Update app.py

app.py

@@ -8,16 +8,7 @@ from langchain_core.prompts import PromptTemplate
 from langchain_core.output_parsers import StrOutputParser
 from transformers import pipeline
 
-# Use environment variables for keys
-HF_TOKEN = os.getenv("HF_TOKEN")
-if HF_TOKEN is None:
-    raise ValueError("HF_TOKEN environment variable not set. Please set it in your Hugging Face Space settings.")
-
-NASA_API_KEY = os.getenv("NASA_API_KEY")
-if NASA_API_KEY is None:
-    raise ValueError("NASA_API_KEY environment variable not set. Please set it in your Hugging Face Space settings.")
-
-# Set up Streamlit UI
+# Must be the first Streamlit command!
 st.set_page_config(page_title="HAL - NASA ChatBot", page_icon="🚀")
 
 # --- Initialize Session State Variables ---
@@ -41,12 +32,12 @@ def get_llm_hf_inference(model_id=model_id, max_new_tokens=128, temperature=0.7)
         repo_id=model_id,
         max_new_tokens=max_new_tokens,
         temperature=temperature,
-        token=HF_TOKEN,
+        token=os.getenv("HF_TOKEN"),
         task="text-generation"
     )
 
 def get_nasa_apod():
-    url = f"https://api.nasa.gov/planetary/apod?api_key={NASA_API_KEY}"
+    url = f"https://api.nasa.gov/planetary/apod?api_key={os.getenv('NASA_API_KEY')}"
     response = requests.get(url)
     if response.status_code == 200:
         data = response.json()
@@ -59,38 +50,37 @@ def analyze_sentiment(user_text):
     return result['label']
 
 def predict_action(user_text):
-    if "NASA" in user_text or "space" in user_text:
+    if "nasa" in user_text.lower() or "space" in user_text.lower():
         return "nasa_info"
     return "general_query"
 
 def generate_follow_up(user_text):
     """
-    Generates two variant follow-up questions and randomly selects one.
-    It also cleans up any unwanted quotation marks or extra meta commentary.
+    Generates one concise, friendly follow-up question related to the user's input.
+    The prompt instructs the model to output a single question without extra commentary.
     """
     prompt_text = (
-        f"Based on the user's question: '{user_text}', generate two concise, friendly follow-up questions "
-        "that invite further discussion. For example, one might be 'Would you like to know more about the six types of quarks?' "
-        "and another might be 'Would you like to explore another aspect of quantum physics?' Do not include extra commentary."
+        f"Generate one concise, friendly follow-up question related to the topic of the user's question: '{user_text}'. "
+        "The output should be only the question, with no extra text."
     )
-    hf = get_llm_hf_inference(max_new_tokens=80, temperature=0.9)
+    hf = get_llm_hf_inference(max_new_tokens=60, temperature=0.9)
     output = hf.invoke(input=prompt_text).strip()
-    variants = re.split(r"\n|[;]+", output)
-    cleaned = [v.strip(' "\'') for v in variants if v.strip()]
-    if not cleaned:
-        cleaned = ["Would you like to explore this topic further?"]
-    return random.choice(cleaned)
+    # If the output is too short or empty, return a default fallback question.
+    if len(output) < 10:
+        return "Would you like to explore this topic further?"
+    # Clean the output from any extraneous quotes.
+    follow_up = output.strip(' "\'')
+    return follow_up
 
 def get_response(system_message, chat_history, user_text, max_new_tokens=256):
     """
-    Generates HAL's answer with depth and a follow-up question.
-    The prompt instructs the model to provide a detailed explanation and then generate a follow-up.
-    If the answer comes back empty, a fallback answer is used.
+    Generates HAL's response with a detailed explanation and a follow-up question.
+    Style instructions (e.g. "in the voice of a physicist") are appended if present.
     """
     sentiment = analyze_sentiment(user_text)
     action = predict_action(user_text)
     
-    # Extract style instruction if present
+    # Extract style instruction if present.
     style_instruction = ""
     lower_text = user_text.lower()
     if "in the voice of" in lower_text or "speaking as" in lower_text:
@@ -117,27 +107,21 @@ def get_response(system_message, chat_history, user_text, max_new_tokens=256):
     
     style_clause = style_instruction if style_instruction else ""
     
-    # Instruct the model to generate a detailed, in-depth answer.
     prompt = PromptTemplate.from_template(
         (
             "[INST] {system_message}\n\nCurrent Conversation:\n{chat_history}\n\n"
             "User: {user_text}.\n [/INST]\n"
-            "AI: Please provide a detailed explanation in depth. "
-            "Ensure your response covers the topic thoroughly and is written in a friendly, conversational style, "
-            "starting with a phrase like 'Certainly!', 'Of course!', or 'Great question!'." + style_clause +
+            "AI: Please provide a detailed, in-depth answer in a friendly, conversational tone. "
+            "Begin with a phrase like 'Certainly!', 'Of course!', or 'Great question!'." + style_clause +
             "\nHAL:"
         )
     )
     
     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))
-    # Remove any extra markers if present.
     response = response.split("HAL:")[-1].strip()
-    
-    # Fallback in case the generated answer is empty
     if not response:
         response = "Certainly, here is an in-depth explanation: [Fallback explanation]."
-    
     chat_history.append({'role': 'user', 'content': user_text})
     chat_history.append({'role': 'assistant', 'content': response})
     
@@ -160,36 +144,14 @@ if st.sidebar.button("Reset Chat"):
     st.session_state.follow_up = ""
     st.experimental_rerun()
 
-st.markdown("""
-    <style>
-    .user-msg {
-        background-color: #696969;
-        color: white;
-        padding: 10px;
-        border-radius: 10px;
-        margin-bottom: 5px;
-        width: fit-content;
-        max-width: 80%;
-    }
-    .assistant-msg {
-        background-color: #333333;
-        color: white;
-        padding: 10px;
-        border-radius: 10px;
-        margin-bottom: 5px;
-        width: fit-content;
-        max-width: 80%;
-    }
-    .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)
+# Render the chat history.
+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)
 
 user_input = st.chat_input("Type your message here...")
 
@@ -203,11 +165,3 @@ if user_input:
         st.image(image_url, caption="NASA Image of the Day")
     st.session_state.follow_up = follow_up
     st.session_state.response_ready = True
-
-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)