handler.py

from typing import  Dict, Any
import torch
import base64
from io import BytesIO
from model import Model
from PIL import Image
# set device
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

if device.type != 'cuda':
    raise ValueError("need to run on GPU")

class EndpointHandler():
    def __init__(self, path=""):
        # load the optimized model
        self.model = Model()


    def __call__(self, data: Any) -> Any:
        """
        Args:
            data (:obj:):
                includes the input data and the parameters for the inference.
        Return:
            A :obj:`dict`:. base64 encoded image
        """
        inputs = data.pop("inputs", data)

        
        image = Image.open(BytesIO(base64.b64decode(inputs['image'])))

        # run inference pipeline
        _, res = self.model.process_lineart(image) 
        
            
        # encoding image as base 64 is done by the default toolkit
        return res