Update app.py

app.py

@@ -242,8 +242,8 @@ for downstream processing by Large Language Models (LLMs).
 if __name__ == "__main__":
     # Configure for concurrent processing with streaming support
     demo.queue(
-        max_size=20,  # Maximum queue size
-        concurrency_count=4,  # Allow 4 concurrent requests
+        max_size=1000,  # Maximum queue size
+        default_concurrency_limit=4,  # Allow 4 concurrent requests
         status_update_rate=0.1,  # Update status every 100ms for better streaming experience
     ).launch(
         server_name="0.0.0.0",