Update app.py

app.py

@@ -45,4 +45,25 @@ def respond(message, history, system_message, max_tokens, temperature, top_p):
         stream=True,
     ):
         token = ""
-        if chunk.choices and
+        if chunk.choices and chunk.choices[0].delta and chunk.choices[0].delta.content:
+            token = chunk.choices[0].delta.content
+        response += token
+        yield response
+
+
+chatbot = gr.ChatInterface(
+    respond,
+    type="messages",
+    additional_inputs=[
+        gr.Textbox(value=SYSTEM_PROMPT, label="System message"),
+        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
+        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
+        gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)"),
+    ],
+)
+
+demo = gr.Blocks()
+with demo:
+    chatbot.render()
+
+app = demo