Update app.py

app.py

@@ -1,35 +1,120 @@
+import nest_asyncio
+nest_asyncio.apply()
+
+import streamlit as st
+import asyncio
+import subprocess
 from transformers import pipeline
+from streamlit.components.v1 import html
+
+# -----------------------------------------------------------
+# Hugging Face CLI Login
+# This will prompt you in the terminal for your Hugging Face token.
+# Ensure you have your token ready.
+subprocess.run(["huggingface-cli", "login"], shell=True)
+# -----------------------------------------------------------
+
+# Initialize session state for timer and results
+if 'result' not in st.session_state:
+    st.session_state.result = {}
+if 'timer_started' not in st.session_state:
+    st.session_state.timer_started = False
+if 'timer_frozen' not in st.session_state:
+    st.session_state.timer_frozen = False
 
-# Step 1: Define the sentiment analysis pipeline.
-# Here, we use a text classification model.
-sentiment_pipe = pipeline("text-classification", model="mixedbread-ai/mxbai-rerank-base-v1")
+# Timer component using HTML and JavaScript
+def timer():
+    return """
+    <div id="timer" style="font-size:16px;color:#666;margin-bottom:10px;">⏱️ Elapsed: 00:00</div>
+    <script>
+    (function() {
+        var start = Date.now();
+        var timerElement = document.getElementById('timer');
+        // Remove any existing freeze flag
+        localStorage.removeItem("freezeTimer");
+        var interval = setInterval(function() {
+            // If freeze flag is set, stop the timer
+            if(localStorage.getItem("freezeTimer") === "true"){
+                clearInterval(interval);
+                timerElement.style.color = '#00cc00';
+                return;
+            }
+            var elapsed = Date.now() - start;
+            var minutes = Math.floor(elapsed / 60000);
+            var seconds = Math.floor((elapsed % 60000) / 1000);
+            timerElement.innerHTML = '⏱️ Elapsed: ' + 
+                (minutes < 10 ? '0' : '') + minutes + ':' + 
+                (seconds < 10 ? '0' : '') + seconds;
+        }, 1000);
+    })();
+    </script>
+    """
 
-# Step 2: Define the text generation pipeline with Gemma.
-gemma_pipe = pipeline("text-generation", model="google/gemma-3-1b-it")
+st.set_page_config(page_title="Sentiment & Report Generator", page_icon="📝")
+st.header("Sentiment Analysis & Report Generation with Gemma")
 
-# Example input text that we want to analyze.
-text = "I love this new product. It has exceeded my expectations and I feel very happy about it."
+# Load models with caching to avoid reloading on every run
+@st.cache_resource
+def load_models():
+    sentiment_pipe = pipeline("text-classification", model="mixedbread-ai/mxbai-rerank-base-v1")
+    gemma_pipe = pipeline("text-generation", model="google/gemma-3-1b-it")
+    return sentiment_pipe, gemma_pipe
 
-# Perform sentiment analysis on the text.
-sentiment_result = sentiment_pipe(text)
-print("Sentiment Analysis Result:")
-print(sentiment_result)
+sentiment_pipe, gemma_pipe = load_models()
 
-# Prepare a prompt that includes the original text and the sentiment result.
-# The prompt instructs the Gemma model to generate a detailed summary report.
-prompt = f"""
+# User input: a text area for the text to analyze
+user_input = st.text_area("Enter your text for sentiment analysis and report generation:")
+
+if st.button("Generate Report"):
+    if not user_input.strip():
+        st.error("Please enter some text!")
+    else:
+        # Start the timer if not already started
+        if not st.session_state.timer_started and not st.session_state.timer_frozen:
+            st.session_state.timer_started = True
+            html(timer(), height=50)
+        
+        # Initialize status message and progress bar
+        status_text = st.empty()
+        progress_bar = st.progress(0)
+        
+        try:
+            # ---------------------------
+            # Stage 1: Sentiment Analysis
+            status_text.markdown("**🔍 Running sentiment analysis...**")
+            progress_bar.progress(0)
+            sentiment_result = sentiment_pipe(user_input)
+            progress_bar.progress(50)
+            
+            # ---------------------------
+            # Stage 2: Generate Report using Gemma
+            status_text.markdown("**📝 Generating report with Gemma...**")
+            # Build a prompt that includes the original text and the sentiment analysis result.
+            prompt = f"""
 Generate a detailed report based on the following analysis.
 
 Original text:
-"{text}"
+"{user_input}"
 
 Sentiment analysis result:
 {sentiment_result}
 
 Please provide a concise summary report explaining the sentiment and key insights.
 """
-
-# Use the Gemma pipeline to generate the summary report.
-report = gemma_pipe(prompt, max_length=200)
-print("\nGenerated Report:")
-print(report[0]['generated_text'])
+            report = gemma_pipe(prompt, max_length=200)
+            progress_bar.progress(100)
+            status_text.success("**✅ Generation complete!**")
+            
+            # Freeze the timer immediately upon completion.
+            html("<script>localStorage.setItem('freezeTimer', 'true');</script>", height=0)
+            st.session_state.timer_frozen = True
+            
+            # Display the results
+            st.write("**Sentiment Analysis Result:**", sentiment_result)
+            st.write("**Generated Report:**", report[0]['generated_text'])
+            
+        except Exception as e:
+            # Remove timer element if an error occurs
+            html("<script>document.getElementById('timer').remove();</script>")
+            status_text.error(f"**❌ Error:** {str(e)}")
+            progress_bar.empty()