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


class Embedder:
    def __init__(self, model_name: str = "BAAI/bge-small-en-v1.5", device: str = "cpu"):
        self.model = SentenceTransformer(model_name, device=device)
        try:
            self.dim = self.model.get_embedding_dimension()
        except AttributeError:
            self.dim = self.model.get_sentence_embedding_dimension()

    def embed(self, texts: List[str], batch_size: int = 32) -> np.ndarray:
        if not texts:
            return np.empty((0, self.dim), dtype=np.float32)
        embeddings = self.model.encode(
            texts,
            normalize_embeddings=True,
            show_progress_bar=False,
            batch_size=batch_size,
        )
        return np.asarray(embeddings, dtype=np.float32)

    def embed_query(self, query: str) -> np.ndarray:
        emb = self.embed([query])
        return emb[0]

    @property
    def dimension(self) -> int:
        return self.dim