course_search/app/run.py

import sys
import os
from pathlib import Path
import subprocess
import logging

project_root = Path(__file__).parent.parent.parent

if str(project_root) not in sys.path:
    sys.path.append(str(project_root))
        
from course_search.search_system.data_pipeline import DataPipeline
from course_search.search_system.rag_system import RAGSystem

# Setup logging
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)

def setup_paths():
    """Setup necessary paths and directories"""
    project_root = Path(__file__).parent.parent.parent
    
    if str(project_root) not in sys.path:
        sys.path.append(str(project_root))
    
    data_dir = project_root / 'data'
    data_dir.mkdir(exist_ok=True)
    
    return project_root, data_dir

def main():
    try:
        # Setup paths
        project_root, data_dir = setup_paths()
        
        # Create cache directory
        cache_dir = data_dir / 'cache'
        cache_dir.mkdir(exist_ok=True)
        
        # Run data pipeline
        logger.info("Running data pipeline...")
        pipeline = DataPipeline()
        df = pipeline.run_pipeline(
            save_path=str(data_dir / 'courses.pkl'),
            force_scrape=False  # Set to True to force new scraping
        )
        
        # Initialize RAG system with caching
        rag_system = RAGSystem()
        rag_system.load_and_process_data(df, cache_dir=cache_dir)
        
        # Run Gradio app
        logger.info("Starting Gradio app...")
        gradio_path = Path(__file__).parent / 'gradio_app.py'
        
        if not gradio_path.exists():
            raise FileNotFoundError(f"Gradio app not found at: {gradio_path}")
        
        # Change to project root directory before running
        os.chdir(str(project_root))
        
        # Run Gradio with proper Python path
        env = os.environ.copy()
        env['PYTHONPATH'] = str(project_root)
        
        subprocess.run(
            ['python', str(gradio_path)],
            env=env,
            check=True
        )
        
    except Exception as e:
        logger.error(f"Error running application: {str(e)}")
        raise

if __name__ == "__main__":
    main()