| .. |
|
__base
|
c7df6783df
Revert "feat: support pinning, including, and excluding for Model Providers and Tools" (#7324)
|
hai 1 ano |
|
anthropic
|
08f922d8c9
fix: anthropic max token NoneType error (#6858)
|
hai 1 ano |
|
azure_openai
|
a9cd6df97e
Remove tts (blocking call) (#6869)
|
hai 1 ano |
|
baichuan
|
adc948e87c
fix(api/core/model_runtime/model_providers/baichuan,localai): Parse ToolPromptMessage. #4943 (#5138)
|
hai 1 ano |
|
bedrock
|
f2cb1fb09f
Fix : Workflow "start" paste url not support s3 pre-signed URL (#6855)
|
hai 1 ano |
|
chatglm
|
228de1f12a
fix: miss usage of os.path.join for URL assembly and add tests on yarl (#4224)
|
hai 1 ano |
|
cohere
|
dcb72e0067
chore: apply flake8-comprehensions Ruff rules to improve collection comprehensions (#5652)
|
hai 1 ano |
|
deepseek
|
bd3ed89516
feat: add function calling for deepseek models (#6990)
|
hai 1 ano |
|
google
|
dcb72e0067
chore: apply flake8-comprehensions Ruff rules to improve collection comprehensions (#5652)
|
hai 1 ano |
|
groq
|
a34285196b
Revise the wrong pricing of certain LLM models. (#6967)
|
hai 1 ano |
|
huggingface_hub
|
063191889d
chore: apply ruff's pyupgrade linter rules to modernize Python code with targeted version (#2419)
|
hai 1 ano |
|
huggingface_tei
|
5b32f2e0dd
Feat: Add model provider Text Embedding Inference for embedding and rerank (#7132)
|
hai 1 ano |
|
hunyuan
|
d7bb422a5c
fix: hunyuan assistant_prompt_message pydantic error (#7062)
|
hai 1 ano |
|
jina
|
26991443ed
fix: Fix incorrect context size for jina-reranker-v2 model (#7006)
|
hai 1 ano |
|
leptonai
|
51a9e678f0
Leptonai integrate (#4079)
|
hai 1 ano |
|
localai
|
9a64aa76c1
fix: typo and check (#5287)
|
hai 1 ano |
|
minimax
|
4086f5051c
feat:Provide parameter config for mask_sensitive_info of MiniMax mode… (#4294)
|
hai 1 ano |
|
mistralai
|
de3b490f8e
Add mixtral 8x22b (#3606)
|
hai 1 ano |
|
moonshot
|
0bf4817474
fix: _convert_prompt_message_to_dict parameters err (#5716)
|
hai 1 ano |
|
novita
|
3d3677e912
Feat/model provider novita (#6717)
|
hai 1 ano |
|
nvidia
|
23ed15d19f
feat:nvidia add nemotron4-340b and microsoft/phi-3 (#6973)
|
hai 1 ano |
|
nvidia_nim
|
696c5308a9
chore: optimize nvidia nim credential schema and info (#4898)
|
hai 1 ano |
|
ollama
|
4cbeb6815b
Fix: Wrong cutoff length lead to empty input in openai compatible embedding model. (#7133)
|
hai 1 ano |
|
openai
|
6ff7fd80a1
feat: support OPENAI json_schema (#7258)
|
hai 1 ano |
|
openai_api_compatible
|
a12ddc47e7
feat: add support of speech2text function for OpenAI-API-compatible and Siliconflow (#7197)
|
hai 1 ano |
|
openllm
|
04ad46dd31
chore: skip unnecessary key checks prior to accessing a dictionary (#4497)
|
hai 1 ano |
|
openrouter
|
8166a8caf5
feat: update llama3.1 parameters for openrouter (#6901)
|
hai 1 ano |
|
perfxcloud
|
d1a6702aa4
Update PerfXCloud Model List (#7212)
|
hai 1 ano |
|
replicate
|
dcb72e0067
chore: apply flake8-comprehensions Ruff rules to improve collection comprehensions (#5652)
|
hai 1 ano |
|
sagemaker
|
4a026fa352
Enhancement: add model provider - Amazon Sagemaker (#6255)
|
hai 1 ano |
|
siliconflow
|
3a33062405
feat: support siliconflow rerank (#7337)
|
hai 1 ano |
|
spark
|
68ac433218
feat: add support Spark4.0 (#5688)
|
hai 1 ano |
|
stepfun
|
07511dfaf4
update stepfun model (#7118)
|
hai 1 ano |
|
tencent
|
7c55c39085
feat: add tencent asr (#6091)
|
hai 1 ano |
|
togetherai
|
ba5f8afaa8
Feat/firecrawl data source (#5232)
|
hai 1 ano |
|
tongyi
|
6fdbc7dbf3
fix error when use farui-plus model (#7316)
|
hai 1 ano |
|
triton_inference_server
|
ec181649ae
Update model provider configuration for Triton Inference Server and X… (#6274)
|
hai 1 ano |
|
upstage
|
d29b32fce2
fix: typo in upstage/llm/_position.yaml (#7286)
|
hai 1 ano |
|
vertex_ai
|
dcb72e0067
chore: apply flake8-comprehensions Ruff rules to improve collection comprehensions (#5652)
|
hai 1 ano |
|
volcengine_maas
|
85744b72e5
feat: support moonshot and glm base models for volcengine provider (#6029)
|
hai 1 ano |
|
wenxin
|
7944ce0594
feat: wenxin add yi-34b-chat (#7117)
|
hai 1 ano |
|
xinference
|
ea30174057
chore: optimize streaming tts of xinference (#6966)
|
hai 1 ano |
|
yi
|
ece0f08a2b
add yi models (#4335)
|
hai 1 ano |
|
zhinao
|
34a9dbe826
Feat/add 360-zhinao provider (#7069)
|
hai 1 ano |
|
zhipuai
|
83acb53c08
feat: add zhipu embedding-3 (#7100)
|
hai 1 ano |
|
__init__.py
|
d069c668f8
Model Runtime (#1858)
|
hai 1 ano |
|
_position.yaml
|
34a9dbe826
Feat/add 360-zhinao provider (#7069)
|
hai 1 ano |
|
model_provider_factory.py
|
c7df6783df
Revert "feat: support pinning, including, and excluding for Model Providers and Tools" (#7324)
|
hai 1 ano |
Weaxs
3a33062405
feat: support siliconflow rerank (#7337)