Update app.py

app.py

@@ -40,11 +40,10 @@ def generate(
 
     stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
 
-    output = ""
+    output_text = ""
     for response in stream:
-        output += response.token.text
-
-    yield output
+        output_text += response.token.text
+        yield output_text, history  # Yield the updated output_text and the updated history
 
 additional_inputs = [
     gr.Textbox(label="System Prompt", max_lines=1, interactive=True),