handler.py

from typing import Dict, List, Any
# from sentence_transformers import SentenceTransformer

class EndpointHandler():
    def __init__(self, path="NV-Embed-v2"):
        # Preload all the elements you are going to need at inference.
        # pseudo:
        # self.model= load_model(path)
        self.embedding_model = SentenceTransformer(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
        """
        # embeddings = self.embedding_model.encode(data)
        # return embeddings
        # pseudo
        # self.model(input)