Update app.py

app.py

@@ -1,86 +1,101 @@
 import os
 import streamlit as st
-import torch
 from groq import Groq
-from transformers import pipeline, AutoModelForCausalLM, AutoTokenizer
-
-# ✅ Ensure set_page_config() is the first Streamlit command
-st.set_page_config(page_title="AI Study Assistant", page_icon="🤖", layout="wide")
 
 # Set up the Groq API Key
-GROQ_API_KEY = "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"  # Replace with your actual key
+GROQ_API_KEY = "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"
 os.environ["GROQ_API_KEY"] = GROQ_API_KEY
 
 # Initialize the Groq client
 client = Groq(api_key=GROQ_API_KEY)
 
-# ✅ Ensure Accelerate is installed
-try:
-    import accelerate  # noqa: F401
-except ImportError:
-    st.error("⚠️ `accelerate` library is required. Install it with: `pip install accelerate`")
-
-# ✅ Initialize Hugging Face DeepSeek R1 model correctly
-MODEL_NAME = "deepseek-ai/DeepSeek-R1"
-
-try:
-    tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME, trust_remote_code=True)
-    
-    model = AutoModelForCausalLM.from_pretrained(
-        MODEL_NAME,
-        trust_remote_code=True,
-        torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,  # ✅ Use FP16 on GPU, FP32 on CPU
-        device_map="auto" if torch.cuda.is_available() else None,  # ✅ Enable auto GPU usage
-        quantization_config=None  # ✅ Disable unsupported FP8 quantization
-    )
-
-    def generate_response_hf(user_message):
-        inputs = tokenizer(user_message, return_tensors="pt").to(model.device)
-        outputs = model.generate(**inputs, max_length=200)
-        return tokenizer.decode(outputs[0], skip_special_tokens=True)
-
-except Exception as e:
-    st.error(f"❌ Error loading DeepSeek-R1: {str(e)}")
-    generate_response_hf = lambda x: "⚠️ Error: Model not loaded."
-
-# Streamlit UI setup
+# Streamlit user interface setup
+st.set_page_config(page_title="AI Study Assistant", page_icon="🤖", layout="wide")
 st.title("📚 Subject-specific AI Chatbot")
 st.write("Hello! I'm your AI Study Assistant. You can ask me any questions related to your subjects, and I'll try to help.")
 
-# Sidebar settings
+# Add sidebar with styling options
 st.sidebar.header("⚙️ Settings")
-chat_model = st.sidebar.radio("Choose AI Model:", ["Groq API", "DeepSeek R1 (Hugging Face)"])
-
-# Initialize session state for conversation
+st.sidebar.write("Customize your chatbot experience!")
+chat_theme = st.sidebar.radio("Choose a theme:", ["Light", "Dark", "Blue", "Green"])
+
+# Apply theme
+if chat_theme == "Dark":
+    st.markdown("""
+        <style>
+            body {background-color: #1e1e1e; color: white;}
+            .stButton>button {background-color: #4CAF50; color: white;}
+            .chat-bubble {background-color: #2c2c2c; border-radius: 10px; padding: 10px;}
+        </style>
+    """, unsafe_allow_html=True)
+elif chat_theme == "Blue":
+    st.markdown("""
+        <style>
+            body {background-color: #e3f2fd; color: black;}
+            .stButton>button {background-color: #2196F3; color: white;}
+            .chat-bubble {background-color: #bbdefb; border-radius: 10px; padding: 10px;}
+        </style>
+    """, unsafe_allow_html=True)
+elif chat_theme == "Green":
+    st.markdown("""
+        <style>
+            body {background-color: #e8f5e9; color: black;}
+            .stButton>button {background-color: #4CAF50; color: white;}
+            .chat-bubble {background-color: #c8e6c9; border-radius: 10px; padding: 10px;}
+        </style>
+    """, unsafe_allow_html=True)
+else:
+    st.markdown("""
+        <style>
+            body {background-color: #ffffff; color: black;}
+            .stButton>button {background-color: #008CBA; color: white;}
+            .chat-bubble {background-color: #f1f1f1; border-radius: 10px; padding: 10px;}
+        </style>
+    """, unsafe_allow_html=True)
+
+# Initialize session state for maintaining conversation
 if 'conversation_history' not in st.session_state:
     st.session_state.conversation_history = []
 
-# Subjects list
+# Define a list of subjects for which the chatbot will answer
 subjects = ["Chemistry", "Computer", "English", "Islamiat", "Mathematics", "Physics", "Urdu"]
 
+# Function to generate chatbot response based on subject-specific user input
 def generate_chatbot_response(user_message):
-    related_subject = next((subject for subject in subjects if subject.lower() in user_message.lower()), None)
+    # Check if the user's question is related to any subject
+    related_subject = None
+    for subject in subjects:
+        if subject.lower() in user_message.lower():
+            related_subject = subject
+            break
     
+    # Custom response for "who created you" type of questions
     if "kisne banaya" in user_message.lower() or "who created you" in user_message.lower():
-        return "I was created by Abdul Basit 😊"
+        return "I Created by Abdul Basit 😊"
 
-    prompt = f"You are a helpful AI chatbot for studying {related_subject if related_subject else 'general knowledge'}. The user is asking: {user_message}. Provide a detailed, helpful response."
-    
-    if chat_model == "Groq API":
-        chat_completion = client.chat.completions.create(
-            messages=[{"role": "user", "content": prompt}],
-            model="deepseek-chat"
-        )
-        return chat_completion.choices[0].message.content
+    if related_subject:
+        prompt = f"You are a helpful AI chatbot for studying {related_subject}. The user is asking: {user_message}. Provide a detailed, helpful response related to {related_subject}."
     else:
-        return generate_response_hf(prompt)
+        prompt = f"You are a helpful AI chatbot. The user is asking: {user_message}. If the question is not related to any of the specified subjects (Chemistry, Computer, English, Islamiat, Mathematics, Physics, Urdu), politely let them know."
 
-# Chat input
+    # Generate response using Groq API
+    chat_completion = client.chat.completions.create(
+        messages=[{"role": "user", "content": prompt}],
+        model="llama3-8b-8192",  # You can replace with the appropriate model name
+    )
+
+    response = chat_completion.choices[0].message.content
+    return response
+
+# User input for conversation (now placed at the bottom)
 st.markdown("### 💬 Chat with me")
 user_input = st.chat_input("Ask me a subject-related question:")
 
+# Handle user input and display conversation
 if user_input:
     chatbot_response = generate_chatbot_response(user_input)
+
+    # Save the conversation history
     st.session_state.conversation_history.append(("User: " + user_input, "Chatbot: " + chatbot_response))
 
 # Display chat history