Domovská stránka Prehľadávať Pomoc
Registrovať Prihlásiť sa
siwei
/
dify
1
0
Fork 0
Súbory Issues 0 Pull requesty 0 Wiki
Strom: 6452342222
Branche Tagy
dify
/
api
/
core
/
model_runtime
/
model_providers
Xiao Ley b28cf68097 chore: enable vision support for models in OpenRouter that should have supported vision (#10191) 1 rok pred
..
__base e61752bd3a feat/enhance the multi-modal support (#8818) 1 rok pred
anthropic e11d5ac708 feat(model_runtime): add new model 'claude-3-5-sonnet-20241022' (#9708) 1 rok pred
azure_ai_studio 1e829ceaf3 chore: format get_customizable_model_schema return value (#9335) 1 rok pred
azure_openai f6fecb957e fix azure chatgpt o1 parameter error (#10067) 1 rok pred
baichuan b90ad587c2 refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423) 1 rok pred
bedrock 4989d0c904 add bedrock claude 3.5 v2 support (#9685) 1 rok pred
chatglm 40fb4d16ef chore: refurbish Python code by applying refurb linter rules (#8296) 1 rok pred
cohere b90ad587c2 refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423) 1 rok pred
deepseek 153807f243 fix: response_format label (#8326) 1 rok pred
fireworks b90ad587c2 refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423) 1 rok pred
fishaudio 62051d5171 Corrected type annotation to "Any" from "any" all files in "model_providers" folder (#9135) 1 rok pred
gitee_ai 0ebd985672 feat: add models for gitee.ai (#9490) 1 rok pred
google 12adcf8925 fix: gemini model use some tools raise error (#9993) 1 rok pred
gpustack 76b0328eb1 feat: add gpustack model provider (#10158) 1 rok pred
groq b92504bebc Added Llama 3.2 Vision Models Speech2Text Models for Groq (#9479) 1 rok pred
huggingface_hub b90ad587c2 refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423) 1 rok pred
huggingface_tei 1e829ceaf3 chore: format get_customizable_model_schema return value (#9335) 1 rok pred
hunyuan 92a3898540 fix: resolve the incorrect model name of hunyuan-standard-256k (#10052) 1 rok pred
jina b90ad587c2 refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423) 1 rok pred
leptonai 2cf1187b32 chore(api/core): apply ruff reformatting (#7624) 1 rok pred
localai 1e829ceaf3 chore: format get_customizable_model_schema return value (#9335) 1 rok pred
minimax b90ad587c2 refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423) 1 rok pred
mistralai 5ddb601e43 add MixtralAI Model (#8517) 1 rok pred
mixedbread b90ad587c2 refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423) 1 rok pred
moonshot 1b5adf40da fix: moonshot response_format raise error (#9847) 1 rok pred
nomic b90ad587c2 refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423) 1 rok pred
novita 2cf1187b32 chore(api/core): apply ruff reformatting (#7624) 1 rok pred
nvidia b90ad587c2 refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423) 1 rok pred
nvidia_nim 2cf1187b32 chore(api/core): apply ruff reformatting (#7624) 1 rok pred
oci b90ad587c2 refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423) 1 rok pred
ollama b90ad587c2 refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423) 1 rok pred
openai 1e829ceaf3 chore: format get_customizable_model_schema return value (#9335) 1 rok pred
openai_api_compatible 70ddc0ce43 openai compatiable api usage and id (#9800) 1 rok pred
openllm 1e829ceaf3 chore: format get_customizable_model_schema return value (#9335) 1 rok pred
openrouter b28cf68097 chore: enable vision support for models in OpenRouter that should have supported vision (#10191) 1 rok pred
perfxcloud b90ad587c2 refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423) 1 rok pred
replicate b90ad587c2 refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423) 1 rok pred
sagemaker 1e829ceaf3 chore: format get_customizable_model_schema return value (#9335) 1 rok pred
siliconflow 1e829ceaf3 chore: format get_customizable_model_schema return value (#9335) 1 rok pred
spark d0e0111f88 fix:Spark's large language model token calculation error #7911 (#8755) 1 rok pred
stepfun 1e829ceaf3 chore: format get_customizable_model_schema return value (#9335) 1 rok pred
tencent 40fb4d16ef chore: refurbish Python code by applying refurb linter rules (#8296) 1 rok pred
togetherai 2cf1187b32 chore(api/core): apply ruff reformatting (#7624) 1 rok pred
tongyi 1e829ceaf3 chore: format get_customizable_model_schema return value (#9335) 1 rok pred
triton_inference_server 1e829ceaf3 chore: format get_customizable_model_schema return value (#9335) 1 rok pred
upstage b90ad587c2 refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423) 1 rok pred
vertex_ai ecc8beef3f feat: added claude 3.5 sonnet v2 model to Google Cloud Vertex AI (#9688) 1 rok pred
vessl_ai 8d5456b6d0 Add VESSL AI OpenAI API-compatible model provider and LLM model (#9474) 1 rok pred
volcengine_maas 1e829ceaf3 chore: format get_customizable_model_schema return value (#9335) 1 rok pred
voyage b90ad587c2 refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423) 1 rok pred
wenxin 4d5546953a add llm: ernie-4.0-turbo-128k of wenxin (#10135) 1 rok pred
xinference 1e829ceaf3 chore: format get_customizable_model_schema return value (#9335) 1 rok pred
yi e0846792d2 feat: add yi custom llm intergration (#9482) 1 rok pred
zhinao 2cf1187b32 chore(api/core): apply ruff reformatting (#7624) 1 rok pred
zhipuai b90ad587c2 refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423) 1 rok pred
__init__.py d069c668f8 Model Runtime (#1858) 1 rok pred
_position.yaml fb49413a41 feat: add voyage ai as a new model provider (#8747) 1 rok pred
model_provider_factory.py 4e7b6aec3a feat: support pinning, including, and excluding for model providers and tools (#7419) 1 rok pred