handler.py

from typing import Any, Dict, List
from transformers import Idefics2Processor, Idefics2Model


class EndpointHandler:
    def __init__(self, path=""):
        # Preload all the elements you are going to need at inference.
        self.processor = Idefics2Processor.from_pretrained(path)
        self.model = Idefics2Model.from_pretrained(path)

    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
        """
        image = data.pop("inputs", data)

        # process image
        output = self.processor(images=image, return_tensors="pt")
        generated_ids = self.model.generate(**output)

        # run prediction
        generated_text = self.processor.batch_decode(
            generated_ids, skip_special_tokens=True
        )

        # decode output
        print(generated_text)