Update app.py

app.py

@@ -3,8 +3,8 @@ from rag import respond_rag_huggingface as response_hf
 
 history = []
 
-def respond(message, chat_history, temperature=0.5, max_tokens=512  ):
-    response = response_hf(message, temperature=temperature,num_predict=max_tokens)  
+def respond(message):
+    response = response_hf(message)  
     chat_history.append((message, response))
     return "", chat_history
 
@@ -12,13 +12,12 @@ with gr.Blocks() as demo:
     gr.Markdown("# Game of Thrones Q&A bot")
 
     chatbot = gr.Chatbot()
-    msg = gr.Textbox(label="Tell me something about 7 kingdoms")
+    msg = gr.Textbox(label="write something about game of thrones here...")
 
-    temp = gr.Slider(0.0, 1.0, value=0.5, label="Temperature")
-    max_tokens = gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens")
+   
 
     clear = gr.Button("Clear")
 
-    msg.submit(respond, [msg, chatbot, temp, max_tokens], [msg, chatbot])
+    msg.submit(respond, [msg], [msg, chatbot])
     clear.click(lambda: ([], ""), None, [chatbot, msg])
 demo.launch()