Update app.py

app.py

@@ -3,24 +3,23 @@ from rag import respond_rag_ollama  # Your custom RAG function using Ollama
 
 history = []
 
-def respond(message, chat_history, temperature=0.5, max_tokens=512,  top_p=0.3):
-    response = respond_rag_ollama(message, temperature=temperature,num_predict=max_tokens,top_p=top_p)  # send only message & temperature
+def respond(message, chat_history, temperature=0.5, max_tokens=512  ):
+    response = respond_rag_ollama(message, temperature=temperature,num_predict=max_tokens)  # send only message & temperature
     chat_history.append((message, response))
     return "", chat_history
 
 with gr.Blocks() as demo:
-    gr.Markdown("# RAG with Ollama Chatbot")
+    gr.Markdown("# Game of Thrones Q&A bot")
 
     chatbot = gr.Chatbot()
-    msg = gr.Textbox(label="Your Message")
+    msg = gr.Textbox(label="Tell me something about 7 kingdoms")
+
     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")
-        
-    top_p=gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p")
+    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,top_p], [msg, chatbot])
+    msg.submit(respond, [msg, chatbot, temp, max_tokens], [msg, chatbot])
     clear.click(lambda: ([], ""), None, [chatbot, msg])
 
 demo.launch()