15 Commits

Author SHA1 Message Date
KevinHuSh
bcb58b7e71
layout refine (#115) 2024-03-08 18:59:53 +08:00
KevinHuSh
8f86ab9f7f
refine pdf parser, add time zone to userinfo (#112) 2024-03-08 11:24:24 +08:00
KevinHuSh
602038ac49
fix task cancling bug (#98) 2024-03-05 16:33:47 +08:00
KevinHuSh
8a57f2afd5
change callback strategy, add timezone to docker (#96) 2024-03-05 12:08:41 +08:00
KevinHuSh
7bfaf0df29
fix position extraction bug (#93)
* fix position extraction bug

* remove delimiter for naive parser
2024-03-04 17:08:35 +08:00
KevinHuSh
685b4d8a95
fix table desc bugs, add positions to chunks (#91) 2024-03-04 14:42:26 +08:00
KevinHuSh
8a726fb04b
solve task execution issues (#90) 2024-03-01 19:48:01 +08:00
KevinHuSh
3d4315c42a
resolve the issue of naive parser (#87) 2024-02-29 18:53:02 +08:00
KevinHuSh
0429107e80
fix user login issue (#85) 2024-02-29 14:03:07 +08:00
KevinHuSh
7fd1eca582
init README of deepdoc, add picture processer. (#71)
* init README of deepdoc, add picture processer.

* add resume parsing
2024-02-23 18:28:12 +08:00
KevinHuSh
cacd36c5e1
use onnx models, new deepdoc (#68) 2024-02-21 16:32:38 +08:00
KevinHuSh
a8294f2168 Refine resume parts and fix bugs in retrival using sql (#66) 2024-02-19 19:22:17 +08:00
KevinHuSh
5e0a689c43 refactor retieval_test, add SQl retrieval methods (#61) 2024-02-08 17:01:01 +08:00
KevinHuSh
407b2523b6 remove unused codes, seperate layout detection out as a new api. Add new rag methed 'table' (#55) 2024-02-05 18:08:17 +08:00
KevinHuSh
51482f3e2a Some document API refined. (#53)
Add naive chunking method to RAG
2024-02-02 19:21:37 +08:00