| .. |
|
__base
|
d1dbbc1e33
feat: backend model load balancing support (#4927)
|
%!s(int64=2) %!d(string=hai) anos |
|
anthropic
|
04ad46dd31
chore: skip unnecessary key checks prior to accessing a dictionary (#4497)
|
%!s(int64=2) %!d(string=hai) anos |
|
azure_openai
|
e57bdd4e58
chore:update gpt-3.5-turbo and gpt-4-turbo parameter for azure (#4596)
|
%!s(int64=2) %!d(string=hai) anos |
|
baichuan
|
f32b440c4a
chore: fix indention violations by applying E111 to E117 ruff rules (#4925)
|
%!s(int64=2) %!d(string=hai) anos |
|
bedrock
|
f32b440c4a
chore: fix indention violations by applying E111 to E117 ruff rules (#4925)
|
%!s(int64=2) %!d(string=hai) anos |
|
chatglm
|
228de1f12a
fix: miss usage of os.path.join for URL assembly and add tests on yarl (#4224)
|
%!s(int64=2) %!d(string=hai) anos |
|
cohere
|
2fdd64c1b5
feat: add proxy configuration for Cohere model (#4152)
|
%!s(int64=2) %!d(string=hai) anos |
|
deepseek
|
8ce93faf08
Typo on deepseek.yaml and yi.yaml (#4170)
|
%!s(int64=2) %!d(string=hai) anos |
|
google
|
5cdb95be1f
fix: gemini timeout error (#4955)
|
%!s(int64=2) %!d(string=hai) anos |
|
groq
|
a4e4fb4094
fix: credentials validate failed for groqcloud model provider (#3817)
|
%!s(int64=2) %!d(string=hai) anos |
|
huggingface_hub
|
063191889d
chore: apply ruff's pyupgrade linter rules to modernize Python code with targeted version (#2419)
|
%!s(int64=2) %!d(string=hai) anos |
|
jina
|
543a00e597
feat: update model_provider jina to support custom url and model (#4110)
|
%!s(int64=2) %!d(string=hai) anos |
|
leptonai
|
51a9e678f0
Leptonai integrate (#4079)
|
%!s(int64=2) %!d(string=hai) anos |
|
localai
|
2deb23e00e
fix: Show rerank in system for localai (#4652)
|
%!s(int64=2) %!d(string=hai) anos |
|
minimax
|
4086f5051c
feat:Provide parameter config for mask_sensitive_info of MiniMax mode… (#4294)
|
%!s(int64=2) %!d(string=hai) anos |
|
mistralai
|
de3b490f8e
Add mixtral 8x22b (#3606)
|
%!s(int64=2) %!d(string=hai) anos |
|
moonshot
|
a0c30702c1
feat: moonshot fc (#3629)
|
%!s(int64=2) %!d(string=hai) anos |
|
nvidia
|
a80fe20456
add-some-new-models-hosted-on-nvidia (#4303)
|
%!s(int64=2) %!d(string=hai) anos |
|
nvidia_nim
|
696c5308a9
chore: optimize nvidia nim credential schema and info (#4898)
|
%!s(int64=2) %!d(string=hai) anos |
|
ollama
|
e0da0744b5
add: ollama keep alive parameter added. issue #4024 (#4655)
|
%!s(int64=2) %!d(string=hai) anos |
|
openai
|
3929d289e0
feat: set default memory messages limit to infinite (#5002)
|
%!s(int64=2) %!d(string=hai) anos |
|
openai_api_compatible
|
aa6d2e3035
fix(openai_api_compatible): fixing the error when converting chunk to json (#3570)
|
%!s(int64=2) %!d(string=hai) anos |
|
openllm
|
04ad46dd31
chore: skip unnecessary key checks prior to accessing a dictionary (#4497)
|
%!s(int64=2) %!d(string=hai) anos |
|
openrouter
|
646858ea08
feat: Vision switch functionality is provided on OpenRouter (#3564)
|
%!s(int64=2) %!d(string=hai) anos |
|
replicate
|
cefe156811
feat: replicate supports default version. (#3884)
|
%!s(int64=2) %!d(string=hai) anos |
|
spark
|
13694293e3
fix: resolve header.uid' length must be less or equal than 32 on Spark V1.5 (#2983)
|
%!s(int64=2) %!d(string=hai) anos |
|
togetherai
|
0ec8b57825
add together ai model setting (#3895)
|
%!s(int64=2) %!d(string=hai) anos |
|
tongyi
|
5b447d61a6
feat: refactor tongyi models (#3496)
|
%!s(int64=2) %!d(string=hai) anos |
|
triton_inference_server
|
5b447d61a6
feat: refactor tongyi models (#3496)
|
%!s(int64=2) %!d(string=hai) anos |
|
vertex_ai
|
b98a1a3303
feat: added Anthropic Claude3 models to Google Cloud Vertex AI (#4870)
|
%!s(int64=2) %!d(string=hai) anos |
|
volcengine_maas
|
6e9066ebf4
feat: support doubao llm and embeding models (#4431)
|
%!s(int64=2) %!d(string=hai) anos |
|
wenxin
|
b189faca52
feat: update ernie model (#4756)
|
%!s(int64=2) %!d(string=hai) anos |
|
xinference
|
f361c7004d
feat: support vision models from xinference (#4094)
|
%!s(int64=2) %!d(string=hai) anos |
|
yi
|
ece0f08a2b
add yi models (#4335)
|
%!s(int64=2) %!d(string=hai) anos |
|
zhipuai
|
cbdb861ee4
add glm-3-turbo max_tokens parameter setting (#4017)
|
%!s(int64=2) %!d(string=hai) anos |
|
__init__.py
|
d069c668f8
Model Runtime (#1858)
|
%!s(int64=2) %!d(string=hai) anos |
|
_position.yaml
|
3c8a120e51
add-nvidia-mim (#4882)
|
%!s(int64=2) %!d(string=hai) anos |
|
model_provider_factory.py
|
d1dbbc1e33
feat: backend model load balancing support (#4927)
|
%!s(int64=2) %!d(string=hai) anos |
takatost
3929d289e0
feat: set default memory messages limit to infinite (#5002)