Default server host to localhost for improved security

Set the default server host to '127.0.0.1' in server configuration and update all relevant server start calls to use this value. Updated README with a security note explaining the default binding and instructions for allowing external connections. This change helps prevent unintended external access by default.

Author: codelion

README.md

@@ -216,15 +216,15 @@ You can then run the optillm proxy as follows.
 ```bash
 python optillm.py
 2024-09-06 07:57:14,191 - INFO - Starting server with approach: auto
-2024-09-06 07:57:14,191 - INFO - Server configuration: {'approach': 'auto', 'mcts_simulations': 2, 'mcts_exploration': 0.2, 'mcts_depth': 1, 'best_of_n': 3, 'model': 'gpt-4o-mini', 'rstar_max_depth': 3, 'rstar_num_rollouts': 5, 'rstar_c': 1.4, 'base_url': ''}
+2024-09-06 07:57:14,191 - INFO - Server configuration: {'approach': 'auto', 'mcts_simulations': 2, 'mcts_exploration': 0.2, 'mcts_depth': 1, 'best_of_n': 3, 'model': 'gpt-4o-mini', 'rstar_max_depth': 3, 'rstar_num_rollouts': 5, 'rstar_c': 1.4, 'base_url': '', 'host': '127.0.0.1'}
  * Serving Flask app 'optillm'
  * Debug mode: off
 2024-09-06 07:57:14,212 - INFO - WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead.
- * Running on all addresses (0.0.0.0)
  * Running on http://127.0.0.1:8000
- * Running on http://192.168.10.48:8000
 2024-09-06 07:57:14,212 - INFO - Press CTRL+C to quit
 ```
+
+> **Security Note**: By default, optillm binds to `127.0.0.1` (localhost only) for security. To allow external connections (e.g., for Docker or remote access), use `--host 0.0.0.0`. Only do this on trusted networks or with proper authentication configured via `--optillm-api-key`.
 ## Usage
 
 Once the proxy is running, you can use it as a drop in replacement for an OpenAI client by setting the `base_url` as `http://localhost:8000/v1`.

optillm/server.py

@@ -189,6 +189,7 @@ def count_reasoning_tokens(text: str, tokenizer=None) -> int:
     'base_url': '',
     'optillm_api_key': '',
     'return_full_response': False,
+    'host': '127.0.0.1',  # Default to localhost for security; use 0.0.0.0 to allow external connections
     'port': 8000,
     'log': 'info',
     'ssl_verify': True,
@@ -1264,7 +1265,8 @@ def process_batch_requests(batch_requests):
             import gradio as gr
             # Start server in a separate thread
             import threading
-            server_thread = threading.Thread(target=app.run, kwargs={'host': '0.0.0.0', 'port': port})
+            host = server_config['host']
+            server_thread = threading.Thread(target=app.run, kwargs={'host': host, 'port': port})
             server_thread.daemon = True
             server_thread.start()
 
@@ -1311,12 +1313,12 @@ def chat_with_optillm(message, history):
                 description=f"Connected to OptILLM proxy at {base_url}"
             )
             demo.queue()  # Enable queue to handle long operations properly
-            demo.launch(server_name="0.0.0.0", share=False)
+            demo.launch(server_name=host, share=False)
         except ImportError:
             logger.error("Gradio is required for GUI. Install it with: pip install gradio")
             return
 
-    app.run(host='0.0.0.0', port=port)
+    app.run(host=server_config['host'], port=port)
 
 if __name__ == "__main__":
     main()