Update app.py

app.py

@@ -2,7 +2,6 @@ import os
 import time
 import streamlit as st
 from twilio.rest import Client
-from twilio.base.exceptions import TwilioRestException
 from pdfminer.high_level import extract_text
 from sentence_transformers import SentenceTransformer
 from transformers import AutoTokenizer
@@ -12,14 +11,17 @@ import docx
 from groq import Groq
 import PyPDF2
 import requests
+from streamlit_autorefresh import st_autorefresh
 
+# Extract text from PDF with fallback
 # --- Document Loaders ---
 def extract_text_from_pdf(pdf_path):
     try:
         text = ""
         with open(pdf_path, 'rb') as file:
             pdf_reader = PyPDF2.PdfReader(file)
-            for page in pdf_reader.pages:
+            for page_num in range(len(pdf_reader.pages)):
+                page = pdf_reader.pages[page_num]
                 page_text = page.extract_text()
                 if page_text:
                     text += page_text
@@ -49,6 +51,7 @@ def retrieve_chunks(question, index, embed_model, text_chunks, k=3):
     D, I = index.search(np.array([question_embedding]), k)
     return [text_chunks[i] for i in I[0]]
 
+# Generate answer using Groq API with retries and timeout
 def generate_answer_with_groq(question, context, retries=3, delay=2):
     url = "https://api.groq.com/openai/v1/chat/completions"
     api_key = os.environ.get("GROQ_API_KEY")
@@ -97,7 +100,7 @@ def generate_answer_with_groq(question, context, retries=3, delay=2):
         except Exception as e:
             return f"⚠️ Groq API Error: {e}"
 
-# --- Twilio Chat Handlers ---
+# Twilio message fetch and send
 def fetch_latest_incoming_message(account_sid, auth_token, conversation_sid):
     client = Client(account_sid, auth_token)
     messages = client.conversations.v1.conversations(conversation_sid).messages.list(limit=10)
@@ -114,60 +117,72 @@ def send_twilio_message(account_sid, auth_token, conversation_sid, body):
     except Exception as e:
         return str(e)
 
-# --- Streamlit UI ---
-st.set_page_config(page_title="SMEHelpBot – WhatsApp Integration", layout="wide")
-st.title("📱 SMEHelpBot + WhatsApp (via Twilio)")
+# Streamlit UI
+st.set_page_config(page_title="Quasa – A Smart WhatsApp Chatbot", layout="wide")
+st.title("📱 Quasa – A Smart WhatsApp Chatbot")
+
+if "last_index" not in st.session_state:
+    st.session_state.last_index = -1
 
-# Load from Hugging Face secrets or fallback to manual input
 account_sid = st.secrets.get("TWILIO_SID")
 auth_token = st.secrets.get("TWILIO_TOKEN")
 GROQ_API_KEY = st.secrets.get("GROQ_API_KEY")
 
 if not all([account_sid, auth_token, GROQ_API_KEY]):
     st.warning("⚠️ Some secrets not found. Please enter missing credentials below:")
-    account_sid = st.text_input("🔐 Twilio SID", value=account_sid or "")
-    auth_token = st.text_input("🔐 Twilio Auth Token", type="password", value=auth_token or "")
-    GROQ_API_KEY = st.text_input("🔐 GROQ API Key", type="password", value=GROQ_API_KEY or "")
+    account_sid = st.text_input("Twilio SID", value=account_sid or "")
+    auth_token = st.text_input("Twilio Auth Token", type="password", value=auth_token or "")
+    GROQ_API_KEY = st.text_input("GROQ API Key", type="password", value=GROQ_API_KEY or "")
+
+enable_autorefresh = st.checkbox("🔄 Enable Auto-Refresh", value=True)
+interval_seconds = st.selectbox("Refresh Interval (seconds)", options=[5, 10, 15, 30, 60], index=5)
+
+if enable_autorefresh:
+    st_autorefresh(interval=interval_seconds * 1000, key="auto-refresh")
 
-if all([account_sid, auth_token, conversation_sid, GROQ_API_KEY]):
+if all([account_sid, auth_token, GROQ_API_KEY, conversation_sid]):
     os.environ["GROQ_API_KEY"] = GROQ_API_KEY
 
-    @st.cache_resource
+    @st.cache_data(show_spinner=False)
     def setup_knowledge_base():
         folder_path = "docs"
         all_text = ""
-        for file in os.listdir(folder_path):
-            if file.endswith(".pdf"):
-                all_text += extract_text_from_pdf(os.path.join(folder_path, file)) + "\n"
-            elif file.endswith((".docx", ".doc")):
-                all_text += extract_text_from_docx(os.path.join(folder_path, file)) + "\n"
-        tokenizer = AutoTokenizer.from_pretrained('bert-base-uncased')
-        chunks = chunk_text(all_text, tokenizer)
-        model = SentenceTransformer('all-mpnet-base-v2')
-        embeddings = model.encode(chunks)
-        dim = embeddings[0].shape[0]
-        index = faiss.IndexFlatL2(dim)
-        index.add(np.array(embeddings))
-        return index, model, chunks
+        try:
+            for file in os.listdir(folder_path):
+                if file.endswith(".pdf"):
+                    all_text += extract_text_from_pdf(os.path.join(folder_path, file)) + "\n"
+                elif file.endswith((".docx", ".doc")):
+                    all_text += extract_text_from_docx(os.path.join(folder_path, file)) + "\n"
+            tokenizer = AutoTokenizer.from_pretrained('bert-base-uncased')
+            chunks = chunk_text(all_text, tokenizer)
+            model = SentenceTransformer('all-mpnet-base-v2')
+            embeddings = model.encode(chunks)
+            dim = embeddings[0].shape[0]
+            index = faiss.IndexFlatL2(dim)
+            index.add(np.array(embeddings).astype('float32'))
+            return index, model, chunks
+        except Exception as e:
+            st.error(f"Error setting up knowledge base: {e}")
+            return None, None, None
 
     index, embedding_model, text_chunks = setup_knowledge_base()
+    if index is None:
+        st.stop()
 
     st.success("✅ Knowledge base ready. Monitoring WhatsApp...")
 
-conversation_sid = st.text_input("💬 Enter Twilio Conversation SID", placeholder="e.g. CHxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx")
-
-    if st.button("🔁 Check for New WhatsApp Query"):
-        with st.spinner("Checking messages..."):
-            question, sender, msg_index = fetch_latest_incoming_message(account_sid, auth_token, conversation_sid)
-            if question:
-                st.info(f"📥 New Question from {sender}:\n\n> {question}")
-                relevant_chunks = retrieve_chunks(question, index, embedding_model, text_chunks)
-                context = "\n\n".join(relevant_chunks)
-                answer = generate_answer_with_groq(question, context)
-                send_twilio_message(account_sid, auth_token, conversation_sid, answer)
-                st.success("📤 Answer sent via WhatsApp!")
-                st.markdown(f"### ✨ Answer:\n\n{answer}")
-            else:
-                st.warning("No new messages from users found.")
+    with st.spinner("⏳ Checking for new WhatsApp messages..."):
+        question, sender, msg_index = fetch_latest_incoming_message(account_sid, auth_token, conversation_sid)
+        if question and msg_index > st.session_state.last_index:
+            st.session_state.last_index = msg_index
+            st.info(f"📥 New Question from {sender}:\n\n> {question}")
+            relevant_chunks = retrieve_chunks(question, index, embedding_model, text_chunks)
+            context = "\n\n".join(relevant_chunks)
+            answer = generate_answer_with_groq(question, context)
+            send_twilio_message(account_sid, auth_token, conversation_sid, answer)
+            st.success("📤 Answer sent via WhatsApp!")
+            st.markdown(f"### ✨ Answer:\n\n{answer}")
+        else:
+            st.caption("✅ No new message yet. Waiting for refresh...")
 else:
-    st.warning("❗ Please provide all required credentials including Conversation SID.")
+    st.warning("❗ Please provide all required credentials and conversation SID.")