Update app.py

app.py

@@ -59,9 +59,9 @@ def generate_response(user_query, relevant_segment):
 
         # Encode the input and generate a response
         input_ids = tokenizer.encode(user_message, return_tensors='pt')
-        
-        # Create attention mask (1 for real tokens, 0 for padding tokens)
-        attention_mask = (input_ids != tokenizer.pad_token_id).long()
+
+        # Create the attention mask (1 for real tokens, 0 for padding tokens)
+        attention_mask = torch.ones(input_ids.shape, dtype=torch.long)  # Create a tensor of ones
 
         # Generate the response using the model
         output = model.generate(
@@ -77,7 +77,7 @@ def generate_response(user_query, relevant_segment):
         # Append assistant's message to messages list for context
         messages.append({"role": "assistant", "content": output_text})
         return output_text
-        
+
     except Exception as e:
         print(f"Error in generating response: {e}")
         return f"Error in generating response: {e}"