Commit History
fix raptor bugs (#928)
75a07ce
KevinHuSh
commited on
Bug fix for volcengine (#909)
6db9c7b
add raptor (#899)
2436df2
KevinHuSh
commited on
Add support for VolcEngine - the current version supports SDK2 (#885)
dea956e
yungongzi
commited on
fixed: The choices may be empty. (#876)
2721f55
dashi6174
commited on
add locally deployed llm (#841)
71b2e07
KevinHuSh
commited on
fix english query bug (#840)
bf46bd5
KevinHuSh
commited on
fix zhipuAI stream issue (#825)
66d269d
KevinHuSh
commited on
fix stream chat for ollama (#816)
09e1055
KevinHuSh
commited on
add stream chat (#811)
028fe40
KevinHuSh
commited on
support gpt-4o (#773)
73099c4
KevinHuSh
commited on
truncate text to fitin embedding model (#692)
c87ddd7
KevinHuSh
commited on
add support for deepseek (#668)
4d5f1c9
KevinHuSh
commited on
optimize srv broker and executor logic (#630)
1d93b24
fix disable and enable llm setting in dialog (#616)
22390c0
KevinHuSh
commited on
refine docker layers (#606)
da67205
KevinHuSh
commited on
refactor code (#583)
2d09c38
KevinHuSh
commited on
Refactor (#537)
3069c36
KevinHuSh
commited on
fix ollama issuet push (#486)
ef15d2d
KevinHuSh
commited on
make sure the models will not be load twice (#422)
c9a1362
KevinHuSh
commited on
Add bce-embedding and fastembed (#383)
ba51460
KevinHuSh
commited on
feat: FastEmbed embedding support (#291)
a86164e
conversation API backend update (#360)
50de567
KevinHuSh
commited on
Support Xinference (#321)
6b3ce5a
KevinHuSh
commited on
Support Xinference (#320)
63df91a
KevinHuSh
commited on
refine log format (#312)
1daa4bd
KevinHuSh
commited on
resolve issure to call ZH?IPUAI (#277)
8bdf2db
KevinHuSh
commited on
remove presence_penalty for chatglm (#268)
4bf8e84
KevinHuSh
commited on
Support Ollama (#261)
8f9784a
KevinHuSh
commited on
fix docker compose issue (#238)
0cfb2df
KevinHuSh
commited on
refine error response, add set api-key MD (#178)
58d441f
KevinHuSh
commited on
refine readme (#170)
0c30cc9
KevinHuSh
commited on
add base url for OpenAI (#166)
e06e08c
KevinHuSh
commited on
let's load model from local (#163)
8ee4f9f
KevinHuSh
commited on
refine OpenAi Api (#159)
adb65d7
KevinHuSh
commited on
apply pep8 formalize (#155)
79ada0b
KevinHuSh
commited on
support snapshot download from local (#153)
8f39e7a
KevinHuSh
commited on
fix plainPdf bugs (#152)
328b4c9
KevinHuSh
commited on
Add 'One' chunk method (#137)
1ed30a6
KevinHuSh
commited on
add Moonshot, debug my_llm (#126)
c1bdfb8
KevinHuSh
commited on
add dockerfile for cuda envirement. Refine table search strategy, (#123)
9fe9fc4
KevinHuSh
commited on
add local llm implementation (#119)
1550520
KevinHuSh
commited on
deal with stop reason being length problem (#109)
cfd888e
KevinHuSh
commited on
change callback strategy, add timezone to docker (#96)
b83edb4
KevinHuSh
commited on
refine admin initialization (#75)
4c52eb9
KevinHuSh
commited on
init README of deepdoc, add picture processer. (#71)
41c7a59
KevinHuSh
commited on
Refine resume parts and fix bugs in retrival using sql (#66)
a8294f2
KevinHuSh
commited on
refactor retieval_test, add SQl retrieval methods (#61)
5e0a689
KevinHuSh
commited on
Test chat API and refine ppt chunker (#42)
e32ef75
KevinHuSh
commited on