser and fix bugs (#59)
* Update .gitignore
* Update .gitignore
* Add resume parser and fix bugs
|
1 anno fa |
KevinHuSh
|
407b2523b6
|
remove unused codes, seperate layout detection out as a new api. Add new rag methed 'table' (#55)
|
1 anno fa |
KevinHuSh
|
51482f3e2a
|
Some document API refined. (#53)
Add naive chunking method to RAG
|
1 anno fa |
KevinHuSh
|
e6acaf6738
|
Add Q&A and Book, fix task running bugs (#50)
|
1 anno fa |
KevinHuSh
|
6224edcd1b
|
Add task moduel, and pipline the task and every parser (#49)
|
1 anno fa |
KevinHuSh
|
96a1a44cb6
|
add paper & manual parser (#46)
|
1 anno fa |