app/start.py

#!/usr/bin/env python3
"""
Startup script that builds the index if data files don't exist,
then starts the FastAPI application.
"""
import os
import subprocess
import sys
import logging

# Configure logging
logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
logger = logging.getLogger(__name__)

def check_data_files():
    """Check if all required data files exist"""
    required_files = [
        "app/data/faiss.index",
        "app/data/movies.npy", 
        "app/data/id_map.json",
        "app/data/movie_metadata.json"
    ]
    
    missing_files = []
    for file_path in required_files:
        if not os.path.exists(file_path):
            missing_files.append(file_path)
    
    return missing_files

def build_index():
    """Run the build_index script"""
    logger.info("🔧 Building movie index and data files...")
    try:
        # Run build_index with reduced dataset for faster startup on HF
        result = subprocess.run([
            sys.executable, "-m", "app.build_index", 
            "--max-pages", "5"  # Reduced for faster startup
        ], check=True, capture_output=True, text=True)
        
        logger.info("✅ Index built successfully!")
        logger.info(result.stdout)
        
    except subprocess.CalledProcessError as e:
        logger.error("❌ Failed to build index:")
        logger.error(e.stderr)
        raise

def start_api():
    """Start the FastAPI application"""
    logger.info("🚀 Starting FastAPI application...")
    os.execv(sys.executable, [
        sys.executable, "-m", "uvicorn", 
        "app.main:app", 
        "--host", "0.0.0.0", 
        "--port", "7860"
    ])

if __name__ == "__main__":
    logger.info("🎬 Karl Movie Vector Backend - Starting up...")
    
    # Check if data files exist
    missing_files = check_data_files()
    
    if missing_files:
        logger.info(f"📁 Missing data files: {missing_files}")
        logger.info("🔄 This is the first startup - building index...")
        
        # Build the index
        build_index()
        
        # Verify files were created
        missing_after_build = check_data_files()
        if missing_after_build:
            logger.error(f"❌ Still missing files after build: {missing_after_build}")
            sys.exit(1)
    else:
        logger.info("✅ All data files present, skipping index build")
    
    # Start the API
    start_api()