handler.py

from typing import  Dict, List, Any
# import torch
from transformers import DistilBertTokenizer, DistilBertForSequenceClassification


# from optimum.onnxruntime import ORTModelForSequenceClassification
from transformers import AutoModel
# from transformers import AutoModelForSequenceClassification, AutoTokenizer

from transformers import pipeline, AutoTokenizer

# checkpoint = "distilbert-base-uncased-finetuned-sst-2-english"
checkpoint = "distilbert-base-uncased"

class EndpointHandler():
    
    def __init__(self, path=""):
        # load the optimized model
        # model = ORTModelForSequenceClassification.from_pretrained(path)
        # model = AutoModel.from_pretrained(checkpoint)
        # model = AutoModelForSequenceClassification.from_pretrained(checkpoint)

        # tokenizer = AutoTokenizer.from_pretrained(path)
        # tokenizer = AutoTokenizer.from_pretrained(pretrained_model_name_or_path=checkpoint)
        model = DistilBertForSequenceClassification.from_pretrained(checkpoint)
        tokenizer = DistilBertTokenizer.from_pretrained(checkpoint)

        # create inference pipeline
        self.pipeline = pipeline("text-classification", model=model, tokenizer=tokenizer)


    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.pipeline(inputs, **parameters)
        else:
            prediction = self.pipeline(inputs)
        # postprocess the prediction
        return prediction