setup_project.py

"""
RAG System Setup and Initialization Script.

Run this script to set up the project environment:
    python setup_project.py
"""

import os
import sys
from pathlib import Path

def check_env_file():
    """Check if .env file exists, create from template if needed."""
    env_path = Path(".env")
    env_template_path = Path(".env.template")
    
    if env_path.exists():
        print("✅ .env file already exists")
        return True
    
    if not env_template_path.exists():
        print("❌ .env.template file not found")
        return False
    
    print("📝 Creating .env file from template...")
    env_content = env_template_path.read_text()
    env_path.write_text(env_content)
    print("✅ .env file created from template")
    print("⚠️  Please edit .env and add your API keys before running the application")
    return True


def check_dependencies():
    """Check if required packages are installed."""
    try:
        import langchain
        import pinecone
        import google.generativeai
        import streamlit
        print("✅ All dependencies are installed")
        return True
    except ImportError as e:
        print(f"❌ Missing dependency: {e}")
        print("\nInstall dependencies with:")
        print("    pip install -r requirements.txt")
        return False


def create_sample_docs_directory():
    """Create sample_docs directory for testing."""
    sample_dir = Path("sample_docs")
    if not sample_dir.exists():
        sample_dir.mkdir()
        print("✅ Created sample_docs directory")
        
        # Create a sample document
        sample_file = sample_dir / "sample.txt"
        sample_content = """This is a sample document for testing the RAG system.

The RAG (Retrieval-Augmented Generation) system combines document retrieval with 
language model generation to provide accurate, context-grounded answers.

Key features of this system:
1. Document Upload - Support for .txt, .pdf, and .docx files
2. Intelligent Chunking - Automatic text splitting for better context
3. Vector Embeddings - Using Google Gemini for semantic understanding
4. Pinecone Storage - Scalable vector database
5. Conversational AI - Google Gemini LLM with RAG

You can upload your own documents and ask questions about them.
The system will search through your documents and provide answers
based only on the content you upload, preventing hallucination."""
        
        sample_file.write_text(sample_content)
        print("✅ Created sample.txt in sample_docs/")
    else:
        print("✅ sample_docs directory already exists")


def main():
    """Main setup function."""
    print("\n" + "="*50)
    print("RAG System - Project Setup")
    print("="*50 + "\n")
    
    # Check environment file
    if not check_env_file():
        print("\n⚠️  Setup incomplete - please create .env file manually")
        return False
    
    print()
    
    # Check dependencies
    if not check_dependencies():
        print("\n⚠️  Setup incomplete - please install dependencies")
        return False
    
    print()
    
    # Create sample docs directory
    create_sample_docs_directory()
    
    print("\n" + "="*50)
    print("✅ Setup complete!")
    print("="*50)
    print("\nNext steps:")
    print("1. Edit .env file with your API keys:")
    print("   - GOOGLE_API_KEY")
    print("   - PINECONE_API_KEY")
    print("   - PINECONE_ENVIRONMENT")
    print("\n2. Initialize Pinecone index:")
    print("   python main.py init")
    print("\n3. Start the Streamlit app:")
    print("   streamlit run app.py")
    print("\nOr use the CLI to process documents:")
    print("   python main.py process sample_docs/")
    print("\n" + "="*50 + "\n")
    
    return True


if __name__ == "__main__":
    success = main()
    sys.exit(0 if success else 1)