Update app.py

app.py

@@ -11,11 +11,12 @@ from langdetect import detect  # Ensure this package is installed
 
 # ✅ Environment Variables
 HF_TOKEN = os.getenv("HF_TOKEN")
-if HF_TOKEN is None:
+NASA_API_KEY = os.getenv("NASA_API_KEY")
+
+if not HF_TOKEN:
     raise ValueError("HF_TOKEN is not set. Please add it to your environment variables.")
 
-NASA_API_KEY = os.getenv("NASA_API_KEY")
-if NASA_API_KEY is None:
+if not NASA_API_KEY:
     raise ValueError("NASA_API_KEY is not set. Please add it to your environment variables.")
 
 # ✅ Set Up Streamlit
@@ -32,8 +33,8 @@ if "follow_up" not in st.session_state:
 # ✅ Model Configuration
 model_id = "mistralai/Mistral-7B-Instruct-v0.3"
 
-# ✅ Initialize Hugging Face Model
-def get_llm_hf_inference(model_id=model_id, max_new_tokens=1024, temperature=0.7):
+# ✅ Initialize Hugging Face Model with Limited Tokens
+def get_llm_hf_inference(model_id=model_id, max_new_tokens=300, temperature=0.7):  # ⬅️ Lowered token limit
     return HuggingFaceEndpoint(
         repo_id=model_id,
         max_new_tokens=max_new_tokens,
@@ -52,10 +53,8 @@ def get_nasa_apod():
     return "", "NASA Data Unavailable", "I couldn't fetch data from NASA right now."
 
 # ✅ Sentiment Analysis
-sentiment_analyzer = pipeline(
-    "sentiment-analysis",
-    model="distilbert/distilbert-base-uncased-finetuned-sst-2-english"
-)
+sentiment_analyzer = pipeline("sentiment-analysis",
+    model="distilbert/distilbert-base-uncased-finetuned-sst-2-english")
 
 def analyze_sentiment(user_text):
     result = sentiment_analyzer(user_text)[0]
@@ -67,12 +66,18 @@ def predict_action(user_text):
         return "nasa_info"
     return "general_query"
 
-# ✅ Follow-Up Question Generation
+# ✅ Ensure Every Response Has a Follow-Up Question
 def generate_follow_up(user_text):
-    prompt_text = f"Based on: '{user_text}', generate a concise, friendly follow-up."
-    hf = get_llm_hf_inference(max_new_tokens=80, temperature=0.9)
+    """Generates a follow-up question suggesting a related topic or next steps."""
+    prompt_text = (
+        f"Given the user's question: '{user_text}', generate a SHORT follow-up question "
+        "suggesting a related topic or asking if they need further help. "
+        "Example: 'Would you like to explore quantum superposition or ask about another physics concept?'"
+    )
+    hf = get_llm_hf_inference(max_new_tokens=40, temperature=0.8)
     output = hf.invoke(input=prompt_text).strip()
-    return output if output else "Would you like to explore this topic further?"
+    
+    return output if output else "Would you like to explore another related topic or ask about something else?"
 
 # ✅ Ensure English Responses
 def ensure_english(text):
@@ -84,24 +89,9 @@ def ensure_english(text):
         return "⚠️ Language detection failed. Please ask your question again."
     return text
 
-# ✅ Ensure Every Response Has a Follow-Up Question
-def generate_follow_up(user_text):
-    """Generates a follow-up question to guide the user toward related topics or next steps."""
-    prompt_text = (
-        f"Given the user's question: '{user_text}', generate a SHORT follow-up question "
-        "suggesting either a related topic or asking if they need further help. "
-        "Example: 'Would you like to explore quantum superposition or ask about another physics concept?' "
-        "Keep it concise and engaging."
-    )
-    hf = get_llm_hf_inference(max_new_tokens=40, temperature=0.8)
-    output = hf.invoke(input=prompt_text).strip()
-    
-    # Fallback in case of an empty response
-    return output if output else "Would you like to explore another related topic or ask about something else?"
-
-# ✅ Main Response Function
-def get_response(system_message, chat_history, user_text, max_new_tokens=512):
-    action = predict_action(user_text)  # 🔥 Fix: Define 'action'
+# ✅ Main Response Function (Shortened Answers + Separate Follow-Up)
+def get_response(system_message, chat_history, user_text, max_new_tokens=300):
+    action = predict_action(user_text)
 
     # ✅ Handle NASA-Specific Queries
     if action == "nasa_info":
@@ -114,17 +104,17 @@ def get_response(system_message, chat_history, user_text, max_new_tokens=512):
         return response, follow_up, chat_history, nasa_url
 
     # ✅ Set Up LLM Request
-    hf = get_llm_hf_inference(max_new_tokens=max_new_tokens, temperature=0.9)
+    hf = get_llm_hf_inference(max_new_tokens=max_new_tokens, temperature=0.7)
 
     # ✅ Format Chat History
     filtered_history = "\n".join(f"{msg['role']}: {msg['content']}" for msg in chat_history)
 
-    # ✅ Prompt Engineering
+    # ✅ Prompt Engineering with Shortened Response Limit
     prompt = PromptTemplate.from_template(
         "[INST] {system_message}\n\nCurrent Conversation:\n{chat_history}\n\n"
         "User: {user_text}.\n [/INST]\n"
-        "AI: Provide a detailed explanation with depth. "
-        "Use a conversational style, starting with 'Certainly!', 'Of course!', or 'Great question!'."
+        "AI: Provide a **concise response** (5 sentences max). "
+        "Make it conversational and engaging. Avoid excessive details."
         "🚨 Answer **only in English**."
         "\nHAL:"
     )
@@ -152,41 +142,24 @@ def get_response(system_message, chat_history, user_text, max_new_tokens=512):
 # ✅ Streamlit UI
 st.title("🚀 HAL - NASA AI Assistant")
 
-# ✅ Justify all chatbot responses
+# ✅ Justify All Chatbot Responses
 st.markdown("""
     <style>
-    .user-msg {
-        background-color: #696969;
-        color: white;
-        padding: 10px;
-        border-radius: 10px;
-        margin-bottom: 5px;
-        width: fit-content;
-        max-width: 80%;
-        text-align: justify;  /* ✅ Justify text */
-    }
-    .assistant-msg {
-        background-color: #333333;
-        color: white;
+    .user-msg, .assistant-msg {
         padding: 10px;
         border-radius: 10px;
         margin-bottom: 5px;
         width: fit-content;
         max-width: 80%;
-        text-align: justify;  /* ✅ Justify text */
-    }
-    .container {
-        display: flex;
-        flex-direction: column;
-        align-items: flex-start;
-    }
-    @media (max-width: 600px) {
-        .user-msg, .assistant-msg { font-size: 16px; max-width: 100%; }
+        text-align: justify;
     }
+    .user-msg { background-color: #696969; color: white; }
+    .assistant-msg { background-color: #333333; color: white; }
+    .container { display: flex; flex-direction: column; align-items: flex-start; }
+    @media (max-width: 600px) { .user-msg, .assistant-msg { font-size: 16px; max-width: 100%; } }
     </style>
 """, unsafe_allow_html=True)
 
-
 # ✅ Reset Chat Button
 if st.sidebar.button("Reset Chat"):
     st.session_state.chat_history = [{"role": "assistant", "content": "Hello! How can I assist you today?"}]
@@ -197,14 +170,12 @@ if st.sidebar.button("Reset Chat"):
 user_input = st.chat_input("Type your message here...")
 
 if user_input:
-    # ✅ Ensure get_response() returns a response
     response, follow_up, st.session_state.chat_history, image_url = get_response(
         system_message="You are a helpful AI assistant.",
         user_text=user_input,
         chat_history=st.session_state.chat_history
     )
 
-    # ✅ Ensure response is not empty before calling st.markdown()
     if response:
         st.markdown(f"<div class='assistant-msg'><strong>HAL:</strong> {response}</div>", unsafe_allow_html=True)
 
@@ -214,7 +185,6 @@ if user_input:
     st.session_state.follow_up = follow_up
     st.session_state.response_ready = True
 
-# ✅ Check before displaying follow-up message
 if st.session_state.response_ready and st.session_state.follow_up:
     st.markdown(f"<div class='assistant-msg'><strong>HAL:</strong> {st.session_state.follow_up}</div>", unsafe_allow_html=True)
     st.session_state.response_ready = False