from typing import Dict, List, Any from InstructorEmbedding import INSTRUCTOR class EndpointHandler: def __init__(self, path=""): # load model on gpu self.model = INSTRUCTOR(path, device="cuda") def __call__(self, data: Dict[str, Any]) -> List[List[float]]: """ data args: inputs (:obj: `str`) Return: A :obj:`list` | `dict`: will be serialized and returned """ # get inputs inputs: dict = data.pop("inputs", data) print(inputs) # add instruction query = [['Retrieve documents that can help answer the question:', inputs]] # encode embedding = self.model.encode(query) return embedding