Update app.py

app.py

@@ -12,8 +12,6 @@ from transformers import pipeline
 st.title("Hi, I am Chatbot Philio :mermaid:")
 st.write("I am your hotel booking assistant for today.")
 
-# tokenizer = AutoTokenizer.from_pretrained("KvrParaskevi/Hotel-Assistant-Attempt4-Llama-2-7b")
-
 tokenizer, model = demo_chat.load_model()
 
 model_identifier = "KvrParaskevi/Hotel-Assistant-Attempt4-Llama-2-7b"
@@ -22,6 +20,18 @@ task = "text-generation"  # Change this to your model's task
 # Load the model using the pipeline
 model_pipeline = pipeline(task, model=model,tokenizer=tokenizer)
 
+scrollable_div_style = """
+<style>
+.scrollable-div {
+    height: 200px;  /* Adjust the height as needed */
+    overflow-y: auto;  /* Enable vertical scrolling */
+    padding: 5px;
+    border: 1px solid #ccc;  /* Optional: adds a border around the div */
+    border-radius: 5px;  /* Optional: rounds the corners of the border */
+}
+</style>
+"""
+
 def render_chat_history(chat_history):
     #renders chat history
     for message in chat_history:
@@ -30,47 +40,47 @@ def render_chat_history(chat_history):
                 st.markdown(message["content"])
 
 #Application 
-with st.container():
-    st.markdown('<div class="scrollable-div">', unsafe_allow_html=True)
-    #Langchain memory in session cache 
-    if 'memory' not in st.session_state:
-        st.session_state.memory = demo_chat.demo_miny_memory(model)
+#Langchain memory in session cache 
+if 'memory' not in st.session_state:
+    st.session_state.memory = demo_chat.demo_miny_memory(model)
 
-    #Check if chat history exists in this session
-    if 'chat_history' not in st.session_state:
-        st.session_state.chat_history = [
-            {
-                "role": "system",
-                "content": "You are a friendly chatbot who always helps the user book a hotel room based on his/her needs."+
-                "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?"},
-        ] #Initialize chat history
-        
-    if 'model' not in st.session_state:
-        st.session_state.model = model
+system_content = "You are a friendly chatbot who always helps the user book a hotel room based on his/her needs." + 
+            "Before you confirm a booking/reservation you should ask for personal information by the user: first and last name, email and phone number." + 
+            "Based on the current social norms you wait for the user's response to your proposals."
+#Check if chat history exists in this session
+if 'chat_history' not in st.session_state:
+    st.session_state.chat_history = [
+        {
+            "role": "system",
+            "content": system_content,
+        },
+        {"role": "assistant", "content": "Hello, how can I help you today?"},
+    ] #Initialize chat history
+    
+if 'model' not in st.session_state:
+    st.session_state.model = model
+    
+st.markdown('<div class="scrollable-div">', unsafe_allow_html=True)
+render_chat_history(st.session_state.chat_history)
+
+#Set up input text field
+#input_text = st.chat_input(placeholder="Here you can chat with our hotel booking model.")
 
-    render_chat_history(st.session_state.chat_history)
+if input_text := st.chat_input(placeholder="Here you can chat with our hotel booking model."):
     
-    #Set up input text field
-    #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
 
-    if input_text := st.chat_input(placeholder="Here you can chat with our hotel booking model."):
+    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("user"):
-            st.markdown(input_text)
-        st.session_state.chat_history.append({"role" : "user", "content" : input_text}) #append message to chat history
-
-        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)
+        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)