Update app.py

app.py

@@ -922,18 +922,18 @@ def respond(
             response = execute_command(command, params)
         else:
             # Generate a regular response using OpenLlama
-        prompt = (
-            f"System: {system_message}\n"
-            f"History: {history}\n"
-            f"User: {message}\n"
-            f"Assistant:"
-        )
-        response = openllama_pipeline(
-            prompt,
-            max_length=max_tokens,
-            temperature=temperature,
-            top_p=top_p,
-        )[0]["generated_text"]
+            prompt = (
+                f"System: {system_message}\n"
+                f"History: {history}\n"
+                f"User: {message}\n"
+                f"Assistant:"
+            )
+            response = openllama_pipeline(
+                prompt,
+                max_length=max_tokens,
+                temperature=temperature,
+                top_p=top_p,
+            )[0]["generated_text"]
 
 
             # Extract the assistant's reply