handler.py

import torch
from typing import Dict, List, Any
from transformers import AutoTokenizer, AutoModelForSequenceClassification, pipeline


# check for GPU
device = 0 if torch.cuda.is_available() else -1

# id2label = {
#     0: "Inconsistency",
#     1: "Consistency"
# }

class EndpointHandler:
    def __init__(self, path=""):
        # load the model
        tokenizer = AutoTokenizer.from_pretrained(path)
        model = AutoModelForSequenceClassification.from_pretrained(path, low_cpu_mem_usage=True)
        # create inference pipeline
        self.pipeline = pipeline("text-classification", model=model, tokenizer=tokenizer, device=device)

    def __call__(self, data: Any) -> List[List[Dict[str, float]]]:
        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