Update app.py

app.py

@@ -2,14 +2,14 @@ import streamlit as st
 from transformers import pipeline, AutoModelForCausalLM, AutoTokenizer
 import torch
 
-# Set page configuration
+# Set page configuration for the app
 st.set_page_config(
     page_title="Review Assistant",
     page_icon="📝",
     layout="centered"
 )
 
-# Custom page styling with CSS
+# Custom CSS styling for the page
 st.markdown("""
 <style>
     .main-header {
@@ -48,24 +48,18 @@ st.markdown("""
         font-weight: bold;
         margin-bottom: 0.5rem;
     }
-    /* Updated button styling with icon */
+    /* Changed button color from blue (#2563EB) to green (#10B981) */
     .stButton>button {
-        background-color: #2563EB;
+        background-color: #10B981;
         color: white;
         border: none;
         padding: 0.5rem 2rem;
         border-radius: 6px;
         font-weight: 500;
-        display: inline-flex;
-        align-items: center;
-        justify-content: center;
     }
+    /* Changed hover color to darker green (#059669) */
     .stButton>button:hover {
-        background-color: #1D4ED8;
-    }
-    /* Button icon styling */
-    .button-icon {
-        margin-right: 8px;
+        background-color: #059669;
     }
     .footer {
         text-align: center;
@@ -79,30 +73,30 @@ st.markdown("""
 </style>
 """, unsafe_allow_html=True)
 
-# Main page header
+# Page headers
 st.markdown("<h1 class='main-header'>Smart Review Analysis Assistant</h1>", unsafe_allow_html=True)
 st.markdown("<p class='sub-header'>Topic Recognition, Sentiment Analysis, and Auto Reply in One Click</p>", unsafe_allow_html=True)
 
-# Function to load ML pipelines - cached to avoid reloading
+# ------- Load ML Pipelines -------
 @st.cache_resource
 def load_pipelines():
     """
-    Load all three machine learning pipelines:
-    1. Topic classifier using zero-shot classification
-    2. Sentiment analysis model
-    3. Reply generator for customer service responses
+    Load all required machine learning models for review analysis:
+    - Topic classifier using zero-shot classification
+    - Sentiment analysis model
+    - Customer reply generation model
     
-    Returns the models and topic labels for use in the app
+    Returns models and topic labels for use in the application
     """
-    # Topic Classification Model (Zero-shot classification)
+    # Define topic categories for classification
     topic_labels = [
         "billing", "account access", "customer service", "loans",
         "fraud", "technical issue", "credit card", "mobile app",
         "branch service", "transaction delay", "account closure", "information error"
     ]
     
-    # Use float32 for better CPU compatibility
-    dtype = torch.float32
+    # Ensure compatibility with CPU-only environments
+    dtype = torch.float32  # Use float32 for better CPU compatibility
     
     # Load topic classification model
     topic_classifier = pipeline(
@@ -121,9 +115,8 @@ def load_pipelines():
     tokenizer = AutoTokenizer.from_pretrained(model_name)
     model = AutoModelForCausalLM.from_pretrained(model_name)
     
-    # Function to generate customer service replies
     def generate_reply(text):
-        """Generate a customer service reply based on the input text"""
+        """Generate a polite customer service reply based on the given review text"""
         prompt_text = f"Please write a short, polite English customer service reply to the following customer comment:\n{text}"
         inputs = tokenizer(prompt_text, return_tensors="pt", truncation=True, max_length=512)
         
@@ -138,14 +131,14 @@ def load_pipelines():
                 early_stopping=True
             )
             
-        # Clean up generated text
+        # Clean up the generated text
         reply = tokenizer.decode(gen_ids[0][inputs.input_ids.shape[1]:], skip_special_tokens=True).strip()
         reply = reply.strip('"').replace('\n', ' ').replace('  ', ' ')
         return reply
     
     return topic_classifier, sentiment_classifier, generate_reply, topic_labels
 
-# Page layout and user input section
+# ------- Page Layout --------
 st.markdown("### Enter a review for instant analysis")
 
 # Updated example review as requested
@@ -158,45 +151,40 @@ user_review = st.text_area(
     height=120
 )
 
-# Custom button with icon
-analyze_button = st.markdown("""
-<button class="stButton primaryButton">
-    <span class="button-icon">📊</span> Analyze
-</button>
-""", unsafe_allow_html=True)
-
-# Check if button is clicked (using the regular button for functionality)
-if st.button("Analyze", key="hidden_button", help="Click to analyze the review"):
+# Button to trigger analysis
+if st.button("Analyze"):
     if not user_review.strip():
-        # Validation check
+        # Validate user input
         st.warning("Please enter a valid review!")
     else:
-        # Show loading spinner during analysis
+        # Show user-friendly loading message
         with st.spinner("Analyzing your review..."):
-            # Load models if not already loaded
+            # Load models on first use to avoid loading message on startup
             if "topic_pipe" not in st.session_state:
                 st.session_state.topic_pipe, st.session_state.sentiment_pipe, st.session_state.reply_generator, st.session_state.topic_labels = load_pipelines()
             
-            # Perform topic classification
+            # Run topic classification
             topic_result = st.session_state.topic_pipe(user_review, st.session_state.topic_labels, multi_label=False)
             topic = topic_result['labels'][0]
+            # Removed confidence percentage as requested
             
-            # Perform sentiment analysis
+            # Run sentiment analysis
             sentiment_result = st.session_state.sentiment_pipe(user_review)
             sentiment = sentiment_result[0]['label']
+            # Removed confidence percentage as requested
             
-            # Generate auto-reply
+            # Generate auto reply
             reply_text = st.session_state.reply_generator(user_review)
 
-        # Display results in a two-column layout
+        # Display results in a visually appealing format
         col1, col2 = st.columns(2)
         with col1:
             st.markdown(f"<div class='result-card topic-card'><p class='result-label'>Topic:</p>{topic}</div>", unsafe_allow_html=True)
         with col2:
             st.markdown(f"<div class='result-card sentiment-card'><p class='result-label'>Sentiment:</p>{sentiment}</div>", unsafe_allow_html=True)
         
-        # Display auto-reply suggestion
+        # Display suggested reply
         st.markdown(f"<div class='result-card reply-card'><p class='result-label'>Auto-reply Suggestion:</p>{reply_text}</div>", unsafe_allow_html=True)
 
 # Page footer
-st.markdown("<div class='footer'>© 2025 Review AI Assistant</div>", unsafe_allow_html=True)
+st.markdown("<div class='footer'>© 2024 Review AI Assistant</div>", unsafe_allow_html=True)