Spaces:

vikramronavrsc
/

BLOCHAIN_RAG_FOR_LASTDAY_EXAM_PREP

Sleeping

App Files Files Community

vikramronavrsc commited on Mar 30

Commit

15f0c95

verified ·

1 Parent(s): 6d9e7a8

Update app.py

Browse files

Files changed (1) hide show

app.py +521 -291

app.py CHANGED Viewed

@@ -1,13 +1,172 @@
-# app.py
 import os
 import shutil
 import streamlit as st
 import torch
 import atexit
 from advanced_rag import AdvancedRAG
 from metamask_component import metamask_connector
 from voice_component import voice_input_component
 # Helper function to initialize session state
 def initialize_session_state():
     """Initialize Streamlit session state variables."""
@@ -23,6 +182,8 @@ def initialize_session_state():
         st.session_state.retrieval_method = "enhanced"
     if "voice_transcript" not in st.session_state:
         st.session_state.voice_transcript = ""
 # Helper function to clean up temporary files
 def cleanup_temp_files():
@@ -34,330 +195,399 @@ def cleanup_temp_files():
         except Exception as e:
             print(f"Error cleaning up temporary directory: {e}")
 # Streamlit UI
 def main():
     st.set_page_config(
-        page_title="Advanced RAG with MetaMask and Voice",
         layout="wide",
         initial_sidebar_state="expanded"
     )
-    st.title("🚀 Advanced RAG System with Blockchain Verification and Voice Input")
-    st.markdown("""
-    This application allows you to:
-    - Upload and process PDF documents
-    - Verify document authenticity on blockchain using MetaMask
-    - Ask questions using voice or text input
-    - Choose between direct retrieval or enhanced LLM-powered answers
-    """)
     # Initialize session state
     initialize_session_state()
-    # MetaMask Connection Section
-    st.header("🦊 MetaMask Connection")
-    st.markdown("Connect your MetaMask wallet to verify documents and log queries on the blockchain.")
-    # Add MetaMask connector and get connection info
-    metamask_info = metamask_connector()
-    # Display MetaMask connection status
-    if metamask_info and metamask_info.get("connected"):
-        st.success(f"✅ MetaMask Connected: {metamask_info.get('address')}")
-        st.info(f"Network: {metamask_info.get('network_name')}")
-        st.session_state.metamask_connected = True
-    else:
-        st.warning("⚠️ MetaMask not connected. Please connect your wallet to use blockchain features.")
-        st.session_state.metamask_connected = False
-    # Update RAG system with MetaMask connection if needed
-    if st.session_state.rag and metamask_info:
-        is_connected = st.session_state.rag.update_blockchain_connection(metamask_info)
-        if is_connected:
-            st.success("RAG system updated with MetaMask connection")
     # Sidebar for configuration and file upload
     with st.sidebar:
-        st.header("⚙️ Configuration")
-        # GPU Detection
-        gpu_available = torch.cuda.is_available()
-        if gpu_available:
-            try:
-                gpu_info = torch.cuda.get_device_properties(0)
-                st.success(f"GPU detected: {gpu_info.name} ({gpu_info.total_memory / 1024**3:.1f} GB)")
-            except Exception as e:
-                st.warning(f"GPU detected but couldn't get properties: {str(e)}")
-                st.info("Running with limited GPU information")
-        else:
-            st.warning("No GPU detected. Running in CPU mode.")
-        # Model selection
-        st.subheader("Model Selection")
-        llm_model = st.selectbox(
-            "LLM Model",
-            options=[
-                "mistralai/Mistral-7B-Instruct-v0.2",
-                "meta-llama/Llama-3.2-1B",
-                "microsoft/Phi-4-mini-instruct",
-                "Salesforce/xgen-7b-8k-inst",
-                "meta-llama/Llama-3.2-3B-Instruct"
-            ],
-            index=0
-        )
-        embedding_model = st.selectbox(
-            "Embedding Model",
-            options=[
-                "sentence-transformers/all-mpnet-base-v2",
-                "sentence-transformers/all-MiniLM-L6-v2",
-                "sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2"
-            ],
-            index=1  # all-MiniLM-L6-v2 is smaller and faster
-        )
-        use_gpu = st.checkbox("Use GPU Acceleration", value=gpu_available)
-        # Blockchain configuration
-        st.subheader("🔗 Blockchain Configuration")
-        use_blockchain = st.checkbox("Enable Blockchain Verification", value=True)
-        if use_blockchain:
-            # Hardcoded contract address - replace with your deployed contract
-            contract_address = os.environ.get("CONTRACT_ADDRESS", "0x123abc...")  # Your pre-deployed contract
-            st.info(f"Using pre-deployed contract: {contract_address[:10]}...")
-            # Display MetaMask connection status in sidebar
             if metamask_info and metamask_info.get("connected"):
-                st.success(f"✅ MetaMask Connected: {metamask_info.get('address')[:10]}...")
             else:
-                st.warning("⚠️ MetaMask not connected. Please connect your wallet above.")
-        # Advanced options
-        with st.expander("Advanced Options"):
-            chunk_size = st.slider("Chunk Size", 100, 2000, 1000)
-            chunk_overlap = st.slider("Chunk Overlap", 0, 500, 200)
-        # Initialize button
-        if st.button("Initialize System"):
-            with st.spinner("Initializing RAG system..."):
-                if use_blockchain and not contract_address:
-                    st.error("Contract address is required for blockchain integration")
-                else:
-                    st.session_state.rag = AdvancedRAG(
-                        llm_model_name=llm_model,
-                        embedding_model_name=embedding_model,
-                        chunk_size=chunk_size,
-                        chunk_overlap=chunk_overlap,
-                        use_gpu=use_gpu and gpu_available,
-                        use_blockchain=use_blockchain,
-                        contract_address=contract_address if use_blockchain else None
-                    )
-                    # Update with current MetaMask connection if available
-                    if use_blockchain and metamask_info:
-                        st.session_state.rag.update_blockchain_connection(metamask_info)
-                    st.success(f"System initialized with {embedding_model} on {st.session_state.rag.device}")
-                    if use_blockchain:
-                        if metamask_info and metamask_info.get("connected"):
-                            st.success("Blockchain verification enabled with MetaMask")
-                        else:
-                            st.warning("Blockchain verification enabled but MetaMask not connected")
-        st.header("📄 Upload Documents")
-        uploaded_files = st.file_uploader("Select PDFs", type="pdf", accept_multiple_files=True)
-        if uploaded_files and st.button("Process PDFs"):
-            if not st.session_state.rag:
-                with st.spinner("Initializing RAG system..."):
-                    st.session_state.rag = AdvancedRAG(
-                        llm_model_name=llm_model,
-                        embedding_model_name=embedding_model,
-                        chunk_size=chunk_size,
-                        chunk_overlap=chunk_overlap,
-                        use_gpu=use_gpu and gpu_available,
-                        use_blockchain=use_blockchain,
-                        contract_address=contract_address if use_blockchain else None
-                    )
-                    # Update with current MetaMask connection if available
-                    if use_blockchain and metamask_info:
-                        st.session_state.rag.update_blockchain_connection(metamask_info)
-            success = st.session_state.rag.process_pdfs(uploaded_files)
-            if success:
-                metrics = st.session_state.rag.get_performance_metrics()
-                if metrics:
-                    st.success("PDFs processed successfully!")
-                    with st.expander("💹 Performance Metrics"):
-                        st.markdown(f"**Documents processed:** {metrics['documents_processed']} chunks")
-                        st.markdown(f"**Index building time:** {metrics['index_building_time']:.2f} seconds")
-                        st.markdown(f"**Total processing time:** {metrics['total_processing_time']:.2f} seconds")
-                        st.markdown(f"**Memory used:** {metrics['memory_used_gb']:.2f} GB")
-                        st.markdown(f"**Device used:** {metrics['device']}")
-                        st.markdown(f"**Blockchain verification:** {'Enabled' if metrics['blockchain_enabled'] else 'Disabled'}")
-                        st.markdown(f"**Blockchain connected:** {'Yes' if metrics.get('blockchain_connected') else 'No'}")
-    # Retrieval Method Selection
-    st.header("🔍 Retrieval Method")
-    retrieval_cols = st.columns(2)
-    with retrieval_cols[0]:
-        if st.button("📄 Direct Retrieval", help="Get raw document chunks without LLM processing", use_container_width=True):
-            st.session_state.retrieval_method = "direct"
-            st.info("Using Direct Retrieval: Raw document passages will be returned without LLM processing")
-    with retrieval_cols[1]:
-        if st.button("🧠 Enhanced Retrieval", help="Process results through LLM for comprehensive answers", use_container_width=True):
-            st.session_state.retrieval_method = "enhanced"
-            st.info("Using Enhanced Retrieval: Documents will be processed by LLM to generate comprehensive answers")
-    # Blockchain verification info
-    if st.session_state.rag and st.session_state.rag.use_blockchain:
-        if st.session_state.metamask_connected:
-            st.info("🔗 Blockchain verification is enabled with MetaMask. Documents are cryptographically verified and queries are logged with immutable audit trail.")
-        else:
-            st.warning("🔗 Blockchain verification is enabled but MetaMask is not connected. Please connect your MetaMask wallet to use blockchain features.")
-    # Display chat messages
-    st.header("💬 Chat")
-    # Chat container
-    chat_container = st.container(height=400, border=True)
-    with chat_container:
-        for message in st.session_state.messages:
-            with st.chat_message(message["role"]):
-                if message["role"] == "user":
-                    st.markdown(message["content"])
-                else:
-                    if isinstance(message["content"], dict):
-                        st.markdown(message["content"]["answer"])
-                        if "query_time" in message["content"]:
-                            st.caption(f"Response time: {message['content']['query_time']:.2f} seconds")
-                        if "method" in message["content"]:
-                            method_name = "Direct Retrieval" if message["content"]["method"] == "direct" else "Enhanced Retrieval"
-                            st.caption(f"Method: {method_name}")
-                        # Display blockchain log if available
-                        if "blockchain_log" in message["content"] and message["content"]["blockchain_log"]:
-                            blockchain_log = message["content"]["blockchain_log"]
-                            st.success(f"✅ Query logged on blockchain | Transaction: {blockchain_log['tx_hash'][:10]}...")
-                        # Display sources in expander
-                        if "sources" in message["content"] and message["content"]["sources"]:
-                            with st.expander("📄 View Sources"):
-                                for i, source in enumerate(message["content"]["sources"]):
-                                    st.markdown(f"**Source {i+1}: {source['source']}**")
-                                    # Show blockchain verification if available
-                                    if source.get("blockchain"):
-                                        st.success(f"✅ Verified on blockchain | TX: {source['blockchain']['tx_hash'][:10]}...")
-                                    st.text(source["content"])
-                                    st.divider()
-                    else:
-                        st.markdown(message["content"])
-    # Voice Input Section
-    st.header("🎤 Voice Input")
-    st.markdown("You can ask questions using your voice or type them below.")
-    # Voice input component
-    voice_transcript = voice_input_component()
-    # Update session state with voice transcript if not empty
-    if voice_transcript and voice_transcript.strip():
-        st.session_state.voice_transcript = voice_transcript.strip()
-        st.success(f"Voice input received: {voice_transcript}")
-    # Chat input - show the voice transcript in the text input
-    prompt_placeholder = "Ask a question about your PDFs..."
-    if st.session_state.voice_transcript:
-        prompt_placeholder = st.session_state.voice_transcript
-    # Chat input
-    prompt = st.chat_input(prompt_placeholder)
-    # Process either voice input or text input
-    if prompt or st.session_state.voice_transcript:
-        # Prioritize text input over voice input
-        if prompt:
-            user_input = prompt
-        else:
-            user_input = st.session_state.voice_transcript
-            # Clear voice transcript after using it
-            st.session_state.voice_transcript = ""
-            # Rerun to clear the voice input display
-            st.rerun()
-        # Add user message to chat
-        st.session_state.messages.append({"role": "user", "content": user_input})
-        # Display user message
-        with chat_container:
-            with st.chat_message("user"):
-                st.markdown(user_input)
-        # Check if system is initialized
-        if not st.session_state.rag:
-            with chat_container:
-                with st.chat_message("assistant"):
-                    message = "Please initialize the system and process PDFs first."
-                    st.markdown(message)
-                    st.session_state.messages.append({"role": "assistant", "content": message})
-        # Get response if vector store is ready
-        elif st.session_state.rag.vector_store:
-            with chat_container:
-                with st.chat_message("assistant"):
-                    # Get retrieval method
-                    method = st.session_state.retrieval_method
-                    # Get response using specified method
-                    response = st.session_state.rag.ask(user_input, method=method)
-                    st.session_state.messages.append({"role": "assistant", "content": response})
-                    if isinstance(response, dict):
-                        st.markdown(response["answer"])
-                        if "query_time" in response:
-                            st.caption(f"Response time: {response['query_time']:.2f} seconds")
-                        if "method" in response:
-                            method_name = "Direct Retrieval" if response["method"] == "direct" else "Enhanced Retrieval"
-                            st.caption(f"Method: {method_name}")
-                        # Display blockchain log if available
-                        if "blockchain_log" in response and response["blockchain_log"]:
-                            blockchain_log = response["blockchain_log"]
-                            st.success(f"✅ Query logged on blockchain | Transaction: {blockchain_log['tx_hash'][:10]}...")
-                        # Display sources in expander
-                        if "sources" in response and response["sources"]:
-                            with st.expander("📄 View Sources"):
-                                for i, source in enumerate(response["sources"]):
-                                    st.markdown(f"**Source {i+1}: {source['source']}**")
-                                    # Show blockchain verification if available
-                                    if source.get("blockchain"):
-                                        st.success(f"✅ Verified on blockchain | TX: {source['blockchain']['tx_hash'][:10]}...")
-                                    st.text(source["content"])
-                                    st.divider()
-                    else:
-                        st.markdown(response)
         else:
-            with chat_container:
-                with st.chat_message("assistant"):
-                    message = "Please upload and process PDF files first."
-                    st.markdown(message)
-                    st.session_state.messages.append({"role": "assistant", "content": message})
 # Main entry point
 if __name__ == "__main__":

+# app.py - Enhanced UI with animations
 import os
 import shutil
 import streamlit as st
 import torch
 import atexit
+import time
 from advanced_rag import AdvancedRAG
 from metamask_component import metamask_connector
 from voice_component import voice_input_component
+# Custom CSS for enhanced UI
+def load_custom_css():
+    st.markdown("""
+    <style>
+    /* Main container styling */
+    .main {
+        background-color: #f9fafb;
+    }
+    /* Card styling */
+    .stCard {
+        border-radius: 12px !important;
+        box-shadow: 0 6px 16px rgba(0,0,0,0.05) !important;
+        transition: all 0.3s ease !important;
+    }
+    .stCard:hover {
+        transform: translateY(-2px);
+        box-shadow: 0 12px 24px rgba(0,0,0,0.08) !important;
+    }
+    /* Chat message styling */
+    .chat-message {
+        padding: 16px;
+        border-radius: 12px;
+        margin-bottom: 10px;
+        animation: fadeIn 0.5s ease;
+    }
+    .user-message {
+        background-color: #f0f7ff;
+        border-left: 5px solid #3b82f6;
+    }
+    .assistant-message {
+        background-color: #f0fdf4;
+        border-left: 5px solid #22c55e;
+    }
+    /* Source section styling */
+    .source-item {
+        padding: 12px;
+        border-radius: 8px;
+        background-color: #f8fafc;
+        border: 1px solid #e2e8f0;
+        margin-bottom: 10px;
+        transition: all 0.2s ease;
+    }
+    .source-item:hover {
+        border-color: #cbd5e1;
+        background-color: #f1f5f9;
+    }
+    .source-header {
+        font-weight: 600;
+        display: flex;
+        justify-content: space-between;
+        margin-bottom: 8px;
+        align-items: center;
+    }
+    .source-content {
+        font-size: 0.9em;
+        color: #475569;
+        max-height: 200px;
+        overflow-y: auto;
+    }
+    .verified-badge {
+        background-color: #10b981;
+        color: white;
+        padding: 2px 8px;
+        border-radius: 12px;
+        font-size: 0.7em;
+        display: inline-flex;
+        align-items: center;
+        gap: 4px;
+    }
+    /* Animated loader */
+    @keyframes pulse-animation {
+        0% { box-shadow: 0 0 0 0 rgba(59, 130, 246, 0.7); }
+        70% { box-shadow: 0 0 0 10px rgba(59, 130, 246, 0); }
+        100% { box-shadow: 0 0 0 0 rgba(59, 130, 246, 0); }
+    }
+    .pulse {
+        animation: pulse-animation 2s infinite;
+    }
+    /* Fade in animation */
+    @keyframes fadeIn {
+        from { opacity: 0; transform: translateY(10px); }
+        to { opacity: 1; transform: translateY(0); }
+    }
+    /* Method selection buttons */
+    .method-button {
+        border-radius: 8px;
+        padding: 8px 16px;
+        transition: all 0.3s ease;
+        border: none;
+        cursor: pointer;
+        font-weight: 500;
+        display: inline-flex;
+        align-items: center;
+        gap: 8px;
+    }
+    .method-direct {
+        background-color: #e0f2fe;
+        color: #0284c7;
+    }
+    .method-direct:hover {
+        background-color: #bae6fd;
+    }
+    .method-enhanced {
+        background-color: #dbeafe;
+        color: #2563eb;
+    }
+    .method-enhanced:hover {
+        background-color: #bfdbfe;
+    }
+    .method-active {
+        box-shadow: 0 0 0 2px #3b82f6;
+    }
+    /* Two-column layout for answer and sources */
+    .answer-container {
+        border-radius: 12px;
+        background-color: white;
+        padding: 20px;
+        box-shadow: 0 4px 12px rgba(0,0,0,0.05);
+        margin-bottom: 20px;
+    }
+    .answer-header {
+        margin-bottom: 16px;
+        color: #1e293b;
+        font-weight: 600;
+        font-size: 1.1em;
+    }
+    .answer-content {
+        font-size: 1em;
+        line-height: 1.6;
+        color: #334155;
+    }
+    .sources-container {
+        border-radius: 12px;
+        background-color: white;
+        padding: 20px;
+        box-shadow: 0 4px 12px rgba(0,0,0,0.05);
+    }
+    .sources-header {
+        margin-bottom: 16px;
+        color: #1e293b;
+        font-weight: 600;
+        font-size: 1.1em;
+    }
+    /* Section animations */
+    .animate-section {
+        animation: fadeIn 0.5s ease;
+    }
+    </style>
+    """, unsafe_allow_html=True)
 # Helper function to initialize session state
 def initialize_session_state():
     """Initialize Streamlit session state variables."""
         st.session_state.retrieval_method = "enhanced"
     if "voice_transcript" not in st.session_state:
         st.session_state.voice_transcript = ""
+    if "current_answer" not in st.session_state:
+        st.session_state.current_answer = None
 # Helper function to clean up temporary files
 def cleanup_temp_files():
         except Exception as e:
             print(f"Error cleaning up temporary directory: {e}")
+# Create an animated loading spinner
+def animated_loader(text="Processing..."):
+    with st.spinner(text):
+        # Add a pulsing animation while processing
+        st.markdown("""
+        <div style="display: flex; justify-content: center; margin: 20px 0;">
+            <div class="pulse" style="width: 20px; height: 20px; border-radius: 50%; background-color: #3b82f6;"></div>
+        </div>
+        """, unsafe_allow_html=True)
+# Animated section container
+def animated_section(key):
+    return st.container(key=f"animated_{key}")
+# Create a method selection button with animation
+def method_button(label, icon, method, current_method):
+    active_class = "method-active" if method == current_method else ""
+    method_class = "method-direct" if method == "direct" else "method-enhanced"
+    button_html = f"""
+    <button class="method-button {method_class} {active_class}">
+        {icon} {label}
+    </button>
+    """
+    return button_html
 # Streamlit UI
 def main():
     st.set_page_config(
+        page_title="Advanced RAG System",
         layout="wide",
         initial_sidebar_state="expanded"
     )
+    # Load custom CSS
+    load_custom_css()
+    # Page header with animation
+    with animated_section("header"):
+        st.title("🚀 Advanced RAG System")
+        st.markdown("""
+        <div style="display: flex; gap: 15px; margin-bottom: 20px;">
+            <div style="background-color: #e0f2fe; color: #0284c7; padding: 8px 16px; border-radius: 20px; font-size: 0.9em; display: flex; align-items: center; gap: 8px;">
+                <svg xmlns="http://www.w3.org/2000/svg" width="16" height="16" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round"><polygon points="12 2 15.09 8.26 22 9.27 17 14.14 18.18 21.02 12 17.77 5.82 21.02 7 14.14 2 9.27 8.91 8.26 12 2"></polygon></svg>
+                Document Analysis
+            </div>
+            <div style="background-color: #f0fdf4; color: #16a34a; padding: 8px 16px; border-radius: 20px; font-size: 0.9em; display: flex; align-items: center; gap: 8px;">
+                <svg xmlns="http://www.w3.org/2000/svg" width="16" height="16" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round"><rect x="3" y="11" width="18" height="11" rx="2" ry="2"></rect><path d="M7 11V7a5 5 0 0 1 10 0v4"></path></svg>
+                Blockchain Verification
+            </div>
+            <div style="background-color: #fef2f2; color: #dc2626; padding: 8px 16px; border-radius: 20px; font-size: 0.9em; display: flex; align-items: center; gap: 8px;">
+                <svg xmlns="http://www.w3.org/2000/svg" width="16" height="16" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round"><path d="M12 2a3 3 0 0 0-3 3v7a3 3 0 0 0 6 0V5a3 3 0 0 0-3-3Z"></path><path d="M19 10v2a7 7 0 0 1-14 0v-2"></path><line x1="12" y1="19" x2="12" y2="22"></line></svg>
+                Voice Input
+            </div>
+        </div>
+        """, unsafe_allow_html=True)
     # Initialize session state
     initialize_session_state()
     # Sidebar for configuration and file upload
     with st.sidebar:
+        with animated_section("sidebar_header"):
+            st.header("System Configuration")
+            st.markdown("""
+            <div style="margin-bottom: 15px; padding: 10px; border-radius: 8px; background-color: #f1f5f9; border-left: 4px solid #3b82f6;">
+                Configure your RAG system and upload documents
+            </div>
+            """, unsafe_allow_html=True)
+        # MetaMask Connection
+        with animated_section("metamask"):
+            st.subheader("🦊 MetaMask Connection")
+            # Add MetaMask connector and get connection info
+            metamask_info = metamask_connector()
+            # Display MetaMask connection status
             if metamask_info and metamask_info.get("connected"):
+                st.success(f"✅ Connected: {metamask_info.get('address')[:10]}...{metamask_info.get('address')[-6:]}")
+                st.info(f"Network: {metamask_info.get('network_name')}")
+                st.session_state.metamask_connected = True
             else:
+                st.warning("⚠️ MetaMask not connected")
+                st.session_state.metamask_connected = False
+            # Update RAG system with MetaMask connection if needed
+            if st.session_state.rag and metamask_info:
+                is_connected = st.session_state.rag.update_blockchain_connection(metamask_info)
+                if is_connected:
+                    st.success("RAG system updated with MetaMask connection")
+        # System Configuration
+        with animated_section("config"):
+            st.subheader("⚙️ System Configuration")
+            # GPU Detection
+            gpu_available = torch.cuda.is_available()
+            if gpu_available:
+                try:
+                    gpu_info = torch.cuda.get_device_properties(0)
+                    st.markdown(f"""
+                    <div style="display: flex; align-items: center; gap: 8px; padding: 8px 12px; background-color: #ecfdf5; border-radius: 8px; margin-bottom: 15px;">
+                        <svg xmlns="http://www.w3.org/2000/svg" width="16" height="16" viewBox="0 0 24 24" fill="none" stroke="#10b981" stroke-width="2" stroke-linecap="round" stroke-linejoin="round"><path d="M17 18a5 5 0 0 1-10 0"></path><line x1="12" y1="2" x2="12" y2="9"></line><line x1="4.22" y1="10.22" x2="5.64" y2="11.64"></line><line x1="1" y1="18" x2="3" y2="18"></line><line x1="21" y1="18" x2="23" y2="18"></line><line x1="18.36" y1="11.64" x2="19.78" y2="10.22"></line><line x1="23" y1="22" x2="1" y2="22"></line><polyline points="8 6 12 2 16 6"></polyline></svg>
+                        <span style="color: #10b981; font-weight: 500;">GPU: {gpu_info.name} ({gpu_info.total_memory / 1024**3:.1f} GB)</span>
+                    </div>
+                    """, unsafe_allow_html=True)
+                except Exception as e:
+                    st.warning(f"GPU detected but couldn't get properties")
+            else:
+                st.warning("No GPU detected. Running in CPU mode.")
+            # Model selection
+            llm_model = st.selectbox(
+                "LLM Model",
+                options=[
+                    "mistralai/Mistral-7B-Instruct-v0.2",
+                    "google/gemma-7b-it",
+                    "google/flan-t5-xl",
+                    "Salesforce/xgen-7b-8k-inst",
+                    "tiiuae/falcon-7b-instruct"
+                ],
+                index=0
+            )
+            embedding_model = st.selectbox(
+                "Embedding Model",
+                options=[
+                    "sentence-transformers/all-mpnet-base-v2",
+                    "sentence-transformers/all-MiniLM-L6-v2",
+                    "sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2"
+                ],
+                index=1
+            )
+            use_gpu = st.checkbox("Use GPU Acceleration", value=gpu_available)
+            # Blockchain configuration
+            use_blockchain = st.checkbox("Enable Blockchain Verification", value=True)
+            if use_blockchain:
+                # Hardcoded contract address - replace with your deployed contract
+                contract_address = os.environ.get("CONTRACT_ADDRESS", "0x123abc...")  # Your pre-deployed contract
+                st.info(f"Using contract: {contract_address[:10]}...")
+            # Advanced options
+            with st.expander("Advanced Options"):
+                chunk_size = st.slider("Chunk Size", 100, 2000, 1000)
+                chunk_overlap = st.slider("Chunk Overlap", 0, 500, 200)
+            # Initialize button with animation
+            if st.button("Initialize System", key="init_button"):
+                with st.spinner("Initializing..."):
+                    animated_loader("Setting up RAG system...")
+                    if use_blockchain and not contract_address:
+                        st.error("Contract address is required for blockchain integration")
+                    else:
+                        st.session_state.rag = AdvancedRAG(
+                            llm_model_name=llm_model,
+                            embedding_model_name=embedding_model,
+                            chunk_size=chunk_size,
+                            chunk_overlap=chunk_overlap,
+                            use_gpu=use_gpu and gpu_available,
+                            use_blockchain=use_blockchain,
+                            contract_address=contract_address if use_blockchain else None
+                        )
+                        # Update with current MetaMask connection if available
+                        if use_blockchain and metamask_info:
+                            st.session_state.rag.update_blockchain_connection(metamask_info)
+                        st.success(f"System initialized with {embedding_model}")
+        # Document Upload
+        with animated_section("upload"):
+            st.subheader("📄 Document Upload")
+            uploaded_files = st.file_uploader("Select PDFs", type="pdf", accept_multiple_files=True)
+            if uploaded_files and st.button("Process PDFs", key="process_button"):
+                if not st.session_state.rag:
+                    with st.spinner("Initializing system first..."):
+                        animated_loader("Setting up RAG system...")
+                        st.session_state.rag = AdvancedRAG(
+                            llm_model_name=llm_model,
+                            embedding_model_name=embedding_model,
+                            chunk_size=chunk_size,
+                            chunk_overlap=chunk_overlap,
+                            use_gpu=use_gpu and gpu_available,
+                            use_blockchain=use_blockchain,
+                            contract_address=contract_address if use_blockchain else None
+                        )
+                        # Update with current MetaMask connection if available
+                        if use_blockchain and metamask_info:
+                            st.session_state.rag.update_blockchain_connection(metamask_info)
+                with st.spinner("Processing documents..."):
+                    animated_loader("Analyzing and indexing PDFs...")
+                    success = st.session_state.rag.process_pdfs(uploaded_files)
+                    if success:
+                        metrics = st.session_state.rag.get_performance_metrics()
+                        if metrics:
+                            st.success("📄 PDFs processed successfully!")
+                            with st.expander("💹 Performance Metrics"):
+                                st.markdown(f"**Documents processed:** {metrics['documents_processed']} chunks")
+                                st.markdown(f"**Index building time:** {metrics['index_building_time']:.2f} seconds")
+                                st.markdown(f"**Total processing time:** {metrics['total_processing_time']:.2f} seconds")
+    # Main content area - Two column layout
+    main_col1, main_col2 = st.columns([2, 1])
+    # Left column - Chat and Answer section
+    with main_col1:
+        # Method Selection
+        with animated_section("method_selection"):
+            st.markdown("### Answer Method")
+            col1, col2 = st.columns(2)
+            with col1:
+                direct_html = method_button(
+                    "Direct Retrieval",
+                    '<svg xmlns="http://www.w3.org/2000/svg" width="16" height="16" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round"><circle cx="11" cy="11" r="8"></circle><line x1="21" y1="21" x2="16.65" y2="16.65"></line></svg>',
+                    "direct",
+                    st.session_state.retrieval_method
+                )
+                if st.markdown(direct_html, unsafe_allow_html=True):
+                    st.session_state.retrieval_method = "direct"
+                    st.rerun()
+            with col2:
+                enhanced_html = method_button(
+                    "Enhanced Answers",
+                    '<svg xmlns="http://www.w3.org/2000/svg" width="16" height="16" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round"><polygon points="13 2 3 14 12 14 11 22 21 10 12 10 13 2"></polygon></svg>',
+                    "enhanced",
+                    st.session_state.retrieval_method
+                )
+                if st.markdown(enhanced_html, unsafe_allow_html=True):
+                    st.session_state.retrieval_method = "enhanced"
+                    st.rerun()
+            # Show current method description
+            if st.session_state.retrieval_method == "direct":
+                st.info("🔍 **Direct Retrieval**: Shows raw document passages without processing. Fast and transparent.")
+            else:
+                st.info("💡 **Enhanced Answers**: Processes content through AI for comprehensive answers. Better quality.")
+        # Voice Input Section
+        with animated_section("voice_input"):
+            st.markdown("### Ask with Voice")
+            voice_transcript = voice_input_component()
+            # Update session state with voice transcript if not empty
+            if voice_transcript and voice_transcript.strip():
+                st.session_state.voice_transcript = voice_transcript.strip()
+                st.experimental_rerun()
+        # Text Input Section
+        with animated_section("text_input"):
+            st.markdown("### Or Type a Question")
+            # Chat input - show the voice transcript in the text input
+            user_input = st.text_input(
+                "Ask a question about your documents",
+                value=st.session_state.voice_transcript,
+                key="text_question"
+            )
+            # Process user input (from text or voice)
+            if user_input or st.session_state.voice_transcript:
+                # Prioritize text input over voice input
+                if user_input:
+                    query = user_input
+                else:
+                    query = st.session_state.voice_transcript
+                    # Clear voice transcript after using it
+                    st.session_state.voice_transcript = ""
+                # Add user message to chat history
+                st.session_state.messages.append({"role": "user", "content": query})
+                # Check if system is initialized
+                if not st.session_state.rag:
+                    st.error("Please initialize the system and process PDFs first.")
+                    st.session_state.messages.append({
+                        "role": "assistant",
+                        "content": "Please initialize the system and process PDFs first."
+                    })
+                # Get response if vector store is ready
+                elif st.session_state.rag.vector_store:
+                    with st.spinner("Generating answer..."):
+                        animated_loader("Searching documents and generating answer...")
+                        # Get retrieval method
+                        method = st.session_state.retrieval_method
+                        # Get response using specified method
+                        response = st.session_state.rag.ask(query, method=method)
+                        st.session_state.messages.append({"role": "assistant", "content": response})
+                        # Store current answer for display
+                        st.session_state.current_answer = response
+                        # Rerun to update the UI
+                        st.experimental_rerun()
+                else:
+                    st.error("Please upload and process PDF files first.")
+                    st.session_state.messages.append({
+                        "role": "assistant",
+                        "content": "Please upload and process PDF files first."
+                    })
+        # Answer Display Section
+        if st.session_state.current_answer and isinstance(st.session_state.current_answer, dict):
+            with animated_section("answer_display"):
+                answer = st.session_state.current_answer
+                st.markdown("""
+                <div class="answer-container animate-section">
+                    <div class="answer-header">
+                        <svg xmlns="http://www.w3.org/2000/svg" width="16" height="16" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" style="margin-right: 8px;"><circle cx="12" cy="12" r="10"></circle><path d="M9.09 9a3 3 0 0 1 5.83 1c0 2-3 3-3 3"></path><line x1="12" y1="17" x2="12.01" y2="17"></line></svg>
+                        Answer
+                    </div>
+                    <div class="answer-content">
+                        {answer_text}
+                    </div>
+                </div>
+                """.format(answer_text=answer["answer"]), unsafe_allow_html=True)
+                # Display metadata
+                meta_cols = st.columns(3)
+                with meta_cols[0]:
+                    method_name = "Direct Retrieval" if answer["method"] == "direct" else "Enhanced Answer"
+                    st.caption(f"Method: {method_name}")
+                with meta_cols[1]:
+                    st.caption(f"Time: {answer['query_time']:.2f} seconds")
+                with meta_cols[2]:
+                    if "blockchain_log" in answer and answer["blockchain_log"]:
+                        blockchain_log = answer["blockchain_log"]
+                        st.caption(f"📝 Logged on blockchain: {blockchain_log['tx_hash'][:8]}...")
+    # Right column - Sources section
+    with main_col2:
+        if st.session_state.current_answer and isinstance(st.session_state.current_answer, dict):
+            with animated_section("sources_display"):
+                answer = st.session_state.current_answer
+                st.markdown("""
+                <div class="sources-container animate-section">
+                    <div class="sources-header">
+                        <svg xmlns="http://www.w3.org/2000/svg" width="16" height="16" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" style="margin-right: 8px;"><path d="M2 3h6a4 4 0 0 1 4 4v14a3 3 0 0 0-3-3H2z"></path><path d="M22 3h-6a4 4 0 0 0-4 4v14a3 3 0 0 1 3-3h7z"></path></svg>
+                        Sources
+                    </div>
+                """, unsafe_allow_html=True)
+                # Display sources
+                if "sources" in answer and answer["sources"]:
+                    for i, source in enumerate(answer["sources"]):
+                        verified_badge = ""
+                        if source.get("blockchain"):
+                            verified_badge = f"""
+                            <div class="verified-badge">
+                                <svg xmlns="http://www.w3.org/2000/svg" width="12" height="12" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round"><path d="M22 11.08V12a10 10 0 1 1-5.93-9.14"></path><polyline points="22 4 12 14.01 9 11.01"></polyline></svg>
+                                Verified
+                            </div>
+                            """
+                        st.markdown(f"""
+                        <div class="source-item">
+                            <div class="source-header">
+                                <div>Source {i+1}: {source['source']}</div>
+                                {verified_badge}
+                            </div>
+                            <div class="source-content">
+                                {source['content']}
+                            </div>
+                        </div>
+                        """, unsafe_allow_html=True)
+                st.markdown("</div>", unsafe_allow_html=True)
         else:
+            # Placeholder when no sources to display
+            st.markdown("""
+            <div style="height: 300px; display: flex; justify-content: center; align-items: center; background-color: white; border-radius: 12px; margin-top: 30px;">
+                <div style="text-align: center; color: #94a3b8;">
+                    <svg xmlns="http://www.w3.org/2000/svg" width="40" height="40" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" style="margin: 0 auto 15px;"><circle cx="12" cy="12" r="10"></circle><path d="M9.09 9a3 3 0 0 1 5.83 1c0 2-3 3-3 3"></path><line x1="12" y1="17" x2="12.01" y2="17"></line></svg>
+                    <p>Ask a question to see document sources here</p>
+                </div>
+            </div>
+            """, unsafe_allow_html=True)
 # Main entry point
 if __name__ == "__main__":