Model works with updated server_name and ssr_mode false, and added client x-ip-token to fix zeroGPU timeout but now am at back of GPU queue

app.py

@@ -49,6 +49,8 @@ References
 """
 
 import spaces
+from gradio_client import Client
+from gradio.routes import Request as gr_Request
 import subprocess
 import sys
 import json
@@ -138,8 +140,7 @@ from quantum_utils import run_vqe_simulation
 from visualization import plot_convergence, create_molecule_viewer, format_molecule_params
 from gradio_molgallery3d import MolGallery3D
 
-from gradio_client import Client
-client = Client("your-space", headers={"X-IP-Token": request.headers['x-ip-token']})
+#Todo later add this working client stuff to fix timeouts client = Client("your-space", headers={"X-IP-Token": request.headers['x-ip-token']})
 
 # Add immediate logging
 print("Imported all modules successfully", file=sys.stderr, flush=True)
@@ -204,6 +205,18 @@ def update_simulation(molecule_choice: str, scale_factor: float) -> tuple:
 def create_interface():
     """Create the Gradio interface for the VQE demo."""
     
+    def set_client_for_session(request: gr.Request):
+        """Initialize client with user's IP token to handle rate limiting."""
+        # from https://www.gradio.app/docs/python-client/using-zero-gpu-spaces
+        try:
+            x_ip_token = request.headers['x-ip-token'] # 
+            return Client("A19grey/Cuda-Quantum-Molecular-Playground", headers={"x-ip-token": x_ip_token})
+        except Exception as e:
+            logger.error(f"Error setting client: {e}")
+            return None
+      
+    
+
     # Load available molecules
     molecules = load_molecules()
     if not molecules:
@@ -233,6 +246,8 @@ def create_interface():
         *Inspired by the [NVIDIA CUDA-Q VQE Example](https://nvidia.github.io/cuda-quantum/latest/applications/python/vqe_advanced.html)*
         """)
         
+        client = gr.State() # added this to fix timeouts - https://www.gradio.app/docs/python-client/using-zero-gpu-spaces
+
         state = gr.State({})  # Store current molecule data
         
         # Top section: 3 columns
@@ -499,11 +514,19 @@ def create_interface():
             inputs=[molecule_choice, scale_factor],
             outputs=[simulation_results, convergence_plot]
         )
-    
+
+        # Add load event to set client
+        demo.load(set_client_for_session, None, client)
+
     return demo
 
 if __name__ == "__main__":
     print("Starting VQE Demo Application")
     demo = create_interface()
-    print("Gonna demo and launch this thing")
-    demo.launch(server_name="0.0.0.0", server_port=7860, ssr=False) 
+    print("Launching demo with custom headers support")
+    demo.launch(
+        server_name="0.0.0.0", 
+        server_port=7860,
+        ssr_mode=False,
+        show_api=True  # Enable API endpoints
+    )