Update app.py

app.py

@@ -52,7 +52,6 @@ class ModelManager:
             for future in tqdm(as_completed(futures), total=len(global_data['model_configs']), desc="Loading models complete"):
                 future.result()
 
-
     def _load_model(self, model_config):
         model_name = model_config['name']
         cache_file = os.path.join(self.model_cache_dir, f"{model_name}.pkl")
@@ -69,6 +68,7 @@ class ModelManager:
                 print(f"Error loading model {model_name}: {e}")
                 self.models[model_name] = None
 
+
     def get_model(self, model_name):
         return self.models.get(model_name)
 
@@ -107,15 +107,18 @@ async def process_message(message):
 
     with ThreadPoolExecutor(max_workers=len(global_data['model_configs'])) as executor:
         futures = [executor.submit(generate_model_response, model_manager.get_model(config['name']), inputs) for config in global_data['model_configs'] if model_manager.get_model(config['name'])]
+
         for i, future in enumerate(tqdm(as_completed(futures), total=len([f for f in futures]), desc="Generating responses")):
-             model_name = global_data['model_configs'][i]['name']
-             responses[model_name] = future.result()
+            model_name = global_data['model_configs'][i]['name']
+            responses[model_name] = future.result()
+
 
 
     formatted_response = "\n\n".join([f"**{model}:**\n{response}" for model, response in responses.items()])
     response_cache[inputs] = formatted_response
     return formatted_response
 
+
 @app.post("/generate_multimodel")
 async def api_generate_multimodel(request: Request):
     try:
@@ -131,6 +134,7 @@ async def api_generate_multimodel(request: Request):
         return JSONResponse({"error": str(e)}, status_code=500)
 
 
+
 iface = gr.Interface(
     fn=process_message,
     inputs=gr.Textbox(lines=2, placeholder="Enter your message here..."),