handler.py

from typing import Dict, List, Any

import torch
from transformers import pipeline, XLMRobertaTokenizerFast, XLMRobertaForSequenceClassification


class EndpointHandler:
    def __init__(self, path=""):
        self.device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
        # load the optimized model
        model = XLMRobertaForSequenceClassification.from_pretrained(path)
        tokenizer = XLMRobertaTokenizerFast.from_pretrained(path)
        model.eval()
        # create inference pipeline
        self.pipline = pipeline("text-classification", tokenizer=tokenizer, model=model, device=self.device)

    def __call__(self, data: Any) -> List[List[Dict[str, float]]]:
        """
        Args:
            data (:obj:):
                includes the input data and the parameters for the inference.
        Return:
            A :obj:`list`:. The object returned should be a list of one list like [[{"label": 0.9939950108528137}]] containing :
                - "label": A string representing what the label/class is. There can be multiple labels.
                - "score": A score between 0 and 1 describing how confident the model is for this label/class.
        """
        inputs = data.pop("inputs", data)
        parameters = data.pop("parameters", None)

        # pass inputs with all kwargs in data
        if parameters is not None:
            prediction = self.pipline(inputs, **parameters)
        else:
            prediction = self.pipline(inputs)
        # postprocess the prediction
        return [{"label": p["label"]} for p in prediction]