Update app.py

app.py

@@ -68,7 +68,6 @@ 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)
 
@@ -95,8 +94,12 @@ def remove_duplicates(text):
 
 @lru_cache(maxsize=128)
 def generate_model_response(model, inputs):
-    response = model(inputs, max_tokens=150)
-    return remove_duplicates(response['choices'][0]['text'])
+    try:
+        response = model(inputs, max_tokens=150)
+        return remove_duplicates(response['choices'][0]['text'])
+    except Exception as e:
+        print(f"Error generating response from model: {e}")
+        return f"Error: Could not generate a response.  Details: {e}"
 
 async def process_message(message):
     inputs = normalize_input(message)
@@ -112,8 +115,6 @@ async def process_message(message):
             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