import torch
from typing import  Dict, List, Any
from transformers import AutoConfig, AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer, BitsAndBytesConfig, TextGenerationPipeline
from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig

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

class EndpointHandler():
    def __init__(self, path=""):
        # load the optimized model
        model = AutoGPTQForCausalLM.from_quantized(path, use_safetensors=True) #file_name="model-quantized.onnx")
        tokenizer = AutoTokenizer.from_pretrained(path)
        # or you can also use pipeline
        self.pipeline = TextGenerationPipeline(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 list contains the embeddings of the inference inputs
        """
        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)

        return prediction