fix: update server configuration and asset handling

- Switch to Gradio's launch method with proper configuration
- Disable unnecessary asset loading
- Configure proper queue and threading
- Improve interface initialization

app.py

@@ -194,7 +194,9 @@ class ChatInterface:
     def create_interface(self) -> gr.Blocks:
         """Create the Gradio interface."""
         with gr.Blocks(
-            title="Advanced Agentic System"
+            title="Advanced Agentic System",
+            css=None,  # Disable custom CSS
+            theme=gr.themes.Soft(),  # Use built-in theme
         ) as interface:
             gr.Markdown("""
                 # 🤖 Advanced Agentic System Chat Interface
@@ -216,16 +218,20 @@ class ChatInterface:
             """)
             
             chatbot = gr.Chatbot(
-                show_label=False,
+                value=[],  # Initialize with empty list
+                type="messages",  # Use OpenAI-style message format
                 height=500,
-                type="messages"  # Use OpenAI-style message format
+                show_label=False,
+                render_markdown=True,
+                avatar_images=None,  # Disable avatars to prevent asset loading issues
             )
             
             with gr.Row():
                 msg = gr.Textbox(
                     show_label=False,
                     placeholder="Chat with the Agentic System...",
-                    container=False
+                    container=False,
+                    autofocus=True,
                 )
                 submit = gr.Button("Send 🚀")
             
@@ -498,11 +504,18 @@ interface = create_chat_interface()
 app = gr.mount_gradio_app(app, interface, path="/")
 
 if __name__ == "__main__":
-    # Run with uvicorn when called directly
-    uvicorn.run(
-        "app:app",
-        host="0.0.0.0",
-        port=7860,
-        reload=True,
-        workers=4
+    chat_interface = ChatInterface()
+    interface = chat_interface.create_interface()
+    interface.queue()
+    interface.launch(
+        server_name="0.0.0.0",
+        server_port=7860,
+        share=True,
+        debug=True,
+        enable_queue=True,
+        show_error=True,
+        favicon_path=None,  # Disable favicon to prevent 404
+        show_api=False,  # Disable API docs to reduce asset loading
+        reload=False,  # Disable auto-reload to use workers properly
+        max_threads=40,
     )