"""NL2SQL 向量化适配器，复用公共 LLM 客户端。"""
from __future__ import annotations

import logging

from config.settings import settings
from tool.llm import llm

logger = logging.getLogger("nl2sql.embedding")
EMBEDDING_BATCH_SIZE = 10


class EmbeddingError(RuntimeError):
    """向量服务返回无效数据时抛出的异常。"""


async def embed_texts(texts: list[str], *, client=None) -> list[list[float]]:
    if not texts:
        return []
    provider = client or llm
    dimension = settings.llm.embed_dimensions
    vectors: list[list[float]] = []
    for start in range(0, len(texts), EMBEDDING_BATCH_SIZE):
        batch = texts[start : start + EMBEDDING_BATCH_SIZE]
        try:
            batch_vectors = await provider.embed(batch)
        except Exception as exc:  # noqa: BLE001 向量服务异常统一转换
            logger.exception("NL2SQL embedding provider failed")
            raise EmbeddingError("Embedding service unavailable") from exc
        if len(batch_vectors) != len(batch) or any(
            len(vector) != dimension for vector in batch_vectors
        ):
            raise EmbeddingError(f"Embedding dimension must be {dimension}")
        vectors.extend(batch_vectors)
    return vectors