import logging

from fastapi import APIRouter, HTTPException

from config import settings
from models.requests import QueryRequest
from models.responses import QueryResponse, SourceInfo
from services.llm_client import LLMClient
from services.rag_pipeline import rag_query

logger = logging.getLogger(__name__)

router = APIRouter(tags=["query"])


@router.post("/query", response_model=QueryResponse)
async def query_rag(request: QueryRequest):
    from main import vectorstore_service

    if vectorstore_service is None:
        raise HTTPException(status_code=503, detail="Service not ready")

    if not settings.deepseek_api_key:
        raise HTTPException(status_code=500, detail="DEEPSEEK_API_KEY not configured")

    llm_client = LLMClient()

    try:
        result = await rag_query(
            vectorstore=vectorstore_service,
            llm_client=llm_client,
            question=request.text,
            top_k=request.top_k,
            document_ids=request.document_ids,
            temperature=request.temperature,
            max_tokens=request.max_tokens,
        )
    except Exception as e:
        logger.exception("RAG query failed")
        raise HTTPException(status_code=500, detail=f"RAG query error: {e}")

    return QueryResponse(
        answer=result["answer"],
        sources=[SourceInfo(**s) for s in result["sources"]],
        model_used=result["model_used"],
        assembled_prompt=result.get("assembled_prompt", ""),
    )