import os
import sys
from pathlib import Path

from dotenv import load_dotenv

from vectorstore import create_vectorstore, load_documents, collection_exists
from agent import create_agent

def main():
    # Load environment variables
    load_dotenv()

    # Configuration
    qdrant_path = os.getenv("QDRANT_PATH", "./qdrant_db")
    embedding_model = os.getenv("EMBEDDING_MODEL", "nomic-embed-text")
    llm_model = os.getenv("LLM_MODEL", "llama3")
    tavily_api_key = os.getenv("TAVILY_API_KEY")
    if not tavily_api_key:
        print("Error: TAVILY_API_KEY not set in .env")
        sys.exit(1)

    # Create vector store
    vectorstore = create_vectorstore(
        persist_directory=qdrant_path,
        collection_name="documents",
        embedding_model=embedding_model,
    )

    # Load documents if collection is empty
    if not collection_exists(vectorstore):
        print("Loading documents into Qdrant...")
        docs_dir = Path("documents")
        if not docs_dir.exists():
            print(f"Documents directory '{docs_dir}' not found.")
            sys.exit(1)
        load_documents(str(docs_dir), vectorstore)
        print("Documents loaded.")
    else:
        print("Qdrant collection already exists. Skipping document load.")

    # Create agent
    agent = create_agent(vectorstore, tavily_api_key, llm_model=llm_model)

    print("Chat agent ready. Type 'exit' to quit.")
    while True:
        try:
            user_input = input("\nYou: ")
        except (KeyboardInterrupt, EOFError):
            print("\nExiting.")
            break

        if user_input.strip().lower() in {"exit", "quit"}:
            print("Goodbye!")
            break

        # Run agent
        try:
            response = agent.run(user_input)
            print(f"\nAssistant: {response}")
        except Exception as e:
            print(f"Error: {e}")

if __name__ == "__main__":
    main()