Update app.py

app.py

@@ -4,31 +4,48 @@ from langchain.memory import ConversationBufferMemory
 from langchain.chains import ConversationChain
 from langchain_google_genai import ChatGoogleGenerativeAI
 
-
+# Get Gemini API key from environment variable
 GEMINI_API_KEY = os.getenv("GEMINI_API_KEY")
 
+st.set_page_config(page_title="Conversational AI Data Science Tutor", page_icon="🤖")
+
+st.title("🤖 Conversational AI Data Science Tutor")
+st.write("Ask me any **Data Science** related question!")
+
 if not GEMINI_API_KEY:
     st.error("❌ GEMINI_API_KEY not found. Please add it in Hugging Face → Settings → Variables and secrets.")
 else:
-    #  Initialize Gemini LLM
-    llm = ChatGoogleGenerativeAI(model="gemini-1.5-pro", google_api_key=GEMINI_API_KEY)
+    # Initialize Gemini LLM
+    llm = ChatGoogleGenerativeAI(
+        model="gemini-1.5-pro",
+        google_api_key=GEMINI_API_KEY
+    )
 
-    #  Add memory for conversation awareness
+    # Add memory for conversation awareness
     memory = ConversationBufferMemory()
     conversation = ConversationChain(
         llm=llm,
         memory=memory,
-        verbose=True
+        verbose=False
     )
 
-    #  Streamlit App UI
-    st.set_page_config(page_title="Conversational AI Data Science Tutor", page_icon="🤖")
-    st.title("🤖 Conversational AI Data Science Tutor")
-    st.write("Ask me any **Data Science** related question!")
+    # Initialize chat history in session_state
+    if "messages" not in st.session_state:
+        st.session_state.messages = []
+
+    # Display previous messages
+    for msg in st.session_state.messages:
+        st.chat_message(msg["role"]).markdown(msg["content"])
+
+    # User input with chat-style box
+    if prompt := st.chat_input("Ask a data science question..."):
+        # Save user message
+        st.session_state.messages.append({"role": "user", "content": prompt})
+        st.chat_message("user").markdown(prompt)
 
-    # User input
-    user_input = st.text_input("You:", placeholder="Ask a data science question...")
+        # Get model response
+        response = conversation.predict(input=prompt)
 
-    if user_input:
-        response = conversation.predict(input=user_input)
-        st.write("**Tutor:**", response)
+        # Save assistant message
+        st.session_state.messages.append({"role": "assistant", "content": response})
+        st.chat_message("assistant").markdown(response)