orangeclk c534d95972 fix: yi model price correction (#2946) 1 éve
..
__base 8b15b742ad generalize position helper for parsing _position.yaml and sorting objects by name (#2803) 1 éve
anthropic 2dee8a25d5 fix: anthropic system prompt not working (#2885) 1 éve
azure_openai f6314f8e73 feat:support azure openai llm 0125 version (#2889) 1 éve
baichuan cb79a90031 feat: Add tools for open weather search and image generation using the Spark API. (#2845) 1 éve
bedrock 507aa6d949 fix: Fix the problem of system not working (#2884) 1 éve
chatglm 063191889d chore: apply ruff's pyupgrade linter rules to modernize Python code with targeted version (#2419) 1 éve
cohere e54c9cd401 Feat/open ai compatible functioncall (#2783) 1 éve
google 3e63abd335 Feat/json mode (#2563) 1 éve
groq 1809f05904 Feat/add groq (#2733) 1 éve
huggingface_hub 063191889d chore: apply ruff's pyupgrade linter rules to modernize Python code with targeted version (#2419) 1 éve
jina 8fe83750b7 Fix/jina tokenizer cache (#2735) 1 éve
localai 742be06ea9 Fix/localai (#2840) 1 éve
minimax 7f3dec7bee fix error msg format issue (#2715) 1 éve
mistralai e54c9cd401 Feat/open ai compatible functioncall (#2783) 1 éve
moonshot 174ee1b646 fix: parameter `user` exceeded max length when invoking moonshot llm (#2596) 1 éve
nvidia 518c1ceb94 Feat/add-NVIDIA-as-a-new-model-provider (#2900) 1 éve
ollama fbbba6db92 feat: optimize ollama model default parameters (#2894) 1 éve
openai 83145486b0 fix: fix unstable function call response arguments missing (#2872) 1 éve
openai_api_compatible e54c9cd401 Feat/open ai compatible functioncall (#2783) 1 éve
openllm 7f3dec7bee fix error msg format issue (#2715) 1 éve
replicate 063191889d chore: apply ruff's pyupgrade linter rules to modernize Python code with targeted version (#2419) 1 éve
spark 063191889d chore: apply ruff's pyupgrade linter rules to modernize Python code with targeted version (#2419) 1 éve
togetherai 063191889d chore: apply ruff's pyupgrade linter rules to modernize Python code with targeted version (#2419) 1 éve
tongyi 8133ba16b1 chore: update Qwen model params (#2892) 1 éve
triton_inference_server 240a94182e Feat/add triton inference server (#2928) 1 éve
wenxin 3e63abd335 Feat/json mode (#2563) 1 éve
xinference 405a00bb2c fix:delete the slash at the end of xinference provider server_url (#2730) 1 éve
yi c534d95972 fix: yi model price correction (#2946) 1 éve
zhipuai e7343cc67c add max_tokens parameter rule for zhipuai glm4 and glm4v (#2861) 1 éve
__init__.py d069c668f8 Model Runtime (#1858) 1 éve
_position.yaml 240a94182e Feat/add triton inference server (#2928) 1 éve
model_provider_factory.py 8b15b742ad generalize position helper for parsing _position.yaml and sorting objects by name (#2803) 1 éve