Update app.py

app.py

@@ -42,7 +42,7 @@ with st.container():
             {
                 "role": "system",
                 "content": "You are a friendly chatbot who always helps the user book a hotel room based on his/her needs."+
-                "Before you make a booking you should ask for personal information: first and last name, email and phone number to confirm booking."
+                "Before you confirm a booking you should ask for user's personal information: first and last name, email and phone number to confirm booking."
                 + "Based on the current social norms you wait for the user's response to your proposals.",
             },
             {"role": "assistant", "content": "Hello, how can I help you today?"},
@@ -57,18 +57,20 @@ with st.container():
     #input_text = st.chat_input(placeholder="Here you can chat with our hotel booking model.")
 
     if input_text := st.chat_input(placeholder="Here you can chat with our hotel booking model."):
+        
         with st.chat_message("user"):
             st.markdown(input_text)
         st.session_state.chat_history.append({"role" : "user", "content" : input_text}) #append message to chat history
-        
-        #chat_response = demo_chat.demo_chain(input_text=input_text, memory=st.session_state.memory, model= chat_model)
-        #first_answer = chat_response.split("Human")[0] #Because of Predict it prints the whole conversation.Here we seperate the first answer only.
-        tokenized_chat = tokenizer.apply_chat_template(st.session_state.chat_history, tokenize=True, add_generation_prompt=True, return_tensors="pt")
-        #st.write(tokenizer.decode(tokenized_chat[0]))
-        outputs = model.generate(tokenized_chat, max_new_tokens=128) 
-        first_answer = tokenizer.decode(outputs[0][tokenized_chat.shape[1]:],skip_special_tokens=True)
-        
-        with st.chat_message("assistant"):
-            st.markdown(first_answer)
-        st.session_state.chat_history.append({"role": "assistant", "content": first_answer})    
+
+        with st.spinner("Generating response..."):
+            #chat_response = demo_chat.demo_chain(input_text=input_text, memory=st.session_state.memory, model= chat_model)
+            #first_answer = chat_response.split("Human")[0] #Because of Predict it prints the whole conversation.Here we seperate the first answer only.
+            tokenized_chat = tokenizer.apply_chat_template(st.session_state.chat_history, tokenize=True, add_generation_prompt=True, return_tensors="pt")
+            #st.write(tokenizer.decode(tokenized_chat[0]))
+            outputs = model.generate(tokenized_chat, max_new_tokens=128) 
+            first_answer = tokenizer.decode(outputs[0][tokenized_chat.shape[1]:],skip_special_tokens=True)
+            
+            with st.chat_message("assistant"):
+                st.markdown(first_answer)
+            st.session_state.chat_history.append({"role": "assistant", "content": first_answer})    
     st.markdown('</div>', unsafe_allow_html=True)