Update app.py

app.py

@@ -28,8 +28,6 @@ st.set_page_config(page_title="HAL - NASA ChatBot", page_icon="🚀")
 # ✅ Initialize Session State Variables (Ensuring Chat History Persists)
 if "chat_history" not in st.session_state:
     st.session_state.chat_history = [{"role": "assistant", "content": "Hello! How can I assist you today?"}]
-if "response_ready" not in st.session_state:
-    st.session_state.response_ready = False
 
 # ✅ Initialize Hugging Face Model (Explicitly Set to CPU/GPU)
 def get_llm_hf_inference(model_id="meta-llama/Llama-2-7b-chat-hf", max_new_tokens=800, temperature=0.3):
@@ -58,7 +56,7 @@ def get_response(system_message, chat_history, user_text, max_new_tokens=800):
     filtered_history = "\n".join(
         f"{msg['role'].capitalize()}: {msg['content']}"
         for msg in chat_history[-5:]  # ✅ Only keep the last 5 exchanges to prevent overflow
-)
+    )
  
     prompt = PromptTemplate.from_template(
         "[INST] You are a highly knowledgeable AI assistant. Answer concisely, avoid repetition, and structure responses well."
@@ -66,7 +64,6 @@ def get_response(system_message, chat_history, user_text, max_new_tokens=800):
         "\nLATEST USER INPUT:\nUser: {user_text}\n"
         "\n[END CONTEXT]\n"
         "Assistant:"
-
     )
 
     # ✅ Invoke Hugging Face Model
@@ -74,21 +71,20 @@ def get_response(system_message, chat_history, user_text, max_new_tokens=800):
     chat = prompt | hf.bind(skip_prompt=True) | StrOutputParser(output_key='content')
 
     response = chat.invoke(input=dict(system_message=system_message, user_text=user_text, chat_history=filtered_history))
+    
+    # Clean up the response - remove any "HAL:" prefix if present
     response = response.split("HAL:")[-1].strip() if "HAL:" in response else response.strip()
-
     response = ensure_english(response)
 
     if not response:
         response = "I'm sorry, but I couldn't generate a response. Can you rephrase your question?"
 
-    # ✅ Preserve conversation history
+    # ✅ Update conversation history
     chat_history.append({'role': 'user', 'content': user_text})
     chat_history.append({'role': 'assistant', 'content': response})
 
     # ✅ Keep only last 10 exchanges to prevent unnecessary repetition
-    st.session_state.chat_history = chat_history[-10:]
-
-    return response, st.session_state.chat_history
+    return response, chat_history[-10:]
 
 # ✅ Streamlit UI
 st.title("🚀 HAL - NASA AI Assistant")
@@ -115,22 +111,18 @@ st.markdown("""
 user_input = st.chat_input("Type your message here...")
 
 if user_input:
+    # Get response and update chat history
     response, st.session_state.chat_history = get_response(
         system_message="You are a helpful AI assistant.",
         user_text=user_input,
         chat_history=st.session_state.chat_history
     )
 
-    if response:
-        st.markdown(f"<div class='assistant-msg'><strong>HAL:</strong> {response}</div>", unsafe_allow_html=True)
-
-# ✅ Display chat history
+# ✅ Display chat history (ONLY display from history, not separately)
 st.markdown("<div class='container'>", unsafe_allow_html=True)
 for message in st.session_state.chat_history:
     if message["role"] == "user":
         st.markdown(f"<div class='user-msg'><strong>You:</strong> {message['content']}</div>", unsafe_allow_html=True)
     else:
         st.markdown(f"<div class='assistant-msg'><strong>HAL:</strong> {message['content']}</div>", unsafe_allow_html=True)
-st.markdown("</div>", unsafe_allow_html=True)
-
-
+st.markdown("</div>", unsafe_allow_html=True)