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


# check for GPU
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")


class EndpointHandler():
    def __init__(self, path=""):
        # Preload all the elements you are going to need at inference.
        # pseudo:
        self.pipeline= pipeline("image-to-text", model="nlpconnect/vit-gpt2-image-captioning", device=device)

    def __call__(self, data: Dict[str, Any]) -> List[Dict[str, Any]]:
        """
       data args:
            inputs (:obj: `str` | `PIL.Image` | `np.array`)
            kwargs
      Return:
            A :obj:`list` | `dict`: will be serialized and returned
        """
        
        inputs = data.pop("inputs", data)
        return self.pipeline(inputs)