from qdrant_client import QdrantClient
from qdrant_client.http import models as _models
from langchain_ollama import OllamaEmbeddings
import uuid
from typing import List, Tuple

class VectorStore:
    def __init__(self, collection_name: str = "rag_collection", host: str = "localhost", port: int = 6333):
        self.client = QdrantClient(host=host, port=port)
        self.collection_name = collection_name
        existing = [c.name for c in self.client.get_collections().collections]
        if collection_name not in existing:
            self.client.recreate_collection(
                collection_name=collection_name,
                vectors_config={"distance": "Cosine"},
            )
        self.embeddings = OllamaEmbeddings(model="nomic-embed-text")

    def add_documents(self, documents: List[str]) -> None:
        vectors = self.embeddings.embed_documents(documents)
        points = []
        for text, vector in zip(documents, vectors):
            points.append(
                _models.PointStruct(
                    id=uuid.uuid4().hex,
                    vector=vector,
                    payload={"text": text},
                )
            )
        self.client.upsert(collection_name=self.collection_name, points=points)

    def search(self, query: str, max_results: int = 5) -> List[Tuple[str, float]]:
        query_vector = self.embeddings.embed_query(query)
        results = self.client.search(
            collection_name=self.collection_name,
            query_vector=query_vector,
            limit=max_results,
            with_payload=True,
        )
        return [(p.payload["text"], p.score) for p in results]