from typing import Dict, List, Any
from transformers import AutoModel, AutoTokenizer, pipeline


class EndpointHandler:
    def __init__(self, path=""):
        # load the model
        tokenizer = AutoTokenizer.from_pretrained(path)
        model = AutoModel.from_pretrained(path, low_cpu_mem_usage=True)
        # create inference pipeline
        # Do I have to check device?
        self.pipeline = pipeline(
            "text-generation", model=model, tokenizer=tokenizer)

    # (Might have to adjust typing)
    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