Update app.py

app.py

@@ -115,14 +115,11 @@ def play_turn(human_response, loc, player, cur, custom_token, request: gr.Reques
         }
     ]
     try:
-        response = asyncio.run(
-            asyncio.to_thread(
-                client.chat_completion,
-                model=LLM_MODEL,
-                messages=messages,
-                max_tokens=500,
-                temperature=0.7
-            )
+        response = client.chat_completion(
+            model=LLM_MODEL,
+            messages=messages,
+            max_tokens=500,
+            temperature=0.7
         )
     except Exception as e:
         yield (
@@ -256,4 +253,4 @@ with gr.Blocks() as demo:
     user_input.submit(**turn_config)
 
 if __name__ == "__main__":
-    demo.queue(max_size=10).launch()
+    demo.queue(max_size=10).launch(ssr_mode=False)