Update frontend.py

frontend.py

@@ -1,3 +1,5 @@
+# [STREAMLIT FRONTEND - Product Feedback AI Assistant]
+
 import streamlit as st
 import requests
 import pandas as pd
@@ -7,7 +9,7 @@ from io import BytesIO
 import os
 import plotly.express as px
 
-st.set_page_config(page_title="NeuroPulse AI", page_icon="🧠", layout="wide")
+st.set_page_config(page_title="PM Feedback Assistant", page_icon="🧠", layout="wide")
 
 if os.path.exists("logo.png"):
     st.image("logo.png", width=180)
@@ -44,15 +46,15 @@ if st.session_state.dark_mode:
     </style>
     """, unsafe_allow_html=True)
 
-# Sidebar settings
+# Sidebar
 with st.sidebar:
-    st.header("⚙️ Global Settings")
+    st.header("⚙️ PM Config")
     st.session_state.dark_mode = st.toggle("🌙 Dark Mode", value=st.session_state.dark_mode)
     st.session_state.intelligence_mode = st.toggle("🧠 Intelligence Mode", value=st.session_state.intelligence_mode)
 
     api_token = st.text_input("🔐 API Token", value="my-secret-key", type="password")
     if not api_token or api_token.strip() == "my-secret-key":
-        st.warning("🧪 Running in demo mode — for full access, enter a valid API key.")
+        st.warning("🧪 Demo Mode — Not all features active.")
 
     backend_url = st.text_input("🌐 Backend URL", value="http://localhost:8000")
 
@@ -63,8 +65,8 @@ with st.sidebar:
     ])
     industry = st.selectbox("🏭 Industry", ["Auto-detect", "Generic", "E-commerce", "Healthcare", "Education"])
     product_category = st.selectbox("🧩 Product Category", ["Auto-detect", "General", "Mobile Devices", "Laptops"])
-    use_aspects = st.checkbox("🔬 Enable Aspect Analysis")
-    use_explain_bulk = st.checkbox("🧠 Generate Explanations (Bulk)")
+    use_aspects = st.checkbox("🔍 Detect Pain Points")
+    use_explain_bulk = st.checkbox("🧠 Generate PM Insight (Bulk)")
     verbosity = st.radio("🗣️ Response Style", ["Brief", "Detailed"])
     voice_lang = st.selectbox("🔈 Voice Language", ["en", "fr", "es", "de", "hi", "zh"])
 
@@ -78,14 +80,14 @@ def speak(text, lang='en'):
     mp3.seek(0)
     return mp3
 
-tab1, tab2 = st.tabs(["🧠 Single Review", "📚 Bulk CSV"])
+tab1, tab2 = st.tabs(["🧠 Analyze Review", "📚 Bulk Reviews"])
 
-# ==== SINGLE REVIEW ====
+# === SINGLE REVIEW ===
 with tab1:
-    st.title("🧠 NeuroPulse AI – Multimodal Review Analyzer")
-    st.markdown("<div style='font-size:16px;color:#888;'>Minimum 20–50 words recommended.</div>", unsafe_allow_html=True)
+    st.title("📊 Product Feedback AI Assistant")
+    st.markdown("Get insights from real user feedback to reduce churn and improve product strategy.")
 
-    review = st.text_area("📝 Enter Review", value=st.session_state.review, height=180)
+    review = st.text_area("📝 Enter Customer Feedback", value=st.session_state.review, height=180)
     st.session_state.review = review
 
     col1, col2, col3 = st.columns(3)
@@ -94,8 +96,8 @@ with tab1:
     with col2:
         if st.button("🎲 Example"):
             st.session_state.review = (
-                "I love this phone! Super fast performance, great battery, and smooth UI. "
-                "Camera is awesome too, though the price is a bit high. Overall, very happy."
+                "The app crashes every time I try to checkout. It's so slow and unresponsive. "
+                "Customer support never replied. I'm switching to another brand."
             )
             st.session_state.trigger_example_analysis = True
             st.rerun()
@@ -108,7 +110,7 @@ with tab1:
     if (analyze or st.session_state.trigger_example_analysis) and st.session_state.review:
         st.session_state.trigger_example_analysis = False
         st.session_state.followup_answer = None
-        with st.spinner("Analyzing..."):
+        with st.spinner("Analyzing feedback..."):
             try:
                 model = None if sentiment_model == "Auto-detect" else sentiment_model
                 payload = {
@@ -131,21 +133,27 @@ with tab1:
 
     data = st.session_state.last_response
     if data:
-        st.subheader("📌 Summary")
+        st.subheader("📌 PM Insight Summary")
         st.info(data["summary"])
-        st.caption("🧠 Summary Model: facebook/bart-large-cnn | " + verbosity + " response")
-        st.markdown(f"**Context:** `{data['industry']}` | `{data['product_category']}` | `Web`")
+        st.caption("🔎 Summary Model: facebook/bart-large-cnn | " + verbosity + " response")
+        st.markdown(f"**Industry:** `{data['industry']}` | **Category:** `{data['product_category']}` | **Device:** Web")
 
         st.metric("📊 Sentiment", data["sentiment"]["label"], delta=f"{data['sentiment']['score']:.2%}")
         st.info(f"💢 Emotion: {data['emotion']}")
-        st.subheader("🔊 Audio")
+
+        if "churn_risk" in data:
+            st.warning(f"⚠️ Estimated Churn Risk: {data['churn_risk']}")
+        if "pain_points" in data and data["pain_points"]:
+            st.error("🔍 Pain Points: " + ", ".join(data["pain_points"]))
+
+        st.subheader("🔊 Audio Summary")
         audio = speak(data["summary"], lang=voice_lang)
-        st.download_button("⬇️ Download Summary Audio", audio.read(), "summary.mp3")
+        st.download_button("⬇️ Download Audio", audio.read(), "summary.mp3")
 
-        st.markdown("### 🔁 Got questions?")
-        sample_questions = ["What did the user like most?", "Any complaints mentioned?", "Is it positive overall?"]
-        selected_q = st.selectbox("💡 Sample Questions", ["Type your own..."] + sample_questions)
-        custom_q = selected_q if selected_q != "Type your own..." else st.text_input("🔍 Ask a follow-up")
+        st.markdown("### 🔁 Ask a Follow-Up")
+        sample_questions = ["What made the user upset?", "Any feature complaints?", "How urgent is this?"]
+        selected_q = st.selectbox("💡 Suggested Questions", ["Type your own..."] + sample_questions)
+        custom_q = selected_q if selected_q != "Type your own..." else st.text_input("🔍 Follow-up Question")
 
         if custom_q:
             with st.spinner("Thinking..."):
@@ -165,66 +173,5 @@ with tab1:
                     st.error(f"⚠️ Follow-up error: {e}")
 
     if st.session_state.followup_answer:
-        st.subheader("🔁 Follow-Up Answer")
+        st.subheader("✅ Answer")
         st.success(st.session_state.followup_answer)
-
-# ==== BULK CSV ====
-with tab2:
-    st.title("📚 Bulk CSV Upload")
-    st.markdown("""
-    Upload a CSV with columns:<br>
-    <code>review</code>, <code>industry</code>, <code>product_category</code>, <code>device</code>, <code>follow_up</code> (optional)
-    """, unsafe_allow_html=True)
-
-    with st.expander("📄 Sample CSV"):
-        with open("sample_reviews.csv", "rb") as f:
-            st.download_button("⬇️ Download sample CSV", f, file_name="sample_reviews.csv")
-
-    uploaded_file = st.file_uploader("📁 Upload your CSV", type="csv")
-
-    if uploaded_file:
-        if not api_token:
-            st.error("🔐 Please enter your API token in the sidebar.")
-        else:
-            try:
-                df = pd.read_csv(uploaded_file)
-                if "review" not in df.columns:
-                    st.error("CSV must contain a `review` column.")
-                else:
-                    for col in ["industry", "product_category", "device", "follow_up"]:
-                        if col not in df.columns:
-                            df[col] = ["Auto-detect"] * len(df)
-                        df[col] = df[col].fillna("Auto-detect").astype(str)
-
-                    df["industry"] = df["industry"].apply(lambda x: "Generic" if x.lower() == "auto-detect" else x)
-                    df["product_category"] = df["product_category"].apply(lambda x: "General" if x.lower() == "auto-detect" else x)
-                    df["device"] = df["device"].apply(lambda x: "Web" if x.lower() == "auto-detect" else x)
-
-                    if st.button("📊 Analyze Bulk Reviews", use_container_width=True):
-                        with st.spinner("Processing..."):
-                            try:
-                                payload = {
-                                    "reviews": df["review"].tolist(),
-                                    "model": None if sentiment_model == "Auto-detect" else sentiment_model,
-                                    "industry": df["industry"].tolist(),
-                                    "product_category": df["product_category"].tolist(),
-                                    "device": df["device"].tolist(),
-                                    "follow_up": df["follow_up"].tolist(),
-                                    "explain": use_explain_bulk,
-                                    "aspects": use_aspects,
-                                    "intelligence": st.session_state.intelligence_mode
-                                }
-                                res = requests.post(f"{backend_url}/bulk/?token={api_token}", json=payload)
-                                if res.status_code == 200:
-                                    results = pd.DataFrame(res.json()["results"])
-                                    st.dataframe(results)
-                                    if "sentiment" in results.columns:
-                                        fig = px.pie(results, names="sentiment", title="Sentiment Distribution")
-                                        st.plotly_chart(fig)
-                                    st.download_button("⬇️ Download Results CSV", results.to_csv(index=False), "results.csv", mime="text/csv")
-                                else:
-                                    st.error(f"❌ Bulk Error {res.status_code}: {res.json().get('detail')}")
-                            except Exception as e:
-                                st.error(f"🚨 Bulk Processing Error: {e}")
-            except Exception as e:
-                st.error(f"❌ File Read Error: {e}")