Commit Graph

179 Commits

Author SHA1 Message Date
9a843667b3 fix github account login issue (#132) 2024-03-19 15:31:47 +08:00
9da671b951 refine manul parser (#131) 2024-03-19 12:26:04 +08:00
de09b0e1a4 resolve table issues (#125) 2024-03-15 14:59:28 +08:00
675a9f8d9a add dockerfile for cuda envirement. Refine table search strategy, (#123) 2024-03-14 19:45:29 +08:00
0feb085c88 refine table parser (#120) 2024-03-12 18:56:04 +08:00
f1f09df901 add local llm implementation (#119) 2024-03-12 11:57:08 +08:00
bcb58b7e71 layout refine (#115) 2024-03-08 18:59:53 +08:00
8f86ab9f7f refine pdf parser, add time zone to userinfo (#112) 2024-03-08 11:24:24 +08:00
436c52bbc5 refine presentation parser (#110) 2024-03-07 17:21:38 +08:00
2d7c9080f4 deal with stop reason being length problem (#109) 2024-03-07 16:12:01 +08:00
d7c362f237 adjust hierarchical_merge strategy (#100) 2024-03-06 09:09:16 +08:00
602038ac49 fix task cancling bug (#98) 2024-03-05 16:33:47 +08:00
8a57f2afd5 change callback strategy, add timezone to docker (#96) 2024-03-05 12:08:41 +08:00
7bfaf0df29 fix position extraction bug (#93)
* fix position extraction bug

* remove delimiter for naive parser
2024-03-04 17:08:35 +08:00
685b4d8a95 fix table desc bugs, add positions to chunks (#91) 2024-03-04 14:42:26 +08:00
8a726fb04b solve task execution issues (#90) 2024-03-01 19:48:01 +08:00
3d4315c42a resolve the issue of naive parser (#87) 2024-02-29 18:53:02 +08:00
0429107e80 fix user login issue (#85) 2024-02-29 14:03:07 +08:00
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
cacd36c5e1 use onnx models, new deepdoc (#68) 2024-02-21 16:32:38 +08:00
a8294f2168 Refine resume parts and fix bugs in retrival using sql (#66) 2024-02-19 19:22:17 +08:00
5e0a689c43 refactor retieval_test, add SQl retrieval methods (#61) 2024-02-08 17:01:01 +08:00
c5ea37cd30 Add resume parser and fix bugs (#59)
* Update .gitignore

* Update .gitignore

* Add resume parser and fix bugs
2024-02-07 19:27:23 +08:00
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
51482f3e2a Some document API refined. (#53)
Add naive chunking method to RAG
2024-02-02 19:21:37 +08:00
e6acaf6738 Add Q&A and Book, fix task running bugs (#50) 2024-02-01 18:53:56 +08:00
6224edcd1b Add task moduel, and pipline the task and every parser (#49) 2024-01-31 19:57:45 +08:00
96a1a44cb6 add paper & manual parser (#46) 2024-01-30 18:28:09 +08:00
072f9dd5bc Add app to rag module: presentaion & laws (#43) 2024-01-25 18:57:39 +08:00