Update app.py

app.py

@@ -37,7 +37,7 @@ def respond(
         chat.append({"role": "assistant", "content": assistant})
     chat.append({"role": "user", "content": message})
 
-    prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+    prompt = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)
     #inputs = tokenizer.encode(prompt, add_special_tokens=False, return_tensors="pt").to(model.device)
 
     streamer = TextIteratorStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
@@ -67,6 +67,7 @@ def respond(
     )
 
     response = outputs[0]["generated_text"]
+    return response
 
 demo = gr.ChatInterface(
     respond,