| .. |
|
__base
|
286cdc41ab
reasoning model unified think tag is <think></think> (#13392)
|
hai 1 ano |
|
anthropic
|
2681bafb76
fix: handle document fetching from URL in Anthropic LLM model, solving base64 decoding error (#11858)
|
hai 1 ano |
|
azure_ai_studio
|
413dfd5628
feat: add completion mode and context size options for LLM configuration (#13325)
|
hai 1 ano |
|
azure_openai
|
34b21b3065
feat: Add o3-mini and o3-mini-2025-01-31 model variants (#13129)
|
hai 1 ano |
|
baichuan
|
daccb10d8c
fix: volcengine_maas and baichuan message error (#11625)
|
hai 1 ano |
|
bedrock
|
1a2523fd15
feat: bedrock_endpoint_url (#12838)
|
hai 1 ano |
|
chatglm
|
40fb4d16ef
chore: refurbish Python code by applying refurb linter rules (#8296)
|
hai 1 ano |
|
cohere
|
b09c39c8dc
refactor: avoid to use extra space when finding model by name (#13043)
|
hai 1 ano |
|
deepseek
|
da2ee04fce
fix: correct linewrap think display in generic openai api (#13260)
|
hai 1 ano |
|
fireworks
|
56e15d09a9
feat: mypy for all type check (#10921)
|
hai 1 ano |
|
fishaudio
|
448a19bf54
fix: fish audio wrong validate credentials interface (#11019)
|
hai 1 ano |
|
gitee_ai
|
6df17a334c
fix: Update the API call address for the text_embedding model (#12342)
|
hai 1 ano |
|
google
|
37117c22d4
feat(model): support Gemini 2.0 Flash Lite Preview model (02-05) in Google's model provider (#13399)
|
hai 1 ano |
|
gpustack
|
2bb521b135
Support TTS and Speech2Text for Model Provider GPUStack (#12381)
|
hai 1 ano |
|
groq
|
c6ddf6d6cc
feat(model_providers): Add Groq DeepSeek-R1-Distill-Llama-70b (#13229)
|
hai 1 ano |
|
huggingface_hub
|
166221d784
chore(lint): fix quotes for f-string formatting by bumping ruff to 0.9.x (#12702)
|
hai 1 ano |
|
huggingface_tei
|
6a0ff3686c
fix: fix typo (#12034)
|
hai 1 ano |
|
hunyuan
|
baeddd4d15
feat:Add support for stop parameter in hunyuan model #12313 (#12315)
|
hai 1 ano |
|
jina
|
56e15d09a9
feat: mypy for all type check (#10921)
|
hai 1 ano |
|
leptonai
|
2cf1187b32
chore(api/core): apply ruff reformatting (#7624)
|
hai 1 ano |
|
localai
|
1e829ceaf3
chore: format get_customizable_model_schema return value (#9335)
|
hai 1 ano |
|
minimax
|
925d69a2ee
feat:Support Minimax-Text-01 (#12763)
|
hai 1 ano |
|
mistralai
|
42d986b96d
[Pixtral] Add new model ; add vision (#11231)
|
hai 1 ano |
|
mixedbread
|
b90ad587c2
refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423)
|
hai 1 ano |
|
moonshot
|
6ea77ab4cd
fix: DeepSeek API Error with response format active (text and json_object) (#12747)
|
hai 1 ano |
|
nomic
|
56e15d09a9
feat: mypy for all type check (#10921)
|
hai 1 ano |
|
novita
|
560c5de1b7
Fixed Novita AI color and added DeepSeek R1 model (#13074)
|
hai 1 ano |
|
nvidia
|
6d66d6da15
feat(model_providers): Support deepseek-r1 for Nvidia Catalog (#13269)
|
hai 1 ano |
|
nvidia_nim
|
2cf1187b32
chore(api/core): apply ruff reformatting (#7624)
|
hai 1 ano |
|
oci
|
40dd63ecef
Upgrade oracle models (#13174)
|
hai 1 ano |
|
ollama
|
286cdc41ab
reasoning model unified think tag is <think></think> (#13392)
|
hai 1 ano |
|
openai
|
7203991032
feat: add parameter "reasoning_effort" and Openai o3-mini (#13243)
|
hai 1 ano |
|
openai_api_compatible
|
286cdc41ab
reasoning model unified think tag is <think></think> (#13392)
|
hai 1 ano |
|
openllm
|
56e15d09a9
feat: mypy for all type check (#10921)
|
hai 1 ano |
|
openrouter
|
6e5c915f96
feat(model): add deepseek-r1 for openrouter (#13312)
|
hai 1 ano |
|
perfxcloud
|
d44882c1b5
refactor: reduce duplciate code by inheritance (#13073)
|
hai 1 ano |
|
replicate
|
56e15d09a9
feat: mypy for all type check (#10921)
|
hai 1 ano |
|
sagemaker
|
147d578922
[Fix] revert sagemaker llm to support model hub (#12378)
|
hai 1 ano |
|
siliconflow
|
8f9db61688
feat: added new silicon flow models (#13369)
|
hai 1 ano |
|
spark
|
9d86147d20
fix: SparkLite API Auth error (#12781) (#12790)
|
hai 1 ano |
|
stepfun
|
3c2e30f348
fix: #12143 support streaming mode content start with "data:" (#12171)
|
hai 1 ano |
|
tencent
|
40fb4d16ef
chore: refurbish Python code by applying refurb linter rules (#8296)
|
hai 1 ano |
|
togetherai
|
56e15d09a9
feat: mypy for all type check (#10921)
|
hai 1 ano |
|
tongyi
|
38c31e64db
add enable_search parameter to qwen_max, plus, turbo (#13335)
|
hai 1 ano |
|
triton_inference_server
|
166221d784
chore(lint): fix quotes for f-string formatting by bumping ruff to 0.9.x (#12702)
|
hai 1 ano |
|
upstage
|
56e15d09a9
feat: mypy for all type check (#10921)
|
hai 1 ano |
|
vertex_ai
|
811d72a727
feat: added a _position.yaml for vertex ai provider (#13367)
|
hai 1 ano |
|
vessl_ai
|
56e15d09a9
feat: mypy for all type check (#10921)
|
hai 1 ano |
|
volcengine_maas
|
16865d43a8
feat: add deepseek models for volcengine provider (#13283)
|
hai 1 ano |
|
voyage
|
8aae235a71
fix: int None will cause error for context size (#11055)
|
hai 1 ano |
|
wenxin
|
166221d784
chore(lint): fix quotes for f-string formatting by bumping ruff to 0.9.x (#12702)
|
hai 1 ano |
|
x
|
cf0ff88120
feat: add grok-2-1212 and grok-2-vision-1212 (#11672)
|
hai 1 ano |
|
xinference
|
286cdc41ab
reasoning model unified think tag is <think></think> (#13392)
|
hai 1 ano |
|
yi
|
56e15d09a9
feat: mypy for all type check (#10921)
|
hai 1 ano |
|
zhinao
|
2cf1187b32
chore(api/core): apply ruff reformatting (#7624)
|
hai 1 ano |
|
zhipuai
|
da67916843
feat: add glm-4-air-0111 (#12997)
|
hai 1 ano |
|
__init__.py
|
d069c668f8
Model Runtime (#1858)
|
%!s(int64=2) %!d(string=hai) anos |
|
_position.yaml
|
59ca44f493
chore(model_runtime): Move deepseek ahead in the providers list. (#13197)
|
hai 1 ano |
|
model_provider_factory.py
|
4e7b6aec3a
feat: support pinning, including, and excluding for model providers and tools (#7419)
|
hai 1 ano |
Riddhimaan-Senapati
811d72a727
feat: added a _position.yaml for vertex ai provider (#13367)