You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
gcgj-dify-1.7.0/api/core/model_runtime/model_providers
takatost 415022aa14
fix: pydantic2 error (#5172)
2 years ago
..
__base fix: JSON mode with an image doesn't work for Gemini (#5169) 2 years ago
anthropic chore: skip unnecessary key checks prior to accessing a dictionary (#4497) 2 years ago
azure_openai chore:add some new api version for azure openai (#5142) 2 years ago
baichuan fix(api/core/model_runtime/model_providers/baichuan,localai): Parse ToolPromptMessage. #4943 (#5138) 2 years ago
bedrock chore: fix indention violations by applying E111 to E117 ruff rules (#4925) 2 years ago
chatglm fix: miss usage of os.path.join for URL assembly and add tests on yarl (#4224) 2 years ago
cohere feat: add proxy configuration for Cohere model (#4152) 2 years ago
deepseek Typo on deepseek.yaml and yi.yaml (#4170) 2 years ago
google fix: pydantic2 error (#5172) 2 years ago
groq fix: credentials validate failed for groqcloud model provider (#3817) 2 years ago
huggingface_hub chore: apply ruff's pyupgrade linter rules to modernize Python code with targeted version (#2419) 2 years ago
hunyuan feat: support hunyuan llm models (#5013) 2 years ago
jina feat: support jina-clip-v1 embedding model (#5146) 2 years ago
leptonai Leptonai integrate (#4079) 2 years ago
localai fix(api/core/model_runtime/model_providers/baichuan,localai): Parse ToolPromptMessage. #4943 (#5138) 2 years ago
minimax feat:Provide parameter config for mask_sensitive_info of MiniMax mode… (#4294) 2 years ago
mistralai Add mixtral 8x22b (#3606) 2 years ago
moonshot feat: moonshot fc (#3629) 2 years ago
nvidia add-some-new-models-hosted-on-nvidia (#4303) 2 years ago
nvidia_nim chore: optimize nvidia nim credential schema and info (#4898) 2 years ago
ollama add: ollama keep alive parameter added. issue #4024 (#4655) 2 years ago
openai feat: set default memory messages limit to infinite (#5002) 2 years ago
openai_api_compatible fix(openai_api_compatible): fixing the error when converting chunk to json (#3570) 2 years ago
openllm chore: skip unnecessary key checks prior to accessing a dictionary (#4497) 2 years ago
openrouter feat: Vision switch functionality is provided on OpenRouter (#3564) 2 years ago
replicate feat: replicate supports default version. (#3884) 2 years ago
siliconflow feat: support siliconflow (#5129) 2 years ago
spark fix: resolve header.uid' length must be less or equal than 32 on Spark V1.5 (#2983) 2 years ago
togetherai add together ai model setting (#3895) 2 years ago
tongyi feat: refactor tongyi models (#3496) 2 years ago
triton_inference_server feat: refactor tongyi models (#3496) 2 years ago
vertex_ai fix(model_providers/vertex_ai): Vertex AI Anthropic models authentication failed (#4971) 2 years ago
volcengine_maas feat: support doubao llm function calling (#5100) 2 years ago
wenxin fix: update presence_penalty configuration for wenxin AI ernie-4.0-8k and ernie-3.5-8k models (#5039) 2 years ago
xinference feat: support vision models from xinference (#4094) 2 years ago
yi add yi models (#4335) 2 years ago
zhipuai feat: add glm4 new models and zhipu embedding-2 (#5089) 2 years ago
__init__.py Model Runtime (#1858) 2 years ago
_position.yaml feat: support siliconflow (#5129) 2 years ago
model_provider_factory.py improve: mordernizing validation by migrating pydantic from 1.x to 2.x (#4592) 2 years ago