import logging

from sentence_transformers import SentenceTransformer

logger = logging.getLogger(__name__)


class EmbeddingService:
    def __init__(self, model_name: str = "intfloat/multilingual-e5-large"):
        logger.info("Loading embedding model: %s", model_name)
        self.model = SentenceTransformer(model_name)
        self.model_name = model_name
        logger.info("Embedding model loaded (dim=%d)", self.model.get_sentence_embedding_dimension())

    def embed_documents(self, texts: list[str]) -> list[list[float]]:
        prefixed = [f"passage: {t}" for t in texts]
        embeddings = self.model.encode(prefixed, normalize_embeddings=True, show_progress_bar=False)
        return embeddings.tolist()

    def embed_query(self, query: str) -> list[float]:
        embedding = self.model.encode(f"query: {query}", normalize_embeddings=True)
        return embedding.tolist()