from typing import Dict, List, Any from InstructorEmbedding import INSTRUCTOR INSTRUCTION_SEPARATOR = "|||" class EndpointHandler: def __init__(self, path=""): # load model self.model = INSTRUCTOR(path, device="cuda") def __call__(self, data: Dict[str, Any]) -> List[Dict[str, Any]]: """ data args: inputs (:obj: `str`) Return: A :obj:`list` | `dict`: will be serialized and returned """ # get inputs texts = data.pop("texts", data) instruction = data.pop("instruction", "Represent this sentence:") # if isinstance(inputs, str): # inputs = [inputs] # run normal prediction # scores = self.model.predict_proba(inputs)[0] # return [{"label": self.id2label[i], "score": score.item()} for i, score in enumerate(scores)] instructions = [[instruction, text] for text in texts] embeddings = self.model.encode(instructions) return embeddings.tolist()