Update app.py

app.py

@@ -7,21 +7,21 @@ from langchain_huggingface import HuggingFaceEndpoint
 from langchain_core.prompts import PromptTemplate
 from langchain_core.output_parsers import StrOutputParser
 from transformers import pipeline
-from langdetect import detect
+from langdetect import detect  # Ensure this package is installed
 
-# Use environment variables for keys
+# ✅ Environment Variables
 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.")
+    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:
-    raise ValueError("NASA_API_KEY environment variable not set. Please set it in your Hugging Face Space settings.")
+    raise ValueError("NASA_API_KEY is not set. Please add it to your environment variables.")
 
-# Set up Streamlit UI
+# ✅ Set Up Streamlit
 st.set_page_config(page_title="HAL - NASA ChatBot", page_icon="🚀")
 
-# --- Initialize Session State Variables ---
+# ✅ Ensure Session State Variables
 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:
@@ -29,14 +29,10 @@ if "response_ready" not in st.session_state:
 if "follow_up" not in st.session_state:
     st.session_state.follow_up = ""
 
-# --- Set Up Model & API Functions ---
+# ✅ Model Configuration
 model_id = "mistralai/Mistral-7B-Instruct-v0.3"
-sentiment_analyzer = pipeline(
-    "sentiment-analysis",
-    model="distilbert/distilbert-base-uncased-finetuned-sst-2-english",
-    revision="714eb0f"
-)
 
+# ✅ Initialize Hugging Face Model
 def get_llm_hf_inference(model_id=model_id, max_new_tokens=128, temperature=0.7):
     return HuggingFaceEndpoint(
         repo_id=model_id,
@@ -46,62 +42,40 @@ def get_llm_hf_inference(model_id=model_id, max_new_tokens=128, temperature=0.7)
         task="text-generation"
     )
 
+# ✅ NASA API Function
 def get_nasa_apod():
     url = f"https://api.nasa.gov/planetary/apod?api_key={NASA_API_KEY}"
     response = requests.get(url)
     if response.status_code == 200:
         data = response.json()
         return data.get("url", ""), data.get("title", ""), data.get("explanation", "")
-    else:
-        return "", "NASA Data Unavailable", "I couldn't fetch data from NASA right now. Please try again later."
+    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"
+)
 
 def analyze_sentiment(user_text):
     result = sentiment_analyzer(user_text)[0]
     return result['label']
 
-def is_apod_query(user_text):
-    """
-    Checks if the user's question contains keywords indicating they are asking for
-    the Astronomy Picture of the Day.
-    """
-    keywords = ["apod", "image", "picture", "photo", "astronomy picture"]
-    return any(keyword in user_text.lower() for keyword in keywords)
-
+# ✅ Intent Detection
 def predict_action(user_text):
-    """
-    Determines the type of response for the user's query.
-    If the query contains "NASA" or "space" and also indicates an APOD query,
-    it returns "nasa_info". Otherwise, it returns "general_query", even if "NASA" is present.
-    """
-    user_text_lower = user_text.lower()
-    if "nasa" in user_text_lower or "space" in user_text_lower:
-        if is_apod_query(user_text):
-            return "nasa_info"
+    if "NASA" in user_text or "space" in user_text:
+        return "nasa_info"
     return "general_query"
 
+# ✅ Follow-Up Question Generation
 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.
-    """
-    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 ."
-        "Answer exclusively in English, and do not include extra commentary."
-    )
+    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)
     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)
-
-from langdetect import detect
+    return output if output else "Would you like to explore this topic further?"
 
+# ✅ Ensure English Responses
 def ensure_english(text):
-    """Check if the model accidentally generated a non-English response."""
     try:
         detected_lang = detect(text)
         if detected_lang != "en":
@@ -110,26 +84,11 @@ def ensure_english(text):
         return "⚠️ Language detection failed. Please ask your question again."
     return text
 
+# ✅ Main Response Function
 def get_response(system_message, chat_history, user_text, max_new_tokens=512):
-    """
-    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.
-    """
-    
-    # 🔍 Determine the user's intent (NASA Info or General Query)
-    action = predict_action(user_text)  # 🔥 Define 'action' here
-    
-    # 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:
-        match = re.search(r"(in the voice of|speaking as)(.*)", lower_text)
-        if match:
-            style_instruction = match.group(2).strip().capitalize()
-            style_instruction = f" Please respond in the voice of {style_instruction}."
-
-    # 🚀 Handle NASA-specific queries
+    action = predict_action(user_text)  # 🔥 Fix: Define 'action'
+
+    # ✅ Handle NASA-Specific Queries
     if action == "nasa_info":
         nasa_url, nasa_title, nasa_explanation = get_nasa_apod()
         response = f"**{nasa_title}**\n\n{nasa_explanation}"
@@ -139,84 +98,53 @@ def get_response(system_message, chat_history, user_text, max_new_tokens=512):
         chat_history.append({'role': 'assistant', 'content': follow_up})
         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)
-    filtered_history = ""
-    for message in chat_history:
-        if message["role"] == "assistant" and message["content"].strip() == "Hello! How can I assist you today?":
-            continue
-        filtered_history += f"{message['role']}: {message['content']}\n"
 
-    style_clause = style_instruction if style_instruction else ""
+    # ✅ Format Chat History
+    filtered_history = "\n".join(f"{msg['role']}: {msg['content']}" for msg in chat_history)
 
-    # Instruct the model to generate a detailed, in-depth answer.
+    # ✅ Prompt Engineering
     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!'."
-            "🚨 IMPORTANT: Answer exclusively in **English only**. Do not generate responses in any other language."
-            "\nHAL:"
-        )
+        "[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!'."
+        "🚨 Answer **only in English**."
+        "\nHAL:"
     )
 
+    # ✅ Invoke LLM Model
     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))
     response = response.split("HAL:")[-1].strip()
 
-    # 🚨 Ensure the response is in English
+    # ✅ Ensure English
     response = ensure_english(response)
 
-# Fallback in case the generated answer is empty
-if not response:
-    
+    # ✅ Fallback Response
+    if not response:
+        response = "I'm sorry, but I couldn't generate a response. Can you rephrase your question?"
 
+    chat_history.append({'role': 'user', 'content': user_text})
+    chat_history.append({'role': 'assistant', 'content': response})
 
+    follow_up = generate_follow_up(user_text)
+    chat_history.append({'role': 'assistant', 'content': follow_up})
 
-# --- Chat UI ---
-st.title("🚀 HAL - Your NASA AI Assistant")
+    return response, follow_up, chat_history, None
+
+# ✅ Streamlit UI
+st.title("🚀 HAL - NASA AI Assistant")
 st.markdown("🌌 *Ask me about space, NASA, and beyond!*")
 
-#Reset Button
+# ✅ Reset Chat Button
 if st.sidebar.button("Reset Chat"):
     st.session_state.chat_history = [{"role": "assistant", "content": "Hello! How can I assist you today?"}]
     st.session_state.response_ready = False
     st.session_state.follow_up = ""
-    st.experimental_rerun()
-
-#Style and Appearance
-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)
 
+# ✅ Chat UI
 user_input = st.chat_input("Type your message here...")
 
 if user_input:
@@ -227,13 +155,10 @@ if user_input:
     )
     if image_url:
         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)
+if st.session_state.response_ready and st.session_state.follow_up:
+    st.write(f"**HAL:** {st.session_state.follow_up}")
+    st.session_state.response_ready = False