def predict()

in src/sagemaker_huggingface_inference_toolkit/handler_service.py [0:0]


    def predict(self, data, model, context=None):
        """The predict handler is responsible for model predictions. Calls the `__call__` method of the provided `Pipeline`
        on decoded_input_data deserialized in input_fn. Runs prediction on GPU if is available.
        The predict handler can be overridden to implement the model inference.

        Args:
            data (dict): deserialized decoded_input_data returned by the input_fn
            model : Model returned by the `load` method or if it is a custom module `model_fn`.
            context (obj): metadata on the incoming request data (default: None).

        Returns:
            obj (dict): prediction result.
        """

        # pop inputs for pipeline
        inputs = data.pop("inputs", data)
        parameters = data.pop("parameters", None)

        # pass inputs with all kwargs in data
        if parameters is not None:
            prediction = model(inputs, **parameters)
        else:
            prediction = model(inputs)
        return prediction