Home Esplora Aiuto
Registrati Accedi
siwei
/
dify
1
0
Forka 0
File Problemi 0 Pull Requests 0 Wiki
Albero (Tree): 25ca0278dd
Rami (Branch) Tag
dify
/
api
/
core
/
model_runtime
/
model_providers
非法操作 033ab5490b feat: support LLM understand video (#9828) 8 mesi fa
..
__base e61752bd3a feat/enhance the multi-modal support (#8818) 9 mesi fa
anthropic 1e8457441d fix(model_runtime): remove vision from features for Claude 3.5 Haiku (#10360) 8 mesi fa
azure_ai_studio 574c4a264f chore(lint): Use logging.exception instead of logging.error (#10415) 8 mesi fa
azure_openai f6fecb957e fix azure chatgpt o1 parameter error (#10067) 9 mesi fa
baichuan b90ad587c2 refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423) 9 mesi fa
bedrock 1e8457441d fix(model_runtime): remove vision from features for Claude 3.5 Haiku (#10360) 8 mesi fa
chatglm 40fb4d16ef chore: refurbish Python code by applying refurb linter rules (#8296) 10 mesi fa
cohere b90ad587c2 refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423) 9 mesi fa
deepseek 153807f243 fix: response_format label (#8326) 10 mesi fa
fireworks b90ad587c2 refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423) 9 mesi fa
fishaudio 62051d5171 Corrected type annotation to "Any" from "any" all files in "model_providers" folder (#9135) 9 mesi fa
gitee_ai 2aa171c348 Using a dedicated interface to obtain the token credential for the gitee.ai provider (#10243) 9 mesi fa
google 12adcf8925 fix: gemini model use some tools raise error (#9993) 9 mesi fa
gpustack 76b0328eb1 feat: add gpustack model provider (#10158) 9 mesi fa
groq b92504bebc Added Llama 3.2 Vision Models Speech2Text Models for Groq (#9479) 9 mesi fa
huggingface_hub b90ad587c2 refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423) 9 mesi fa
huggingface_tei 1e829ceaf3 chore: format get_customizable_model_schema return value (#9335) 9 mesi fa
hunyuan 92a3898540 fix: resolve the incorrect model name of hunyuan-standard-256k (#10052) 9 mesi fa
jina b90ad587c2 refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423) 9 mesi fa
leptonai 2cf1187b32 chore(api/core): apply ruff reformatting (#7624) 10 mesi fa
localai 1e829ceaf3 chore: format get_customizable_model_schema return value (#9335) 9 mesi fa
minimax b90ad587c2 refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423) 9 mesi fa
mistralai 5ddb601e43 add MixtralAI Model (#8517) 10 mesi fa
mixedbread b90ad587c2 refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423) 9 mesi fa
moonshot 1b5adf40da fix: moonshot response_format raise error (#9847) 9 mesi fa
nomic b90ad587c2 refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423) 9 mesi fa
novita 2cf1187b32 chore(api/core): apply ruff reformatting (#7624) 10 mesi fa
nvidia b90ad587c2 refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423) 9 mesi fa
nvidia_nim 2cf1187b32 chore(api/core): apply ruff reformatting (#7624) 10 mesi fa
oci b90ad587c2 refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423) 9 mesi fa
ollama b90ad587c2 refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423) 9 mesi fa
openai 1e829ceaf3 chore: format get_customizable_model_schema return value (#9335) 9 mesi fa
openai_api_compatible 70ddc0ce43 openai compatiable api usage and id (#9800) 9 mesi fa
openllm 1e829ceaf3 chore: format get_customizable_model_schema return value (#9335) 9 mesi fa
openrouter 5a9448245b fix: remove unsupported vision in OpenRouter Haiku 3.5 (#10364) 8 mesi fa
perfxcloud b90ad587c2 refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423) 9 mesi fa
replicate b90ad587c2 refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423) 9 mesi fa
sagemaker d45d90e8ae chore: lazy import sagemaker (#10342) 8 mesi fa
siliconflow 1e829ceaf3 chore: format get_customizable_model_schema return value (#9335) 9 mesi fa
spark d0e0111f88 fix:Spark's large language model token calculation error #7911 (#8755) 10 mesi fa
stepfun 1e829ceaf3 chore: format get_customizable_model_schema return value (#9335) 9 mesi fa
tencent 40fb4d16ef chore: refurbish Python code by applying refurb linter rules (#8296) 10 mesi fa
togetherai 2cf1187b32 chore(api/core): apply ruff reformatting (#7624) 10 mesi fa
tongyi 033ab5490b feat: support LLM understand video (#9828) 8 mesi fa
triton_inference_server 1e829ceaf3 chore: format get_customizable_model_schema return value (#9335) 9 mesi fa
upstage b90ad587c2 refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423) 9 mesi fa
vertex_ai ecc8beef3f feat: added claude 3.5 sonnet v2 model to Google Cloud Vertex AI (#9688) 9 mesi fa
vessl_ai 8d5456b6d0 Add VESSL AI OpenAI API-compatible model provider and LLM model (#9474) 9 mesi fa
volcengine_maas 1e829ceaf3 chore: format get_customizable_model_schema return value (#9335) 9 mesi fa
voyage b90ad587c2 refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423) 9 mesi fa
wenxin 4d5546953a add llm: ernie-4.0-turbo-128k of wenxin (#10135) 9 mesi fa
x bf9349c4dc feat: add xAI model provider (#10272) 8 mesi fa
xinference 1e829ceaf3 chore: format get_customizable_model_schema return value (#9335) 9 mesi fa
yi e0846792d2 feat: add yi custom llm intergration (#9482) 9 mesi fa
zhinao 2cf1187b32 chore(api/core): apply ruff reformatting (#7624) 10 mesi fa
zhipuai 033ab5490b feat: support LLM understand video (#9828) 8 mesi fa
__init__.py d069c668f8 Model Runtime (#1858) 1 anno fa
_position.yaml fb49413a41 feat: add voyage ai as a new model provider (#8747) 10 mesi fa
model_provider_factory.py 4e7b6aec3a feat: support pinning, including, and excluding for model providers and tools (#7419) 11 mesi fa