from typing import Dict, List, Any

from transformers import Blip2Processor, Blip2ForConditionalGeneration

from PIL import Image
from io import BytesIO
import torch, os, base64


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

        self.processor = Blip2Processor.from_pretrained("Salesforce/blip2-opt-2.7b") 
        self.model = Blip2ForConditionalGeneration.from_pretrained("Salesforce/blip2-opt-2.7b", device_map="auto")



    def __call__(self, data: Any) -> Dict[str, Any]:
        """
        Args:
            data (:obj:):
                includes the input data and the parameters for the inference.
        Return:
            A :obj:`dict`:. The object returned should be a dict of one list like {"captions": ["A hugging face at the office"]} containing :
                - "caption": A string corresponding to the generated caption.
        """

        inputs = data["inputs"]
        # parameters = data.pop("parameters", {})
        device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

        if type(inputs) is str:
            inputs = inputs.encode('utf-8')

        raw_images = Image.open(BytesIO(inputs))
                                     
        processed_image = self.processor(images=raw_images, return_tensors="pt").to(device)

        out = self.model.generate(**processed_image)
       
        captions = self.processor.decode(out[0], skip_special_tokens=True)

        # postprocess the prediction
        return {"captions": captions}
    

EndpointHandler()