services:
  qdrant:
    image: qdrant/qdrant:latest
    ports:
      - "6333:6333"
    volumes:
      - qdrant_data:/qdrant/storage

volumes:
  qdrant_data:

class RAGService:
    def __init__(
        self,
        vector_db: QdrantAdapter,
        embedder: LocalEmbeddingAdapter,
        llm_adapter,
    ) -> None:
        self._db = vector_db
        self._embedder = embedder
        self._llm = llm_adapter

    async def answer(self, question: str, top_k: int = 5) -> dict:
        query_embedding = self._embedder.embed([question])[0]
        retrieved = await self._db.search(query_embedding, top_k=top_k)

        if not retrieved:
            return {"answer": "No information found in knowledge base.", "sources": []}

        context = "\n\n---\n\n".join(r["text"] for r in retrieved)
        sources = list({r["source"] for r in retrieved})

        answer = await self._llm.invoke(
            system="Answer based only on the provided context. If the answer is not in the context, say so explicitly.",
            messages=[{"role": "user", "content": f"Context:\n{context}\n\nQuestion: {question}"}],
        )

        return {"answer": answer, "sources": sources, "retrieved_count": len(retrieved)}