ModelScopeModel

class ModelScopeModel(OpenAICompatibleModel):

ModelScope API in a unified OpenAICompatibleModel interface.

Parameters:

  • model_type (Union[ModelType, str]): Model for which a backend is created, one of ModelScope series.
  • model_config_dict (Optional[Dict[str, Any]], optional): A dictionary that will be fed into:obj:openai.ChatCompletion.create(). If :obj:None, :obj:ModelScopeConfig().as_dict() will be used. (default: :obj:None)
  • api_key (Optional[str], optional): The MODELSCOPE_SDK_TOKEN for authenticating with the ModelScope service. (default: :obj:None) refer to the following link for more details:
  • https: //modelscope.cn/my/myaccesstoken
  • url (Optional[str], optional): The url to the ModelScope service. (default: :obj:https://api-inference.modelscope.cn/v1/)
  • token_counter (Optional[BaseTokenCounter], optional): Token counter to use for the model. If not provided, :obj:OpenAITokenCounter( ModelType.GPT_4O_MINI) will be used. (default: :obj:None)
  • timeout (Optional[float], optional): The timeout value in seconds for API calls. If not provided, will fall back to the MODEL_TIMEOUT environment variable or default to 180 seconds. (default: :obj:None)

init

def __init__(
    self,
    model_type: Union[ModelType, str],
    model_config_dict: Optional[Dict[str, Any]] = None,
    api_key: Optional[str] = None,
    url: Optional[str] = None,
    token_counter: Optional[BaseTokenCounter] = None,
    timeout: Optional[float] = None
):

_post_handle_response

def _post_handle_response(
    self,
    response: Union[ChatCompletion, Stream[ChatCompletionChunk]]
):

Handle reasoning content with <think> tags at the beginning.

_request_chat_completion

def _request_chat_completion(
    self,
    messages: List[OpenAIMessage],
    tools: Optional[List[Dict[str, Any]]] = None
):

check_model_config

def check_model_config(self):