Update app.py

app.py

@@ -1,6 +1,5 @@
 import streamlit as st
 from transformers import pipeline
-import re
 
 # Load models
 emotion_classifier = pipeline(
@@ -11,7 +10,6 @@ emotion_classifier = pipeline(
 intent_classifier = pipeline("zero-shot-classification", model="facebook/bart-large-mnli")
 text_generator = pipeline("text2text-generation", model="declare-lab/flan-alpaca-base")
 
-# Predefined customer intents
 candidate_tasks = [
     "change mobile plan",
     "top up balance",
@@ -23,7 +21,6 @@ candidate_tasks = [
     "upgrade device"
 ]
 
-# Emotion refinement
 urgent_emotions = {"anger", "frustration", "anxiety", "urgency", "afraid", "annoyed"}
 moderate_emotions = {"confused", "sad", "tired", "concerned", "sadness"}
 
@@ -55,20 +52,20 @@ def get_emotion_score(emotion):
 
 def generate_response(intent, human=True):
     prompt = (
-        f"You are a telecom customer service assistant. For the customer intent '{intent}', generate a 3-part response:\n"
-        "[Greeting: polite welcome.]\n"
-        "[Middle: mention the customer is currently on Plan X (¥X/month), and suggest switching to Plan Y with XXGB at ¥Y/month. Use fictional placeholder values.]\n"
+        f"You are a telecom customer service assistant. For the customer intent '{intent}', generate a 3-part response:
+"
+        "[Greeting: polite welcome.]
+"
+        "[Middle: mention the customer is currently on Plan X (¥X/month), and suggest switching to Plan Y with XXGB at ¥Y/month. Use fictional placeholder values.]
+"
         "[End: ask if they'd like to proceed with the new plan or need more details.]"
     )
     result = text_generator(prompt, max_new_tokens=100, do_sample=False)
     return result[0]['generated_text'].strip()
 
-
-# Streamlit config
 st.set_page_config(page_title="Smart Customer Support Assistant", layout="wide")
 st.sidebar.title("📁 Customer Selector")
 
-# Session state setup
 if "customers" not in st.session_state:
     st.session_state.customers = {"Customer A": [], "Customer B": [], "Customer C": []}
 if "chat_sessions" not in st.session_state:
@@ -88,17 +85,14 @@ if selected_customer not in st.session_state.chat_sessions:
 
 session = st.session_state.chat_sessions[selected_customer]
 
-# Title
 st.title("Smart Customer Support Assistant (for Agents Only)")
 
-# Conversation display
 st.markdown("### Conversation")
 for msg in session["chat"]:
     avatar = "👤" if msg['role'] == 'user' else ("🤖" if msg.get("auto") else "👨‍💼")
     with st.chat_message(msg['role'], avatar=avatar):
         st.markdown(msg['content'])
 
-# Customer input and Analyze
 col1, col2 = st.columns([6, 1])
 with col1:
     user_input = st.text_input("Enter customer message:", key="customer_input")
@@ -124,7 +118,7 @@ if analyze_clicked and user_input.strip():
 
     if final_score < 0.5 and top_intents:
         intent = top_intents[0]
-        response = generate_response(intent, human=False)
+        response = generate_response(intent, human=True)
         session["chat"].append({"role": "assistant", "content": response, "auto": True})
         session["system_result"] = None
         session["support_required"] = "🟢 Automated response handled this request."
@@ -139,11 +133,9 @@ if analyze_clicked and user_input.strip():
 
     st.rerun()
 
-# Support judgment display
 if session["support_required"]:
     st.markdown(f"### {session['support_required']}")
 
-# Agent input
 st.subheader("Agent Response Console")
 session["agent_reply"] = st.text_area("Compose your reply:", value=session["agent_reply"], key="agent_reply_box")
 if st.button("Send Reply"):
@@ -154,7 +146,6 @@ if st.button("Send Reply"):
         session["support_required"] = ""
         st.experimental_rerun()
 
-# If human needed: show analysis & suggestions
 if session["system_result"] is not None:
     st.markdown("#### Customer Status")
     st.markdown(f"- **Emotion:** {session['system_result']['emotion'].capitalize()}")
@@ -166,7 +157,6 @@ if session["system_result"] is not None:
         st.markdown(f"**• {intent.capitalize()}**")
         st.code(suggestion)
 
-# End conversation button
 if st.button("End Conversation"):
     session["chat"] = []
     session["system_result"] = None