import os
from typing import Dict, List, Any
from groundingdino.util.inference import load_model, load_image, predict, annotate

HOME = os.getcwd()
CONFIG_PATH = os.path.join(HOME, "GroundingDINO/groundingdino/config/GroundingDINO_SwinT_OGC.py")
WEIGHTS_PATH = os.path.join(HOME, "weights", "groundingdino_swint_ogc.pth")

class EndpointHandler():
    def __init__(self):
        # Preload all the elements you are going to need at inference.
        self.model = load_model(CONFIG_PATH, WEIGHTS_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
        """
        inputs = data.pop("inputs")
        image = inputs.pop("image")
        prompt = inputs.pop("prompt")

        return [{
            "image": image,
            "prompt": prompt,
        }]