encoder.py

from sentence_transformers import SentenceTransformer
import numpy as np
from typing import List, Union

class EnglishSentenceEncoder:
    def __init__(self, model_name: str = "all-MiniLM-L6-v2"):
        self.device = "cpu"
        self.model = SentenceTransformer(model_name, device=self.device)

    def encode(self, sentences: Union[str, List[str]]) -> np.ndarray:
        if isinstance(sentences, str):
            sentences = [sentences]
        return self.model.encode(sentences, convert_to_numpy=True)

    def __call__(self, sentences: Union[str, List[str]]) -> np.ndarray:
        return self.encode(sentences)