"""Wrapper around QdrantVectorStore using Ollama embeddings.

This module is intentionally lightweight and can be imported from any
context without requiring the caller to set up a package structure.
"""

import os
import sys

# Ensure the current directory is in sys.path so that relative imports work
sys.path.append(os.path.dirname(__file__))

from langchain_ollama import OllamaEmbeddings
from langchain_qdrant import QdrantVectorStore
from langchain_text_splitters import RecursiveCharacterTextSplitter
from typing import List, Dict

class QdrantStore:
    """Wrapper around QdrantVectorStore using Ollama embeddings."""

    def __init__(self, host: str = "localhost", port: int = 6333, collection_name: str = "knowledge_base"):
        self.embeddings = OllamaEmbeddings(model="nomic-embed-text")
        self.store = QdrantVectorStore(
            url=f"http://{host}:{port}",
            collection_name=collection_name,
            embeddings=self.embeddings,
        )

    def add_document(self, content: str, title: str) -> None:
        splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
        chunks = splitter.split_text(content)
        metadatas = [{"title": title, "source": title} for _ in chunks]
        self.store.add_texts(chunks, metadatas=metadatas)

    def search(self, query: str, k: int = 5) -> List[Dict]:
        results = self.store.similarity_search(query, k=k)
        return [{"content": doc.page_content, "metadata": doc.metadata} for doc in results]