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
Bowen Liang 0d74466f45 chore: lazy import sagemaker (#10342) 1 year ago
..
__base feat/enhance the multi-modal support (#8818) 2 years ago
anthropic feat(model_runtime): add new model 'claude-3-5-haiku-20241022' (#10285) 1 year ago
azure_ai_studio chore: format get_customizable_model_schema return value (#9335) 2 years ago
azure_openai fix azure chatgpt o1 parameter error (#10067) 1 year ago
baichuan refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423) 2 years ago
bedrock fix(model_runtime): fix wrong max_tokens for Claude 3.5 Haiku on Amazon Bedrock (#10286) 1 year ago
chatglm
cohere refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423) 2 years ago
deepseek
fireworks refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423) 2 years ago
fishaudio Corrected type annotation to "Any" from "any" all files in "model_providers" folder (#9135) 2 years ago
gitee_ai Using a dedicated interface to obtain the token credential for the gitee.ai provider (#10243) 1 year ago
google fix: gemini model use some tools raise error (#9993) 2 years ago
gpustack feat: add gpustack model provider (#10158) 1 year ago
groq Added Llama 3.2 Vision Models Speech2Text Models for Groq (#9479) 2 years ago
huggingface_hub refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423) 2 years ago
huggingface_tei chore: format get_customizable_model_schema return value (#9335) 2 years ago
hunyuan fix: resolve the incorrect model name of hunyuan-standard-256k (#10052) 1 year ago
jina refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423) 2 years ago
leptonai
localai chore: format get_customizable_model_schema return value (#9335) 2 years ago
minimax refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423) 2 years ago
mistralai
mixedbread refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423) 2 years ago
moonshot fix: moonshot response_format raise error (#9847) 2 years ago
nomic refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423) 2 years ago
novita
nvidia refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423) 2 years ago
nvidia_nim
oci refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423) 2 years ago
ollama refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423) 2 years ago
openai chore: format get_customizable_model_schema return value (#9335) 2 years ago
openai_api_compatible openai compatiable api usage and id (#9800) 2 years ago
openllm chore: format get_customizable_model_schema return value (#9335) 2 years ago
openrouter feat: add support for anthropic/claude-3-5-haiku through OpenRouter (#10331) 1 year ago
perfxcloud refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423) 2 years ago
replicate refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423) 2 years ago
sagemaker chore: lazy import sagemaker (#10342) 1 year ago
siliconflow chore: format get_customizable_model_schema return value (#9335) 2 years ago
spark
stepfun chore: format get_customizable_model_schema return value (#9335) 2 years ago
tencent
togetherai
tongyi chore: format get_customizable_model_schema return value (#9335) 2 years ago
triton_inference_server chore: format get_customizable_model_schema return value (#9335) 2 years ago
upstage refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423) 2 years ago
vertex_ai feat: added claude 3.5 sonnet v2 model to Google Cloud Vertex AI (#9688) 2 years ago
vessl_ai Add VESSL AI OpenAI API-compatible model provider and LLM model (#9474) 1 year ago
volcengine_maas chore: format get_customizable_model_schema return value (#9335) 2 years ago
voyage refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423) 2 years ago
wenxin add llm: ernie-4.0-turbo-128k of wenxin (#10135) 1 year ago
x feat: add xAI model provider (#10272) 1 year ago
xinference chore: format get_customizable_model_schema return value (#9335) 2 years ago
yi feat: add yi custom llm intergration (#9482) 2 years ago
zhinao
zhipuai refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423) 2 years ago
__init__.py
_position.yaml
model_provider_factory.py