app.py

#!/usr/bin/env python
"""
Main entry point for Hugging Face Spaces deployment.
This file starts the Streamlit UI when deployed to Hugging Face Spaces.
"""
import subprocess
import os
import sys
import time
import random
import logging

# Configure logging
logging.basicConfig(
    level=logging.INFO,
    format="%(asctime)s [%(levelname)s] %(message)s",
    handlers=[
        logging.StreamHandler()
    ]
)

logger = logging.getLogger(__name__)

# Make sure the app directory is in the path
# Add the current directory to the path so that 'app' is recognized as a package
sys.path.append(os.path.dirname(os.path.abspath(__file__)))
# Also add the parent directory to path to ensure imports work properly
sys.path.append(os.path.abspath('.'))

# Create necessary directories
logger.info("Creating necessary directories...")
os.makedirs('data/documents', exist_ok=True)
os.makedirs('data/vector_db', exist_ok=True)

# Create multiple vector database paths to help with concurrent access
for i in range(1, 4):
    path = f'data/vector_db_{i}'
    os.makedirs(path, exist_ok=True)
    # Ensure directories have proper permissions
    try:
        os.chmod(path, 0o777)
    except Exception as e:
        logger.warning(f"Could not set permissions for {path}: {e}")

# Set environment variable for Python path
os.environ['PYTHONPATH'] = os.path.abspath('.')

# Add a small delay to ensure directory creation is complete
logger.info("Starting application...")
time.sleep(1)

# Run the Streamlit app with specific port to match huggingface-space.yml
# Add server.maxMessageSize to handle larger files and messages
cmd = [
    "streamlit", "run", "app/ui/streamlit_app.py", 
    "--server.port=7860", 
    "--server.address=0.0.0.0",
    "--server.maxUploadSize=10",
    "--server.maxMessageSize=200"
]

logger.info(f"Running command: {' '.join(cmd)}")
subprocess.run(cmd)