File size: 2,112 Bytes
b269c5d |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 |
#!/usr/bin/env python3
"""
Main file for launching LLM Structured Output application in Docker
"""
import argparse
import threading
import time
from config import Config
def run_gradio():
"""Launch Gradio interface"""
from app import create_gradio_interface
print(f"🎨 Starting Gradio interface at http://{Config.HOST}:{Config.GRADIO_PORT}")
demo = create_gradio_interface()
demo.launch(
server_name=Config.HOST,
server_port=Config.GRADIO_PORT,
share=False,
debug=False # Disabled debug for production
)
def run_api():
"""Launch FastAPI server"""
import uvicorn
from api import api_app
print(f"🔌 Starting API at http://{Config.HOST}:{Config.API_PORT}")
uvicorn.run(
api_app,
host=Config.HOST,
port=Config.API_PORT,
log_level="info"
)
def run_both():
"""Launch both services simultaneously"""
print("🚀 Starting LLM Structured Output application...")
print("=" * 60)
print(f"📊 Gradio interface: http://{Config.HOST}:{Config.GRADIO_PORT}")
print(f"🔌 API: http://{Config.HOST}:{Config.API_PORT}")
print(f"📖 API documentation: http://{Config.HOST}:{Config.API_PORT}/docs")
print("=" * 60)
# Start API in separate thread
api_thread = threading.Thread(target=run_api, daemon=True)
api_thread.start()
# Small delay for API startup
time.sleep(2)
# Start Gradio in main thread
run_gradio()
def main():
"""Main function with command line arguments"""
parser = argparse.ArgumentParser(description="LLM Structured Output application")
parser.add_argument(
"--mode",
choices=["gradio", "api", "both"],
default="gradio", # Default to gradio only for HuggingFace Spaces
help="Launch mode: gradio (interface only), api (API only), both (both services)"
)
args = parser.parse_args()
if args.mode == "gradio":
run_gradio()
elif args.mode == "api":
run_api()
else:
run_both()
if __name__ == "__main__":
main()
|