from functools import lru_cache

from sentence_transformers import SentenceTransformer

# Multilingual so German player messages retrieve relevant chunks from the
# English-language rulebooks. 384-dim output, matching RulebookChunk.embedding.
MODEL_NAME = "paraphrase-multilingual-MiniLM-L12-v2"


@lru_cache
def get_embedding_model() -> SentenceTransformer:
    return SentenceTransformer(MODEL_NAME)


def embed_texts(texts: list[str]) -> list[list[float]]:
    model = get_embedding_model()
    embeddings = model.encode(texts, normalize_embeddings=True, show_progress_bar=False)
    return embeddings.tolist()


def embed_query(text: str) -> list[float]:
    return embed_texts([text])[0]