Update app.py

app.py

@@ -17,47 +17,47 @@ def respond(
 ):
     messages = [{"role": "system", "content": system_message}]
 
-    for user_msg, assistant_msg in history:
-        if user_msg:
-            messages.append({"role": "user", "content": user_msg})
-        if assistant_msg:
-            messages.append({"role": "assistant", "content": assistant_msg})
+    for val in history:
+        if val[0]:
+            messages.append({"role": "user", "content": val[0]})
+        if val[1]:
+            messages.append({"role": "assistant", "content": val[1]})
 
     messages.append({"role": "user", "content": message})
 
     response = ""
 
-    for event in client.chat_completion(
+    for message in client.chat_completion(
         messages,
-        max_tokens=int(max_tokens),
+        max_tokens=max_tokens,
         stream=True,
         temperature=temperature,
         top_p=top_p,
     ):
-        if event.token is not None:
-            response += event.token
-            yield response
+        token = message.choices[0].delta.content
+
+        response += token
+        yield response
 
 
 """
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
 """
-with gr.Blocks() as demo:
-    chatbot = gr.ChatInterface(
-        respond,
-        additional_inputs=[
-            gr.Textbox(value="You are a friendly Chatbot.", 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.ChatInterface(
+    respond,
+    additional_inputs=[
+        gr.Textbox(value="You are a friendly Chatbot.", 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)",
+        ),
+    ],
+)
 
 
 if __name__ == "__main__":