"""BGE Embedding Service Client"""
import requests
import logging
from typing import List

logger = logging.getLogger(__name__)

# BGE-small-zh-v1.5: 512 tokens, roughly ~1500 Chinese chars
# Conservative limit: 2000 chars (most text under this is safe)
MAX_TEXT_CHARS = 2000


class EmbeddingService:
    """Client for BGE-small-zh-v1.5 embedding service."""

    def __init__(self, base_url: str = "http://127.0.0.1:8080", timeout: int = 30):
        self.base_url = base_url.rstrip("/")
        self.timeout = timeout

    def embed(self, text: str) -> List[float]:
        """Get embedding for a single text.
        
        Text is truncated to MAX_TEXT_CHARS if too long.
        """
        original_len = len(text)
        if len(text) > MAX_TEXT_CHARS:
            logger.warning(f"Text too long ({original_len} chars), truncating to {MAX_TEXT_CHARS}")
            text = text[:MAX_TEXT_CHARS]

        try:
            resp = requests.post(
                f"{self.base_url}/embed",
                json={"text": text},
                timeout=self.timeout,
            )
            resp.raise_for_status()
            data = resp.json()
            return data["embedding"]
        except requests.exceptions.ConnectionError:
            msg = "Embedding service unavailable (connection refused)"
            logger.error(msg)
            raise RuntimeError(msg)
        except requests.exceptions.Timeout:
            msg = f"Embedding request timeout ({self.timeout}s). Text may be too long ({original_len} chars, max {MAX_TEXT_CHARS})"
            logger.error(msg)
            raise RuntimeError(msg)
        except requests.exceptions.HTTPError as e:
            status = e.response.status_code if e.response is not None else "unknown"
            msg = f"Embedding service error (HTTP {status}): {e}"
            logger.error(msg)
            raise RuntimeError(msg)
        except Exception as e:
            msg = f"Embedding failed: {e}"
            logger.error(msg)
            raise RuntimeError(msg)

    def embed_batch(self, texts: List[str]) -> List[List[float]]:
        """Get embeddings for multiple texts."""
        return [self.embed(t) for t in texts]

    def health_check(self) -> bool:
        """Check if embedding service is alive."""
        try:
            resp = requests.get(f"{self.base_url}/health", timeout=5)
            return resp.status_code == 200
        except Exception:
            return False