"""
RAG vector store using Qdrant and Ollama embeddings.
"""

from pathlib import Path
from typing import List

import chromadb  # kept for compatibility if needed
from langchain.embeddings.ollama import OllamaEmbeddings
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.schema.document import Document
from langchain.vectorstores import Qdrant

CHROMA_DIR = "./chroma_db"
EMBED_MODEL = "nomic-embed-text"


def create_vectorstore(persist_directory: str = CHROMA_DIR):
    """Create or load a Qdrant vector store.

    Parameters
    ----------
    persist_directory:
        Directory where the Qdrant database is stored. If it does not exist, it will be created.
    """
    embeddings = OllamaEmbeddings(model=EMBED_MODEL)
    # Qdrant can use a local file store via `path` argument
    client = Qdrant(persist_directory=persist_directory, embedding_function=embeddings)
    return client


def load_documents(directory: str, vectorstore) -> None:
    """Load all .txt and .md files from *directory*, chunk them and add to the vector store.

    The function does not return anything; it mutates the provided collection.
    """
    text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
    docs: List[Document] = []
    for path in Path(directory).rglob("*.txt"):
        content = path.read_text(encoding="utf-8")
        docs.extend(text_splitter.create_documents([content], metadata={"source": str(path)}))
    for path in Path(directory).rglob("*.md"):
        content = path.read_text(encoding="utf-8")
        docs.extend(text_splitter.create_documents([content], metadata={"source": str(path)}))

    if docs:
        # Qdrant expects texts and metadatas lists
        vectorstore.add_texts(
            texts=[doc.page_content for doc in docs],
            metadatas=[doc.metadata for doc in docs],
        )