Update app.py

app.py

@@ -24,6 +24,7 @@ def load_model():
     return tokenizer, model
 
 tokenizer, model = load_model()
+
 # Function to generate chatbot response using the provided template
 def get_completion(query: str, model, tokenizer) -> str:
     device = "cuda:0" if torch.cuda.is_available() else "cpu" #Use cuda if available.
@@ -52,13 +53,11 @@ def get_completion(query: str, model, tokenizer) -> str:
     return model_response
 
 # Streamlit app
-st.title("Customer Care Chatbot")
+st.title("Gemma-2b-it Support Chatbot")
 
 # Initialize chat history
 if "messages" not in st.session_state:
     st.session_state.messages = []
-if "chat_history" not in st.session_state:
-    st.session_state.chat_history = ""
 
 # Display chat messages from history on app rerun
 for message in st.session_state.messages:
@@ -66,7 +65,7 @@ for message in st.session_state.messages:
         st.markdown(message["content"])
 
 # Accept user input
-if prompt := st.chat_input("What is up?"):
+if prompt := st.chat_input("How can I help you?"):
     # Add user message to chat history
     st.session_state.messages.append({"role": "user", "content": prompt})
     # Display user message in chat message container
@@ -77,7 +76,7 @@ if prompt := st.chat_input("What is up?"):
     with st.chat_message("assistant"):
         message_placeholder = st.empty()
         full_response = ""
-        response = generate_response(prompt, st.session_state.chat_history)
+        response = get_completion(prompt, model, tokenizer)
 
         # Simulate stream of responses with milliseconds delay
         import time
@@ -89,6 +88,4 @@ if prompt := st.chat_input("What is up?"):
         message_placeholder.markdown(full_response)
 
     # Add assistant response to chat history
-    st.session_state.messages.append({"role": "assistant", "content": full_response})
-    #update the chat history.
-    st.session_state.chat_history += prompt + response
+    st.session_state.messages.append({"role": "assistant", "content": full_response})