WatsonXModel

class WatsonXModel(BaseModelBackend):

WatsonX API in a unified BaseModelBackend interface.

Parameters:

  • model_type (Union[ModelType, str]): Model type for which a backend is created, one of WatsonX series.
  • model_config_dict (Optional[Dict[str, Any]], optional): A dictionary that will be fed into :obj:ModelInference.chat().
  • If: obj:None, :obj:WatsonXConfig().as_dict() will be used. (default: :obj:None)
  • api_key (Optional[str], optional): The API key for authenticating with the WatsonX service. (default: :obj:None)
  • url (Optional[str], optional): The url to the WatsonX service. (default: :obj:None)
  • project_id (Optional[str], optional): The project ID authenticating with the WatsonX service. (default: :obj:None)
  • 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,
    project_id: Optional[str] = None,
    token_counter: Optional[BaseTokenCounter] = None,
    timeout: Optional[float] = None
):

_to_openai_response

def _to_openai_response(self, response: Dict[str, Any]):

Convert WatsonX response to OpenAI format.

token_counter

def token_counter(self):

Returns:

BaseTokenCounter: The token counter following the model’s tokenization style.

_prepare_request

def _prepare_request(
    self,
    messages: List[OpenAIMessage],
    response_format: Optional[Type[BaseModel]] = None,
    tools: Optional[List[Dict[str, Any]]] = None
):

_run

def _run(
    self,
    messages: List[OpenAIMessage],
    response_format: Optional[Type[BaseModel]] = None,
    tools: Optional[List[Dict[str, Any]]] = None
):

Runs inference of WatsonX chat completion.

Parameters:

  • messages (List[OpenAIMessage]): Message list with the chat history in OpenAI API format.
  • response_format (Optional[Type[BaseModel]], optional): The response format. (default: :obj:None)
  • tools (Optional[List[Dict[str, Any]]], optional): tools to use. (default: :obj:None)

Returns:

ChatCompletion.

check_model_config

def check_model_config(self):

stream

def stream(self):

Returns:

bool: Whether the model is in stream mode.