def execute()

in templates/inference-endpoints/postprocessing/1/model.py [0:0]
9 lines of code
4 McCabe index (conditional complexity)

    def execute(self, requests):
        """`execute` must be implemented in every Python model. `execute`
        function receives a list of pb_utils.InferenceRequest as the only
        argument. This function is called when an inference is requested
        for this model. Depending on the batching configuration (e.g. Dynamic
        Batching) used, `requests` may contain multiple requests. Every
        Python model, must create one pb_utils.InferenceResponse for every
        pb_utils.InferenceRequest in `requests`. If there is an error, you can
        set the error argument when creating a pb_utils.InferenceResponse.
        Parameters
        ----------
        requests : list
          A list of pb_utils.InferenceRequest
        Returns
        -------
        list
          A list of pb_utils.InferenceResponse. The length of this list must
          be the same as `requests`
        """

        responses = []

        # Every Python backend must iterate over every request
        # and create a pb_utils.InferenceResponse for each of them.
        for idx, request in enumerate(requests):
            # Get input tensors
            tokens_batch = pb_utils.get_input_tensor_by_name(request, 'TOKENS_BATCH').as_numpy()

            # Reshape Input
            # tokens_batch = tokens_batch.reshape([-1, tokens_batch.shape[0]])
            # tokens_batch = tokens_batch.T

            # Postprocessing output data.
            outputs = self._postprocessing(tokens_batch)

            # Create output tensors. You need pb_utils.Tensor
            # objects to create pb_utils.InferenceResponse.
            output_tensor = pb_utils.Tensor('OUTPUT', np.array(outputs).astype(self.output_dtype))

            # Create InferenceResponse. You can set an error here in case
            # there was a problem with handling this inference request.
            # Below is an example of how you can set errors in inference
            # response:
            #
            # pb_utils.InferenceResponse(
            #    output_tensors=..., TritonError("An error occurred"))
            inference_response = pb_utils.InferenceResponse(output_tensors=[output_tensor])
            responses.append(inference_response)

        # You should return a list of pb_utils.InferenceResponse. Length
        # of this list must match the length of `requests` list.
        return responses