import time

from app.core.config import settings
from app.integrations.embedding_adapter import OpenAICompatibleEmbeddingClient


class EmbeddingService:
    """Embedding 服务：按配置批量调用向量模型，控制批大小和耗时统计。"""

    def __init__(self, client: OpenAICompatibleEmbeddingClient | None = None) -> None:
        self.client = client or OpenAICompatibleEmbeddingClient()

    async def embed_texts(self, texts: list[str]) -> tuple[list[list[float]], int]:
        """批量向量化：按 EMBEDDING_BATCH_SIZE 分批生成向量并返回总耗时。"""
        start = time.perf_counter()
        vectors: list[list[float]] = []
        batch_size = max(1, settings.embedding_batch_size)
        for index in range(0, len(texts), batch_size):
            batch = texts[index : index + batch_size]
            batch_vectors, _usage = await self.client.embed_texts(batch)
            vectors.extend(batch_vectors)
        return vectors, int((time.perf_counter() - start) * 1000)