from qdrant_client import QdrantClient
from qdrant_client.http import models
from langchain_ollama import OllamaEmbeddings

class QdrantStore:
    def __init__(self, url="http://localhost:6333", collection_name="rag_collection"):
        self.client = QdrantClient(url=url)
        self.collection_name = collection_name
        self._ensure_collection()

    def _ensure_collection(self):
        if self.collection_name not in self.client.get_collections().collections:
            self.client.recreate_collection(
                collection_name=self.collection_name,
                vectors_config=models.VectorParams(size=384, distance=models.Distance.COSINE),
            )

    def add_documents(self, documents, titles):
        embeddings = OllamaEmbeddings(model="nomic-embed-text")
        vectors = embeddings.embed_documents(documents)
        payload = [{"title": t} for t in titles]
        self.client.upsert(
            collection_name=self.collection_name,
            points=models.Batch(points=[models.PointStruct(id=i, vector=v, payload=p) for i, (v, p) in enumerate(zip(vectors, payload))])
        )

    def search(self, query, limit=5):
        embeddings = OllamaEmbeddings(model="nomic-embed-text")
        query_vector = embeddings.embed_query(query)
        results = self.client.search(
            collection_name=self.collection_name,
            query_vector=query_vector,
            limit=limit,
            with_payload=True,
        )
        return [r.payload for r in results]