from typing import Dict, List, Any
from transformers import CLIPTokenizer, CLIPModel
import numpy as np
import os


class EndpointHandler:
    def __init__(self, path=""):
        self.model = CLIPModel.from_pretrained("openai/clip-vit-large-patch14")
        self.tokenizer = CLIPTokenizer.from_pretrained("openai/clip-vit-large-patch14")

        self.artwork_urls = np.load(os.path.join(path, "artwork_urls.npy"), allow_pickle=True)
        self.embeddings = np.load(os.path.join(path, "embeddings.npy"), allow_pickle=True)

    def __call__(self, data: Dict[str, Any]) -> List[float]:
        """
         data args:
              inputs (:obj: `str` | `PIL.Image` | `np.array`)
              kwargs
        Return:
              A :obj:`list` | `dict`: will be serialized and returned
        """
        inputs = self.tokenizer(data["inputs"], padding=True, return_tensors="pt")
        text_features = self.model.get_text_features(**inputs)
        text_features = text_features.detach().numpy() 
        input_embedding = text_features[0]
        input_embedding = input_embedding / np.linalg.norm(input_embedding)

        cos_score = self.embeddings @ input_embedding
        top_10 = cos_score.argsort()[-100:][::-1]

        return self.artwork_urls[top_10].tolist()