majian 99b78dd198 feat: add gpt-4o-2024-08-06 (#7046) 8 ヶ月 前
..
__base 6da14c2d48 security: fix api image security issues (#6971) 8 ヶ月 前
anthropic 08f922d8c9 fix: anthropic max token NoneType error (#6858) 9 ヶ月 前
azure_openai a9cd6df97e Remove tts (blocking call) (#6869) 9 ヶ月 前
baichuan adc948e87c fix(api/core/model_runtime/model_providers/baichuan,localai): Parse ToolPromptMessage. #4943 (#5138) 10 ヶ月 前
bedrock 9ce5cea911 feat: bedrock invoke enhancement (#6808) 9 ヶ月 前
chatglm 228de1f12a fix: miss usage of os.path.join for URL assembly and add tests on yarl (#4224) 11 ヶ月 前
cohere dcb72e0067 chore: apply flake8-comprehensions Ruff rules to improve collection comprehensions (#5652) 10 ヶ月 前
deepseek bd3ed89516 feat: add function calling for deepseek models (#6990) 8 ヶ月 前
google dcb72e0067 chore: apply flake8-comprehensions Ruff rules to improve collection comprehensions (#5652) 10 ヶ月 前
groq a34285196b Revise the wrong pricing of certain LLM models. (#6967) 8 ヶ月 前
huggingface_hub 063191889d chore: apply ruff's pyupgrade linter rules to modernize Python code with targeted version (#2419) 1 年間 前
hunyuan 4b410494b3 Add model parameter enable_enhance for hunyuan llm model (#6847) 9 ヶ月 前
jina 26991443ed fix: Fix incorrect context size for jina-reranker-v2 model (#7006) 8 ヶ月 前
leptonai 51a9e678f0 Leptonai integrate (#4079) 1 年間 前
localai 9a64aa76c1 fix: typo and check (#5287) 10 ヶ月 前
minimax 4086f5051c feat:Provide parameter config for mask_sensitive_info of MiniMax mode… (#4294) 11 ヶ月 前
mistralai de3b490f8e Add mixtral 8x22b (#3606) 1 年間 前
moonshot 0bf4817474 fix: _convert_prompt_message_to_dict parameters err (#5716) 10 ヶ月 前
novita 3d3677e912 Feat/model provider novita (#6717) 9 ヶ月 前
nvidia 23ed15d19f feat:nvidia add nemotron4-340b and microsoft/phi-3 (#6973) 8 ヶ月 前
nvidia_nim 696c5308a9 chore: optimize nvidia nim credential schema and info (#4898) 11 ヶ月 前
ollama 56af1a0adf pref: change ollama embedded api request (#6876) 9 ヶ月 前
openai 99b78dd198 feat: add gpt-4o-2024-08-06 (#7046) 8 ヶ月 前
openai_api_compatible d7a6f25c63 fix: differentiate prompts fields based on function_calling_type (#5880) 9 ヶ月 前
openllm 04ad46dd31 chore: skip unnecessary key checks prior to accessing a dictionary (#4497) 11 ヶ月 前
openrouter 8166a8caf5 feat: update llama3.1 parameters for openrouter (#6901) 9 ヶ月 前
perfxcloud 215661ef91 feat: add PerfXCloud, Qwen series #6116 (#6117) 9 ヶ月 前
replicate dcb72e0067 chore: apply flake8-comprehensions Ruff rules to improve collection comprehensions (#5652) 10 ヶ月 前
sagemaker 4a026fa352 Enhancement: add model provider - Amazon Sagemaker (#6255) 9 ヶ月 前
siliconflow 3e18d32ce5 add deepseek-coder-v2 in siliconflow (#6149) 9 ヶ月 前
spark 68ac433218 feat: add support Spark4.0 (#5688) 10 ヶ月 前
stepfun 3b5b548af3 Add Stepfun LLM Support (#6346) 9 ヶ月 前
tencent 7c55c39085 feat: add tencent asr (#6091) 9 ヶ月 前
togetherai ba5f8afaa8 Feat/firecrawl data source (#5232) 10 ヶ月 前
tongyi f8617db012 fix tongyi tool calls (#6896) 9 ヶ月 前
triton_inference_server ec181649ae Update model provider configuration for Triton Inference Server and X… (#6274) 9 ヶ月 前
upstage 2e941bb91c add new provider Solar (#6884) 9 ヶ月 前
vertex_ai dcb72e0067 chore: apply flake8-comprehensions Ruff rules to improve collection comprehensions (#5652) 10 ヶ月 前
volcengine_maas 85744b72e5 feat: support moonshot and glm base models for volcengine provider (#6029) 9 ヶ月 前
wenxin 3516989738 fix: typos in wenxin llm (#7021) 8 ヶ月 前
xinference ea30174057 chore: optimize streaming tts of xinference (#6966) 8 ヶ月 前
yi ece0f08a2b add yi models (#4335) 11 ヶ月 前
zhipuai b47fa27a35 fix: zhipuai validate error when user's api key not support for chatglm_turbo in issue #6289 (#6290) 9 ヶ月 前
__init__.py d069c668f8 Model Runtime (#1858) 1 年間 前
_position.yaml 2e941bb91c add new provider Solar (#6884) 9 ヶ月 前
model_provider_factory.py 23fa3dedc4 fix(core): Fix incorrect type hints. (#5427) 10 ヶ月 前