Update app.py

app.py

@@ -16,7 +16,7 @@ from io import StringIO
 from pdfminer.high_level import extract_text_to_fp
 from pdfminer.layout import LAParams
 
-# --- PDF Extraction (Improved for Tables & Paragraphs) ---
+# --- PDF Extraction ---
 def extract_text_from_pdf(pdf_path):
     output_string = StringIO()
     with open(pdf_path, 'rb') as file:
@@ -29,7 +29,7 @@ def clean_extracted_text(text):
     for line in lines:
         line = line.strip()
         if line:
-            line = ' '.join(line.split())  # remove extra spaces
+            line = ' '.join(line.split())
             cleaned.append(line)
     return '\n'.join(cleaned)
 
@@ -41,7 +41,7 @@ def extract_text_from_docx(docx_path):
     except:
         return ""
 
-# --- Chunking & Retrieval ---
+# --- Chunking ---
 def chunk_text(text, tokenizer, chunk_size=128, chunk_overlap=32, max_tokens=512):
     tokens = tokenizer.tokenize(text)
     chunks = []
@@ -95,21 +95,6 @@ def generate_answer_with_groq(question, context):
     return response.json()['choices'][0]['message']['content'].strip()
 
 # --- Twilio Functions ---
-def get_latest_whatsapp_conversation_sid(client):
-    conversations = client.conversations.v1.conversations.list(limit=10)
-    for convo in conversations:
-        try:
-            participants = client.conversations.v1.conversations(convo.sid).participants.list()
-            for p in participants:
-                if (p.identity and p.identity.startswith("whatsapp:")) or (
-                    p.messaging_binding and p.messaging_binding.get("address", "").startswith("whatsapp:")
-                ):
-                    return convo.sid
-        except:
-            continue
-    return None
-
-
 def fetch_latest_incoming_message(client, conversation_sid):
     messages = client.conversations.v1.conversations(conversation_sid).messages.list(limit=10)
     for msg in reversed(messages):
@@ -149,31 +134,50 @@ def setup_knowledge_base():
     return index, model, chunks
 
 # --- Monitor Conversations ---
-def monitor_all_conversations():
-    print("➡️ Monitoring all new incoming WhatsApp conversations...")
+def start_conversation_monitor(client, index, embed_model, text_chunks):
+    processed_convos = set()
+    last_processed_timestamp = {}
+
+    def poll_conversation(convo_sid):
+        while True:
+            try:
+                latest_msg = fetch_latest_incoming_message(client, convo_sid)
+                if latest_msg:
+                    msg_time = latest_msg["timestamp"]
+                    if convo_sid not in last_processed_timestamp or msg_time > last_processed_timestamp[convo_sid]:
+                        last_processed_timestamp[convo_sid] = msg_time
+                        question = latest_msg["body"]
+                        sender = latest_msg["author"]
+                        print(f"\n📥 New message from {sender} in {convo_sid}: {question}")
+                        context = "\n\n".join(retrieve_chunks(question, index, embed_model, text_chunks))
+                        answer = generate_answer_with_groq(question, context)
+                        send_twilio_message(client, convo_sid, answer)
+                        print(f"📤 Replied to {sender}: {answer}")
+                time.sleep(3)
+            except Exception as e:
+                print(f"❌ Error in convo {convo_sid} polling:", e)
+                time.sleep(5)
 
     def poll_new_conversations():
-        processed_convos = set()
+        print("➡️ Monitoring for new WhatsApp conversations...")
         while True:
             try:
                 conversations = client.conversations.v1.conversations.list(limit=20)
                 for convo in conversations:
                     if convo.sid not in processed_convos:
-                        # Check if WhatsApp participant exists
                         participants = client.conversations.v1.conversations(convo.sid).participants.list()
                         for p in participants:
                             address = p.messaging_binding.get("address", "") if p.messaging_binding else ""
                             if address.startswith("whatsapp:"):
+                                print(f"🆕 New WhatsApp convo found: {convo.sid}")
                                 processed_convos.add(convo.sid)
-                                print(f"🆕 New conversation detected: {convo.sid}")
                                 threading.Thread(target=poll_conversation, args=(convo.sid,), daemon=True).start()
             except Exception as e:
-                print("❌ Error while polling for new conversations:", e)
+                print("❌ Error polling conversations:", e)
             time.sleep(5)
 
     threading.Thread(target=poll_new_conversations, daemon=True).start()
 
-
 # --- Streamlit UI ---
 st.set_page_config(page_title="Quasa – A Smart WhatsApp Chatbot", layout="wide")
 st.title("📱 Quasa – A Smart WhatsApp Chatbot")
@@ -191,8 +195,8 @@ if not all([account_sid, auth_token, GROQ_API_KEY]):
 if all([account_sid, auth_token, GROQ_API_KEY]):
     os.environ["GROQ_API_KEY"] = GROQ_API_KEY
     client = Client(account_sid, auth_token)
-    latest_sid = get_latest_whatsapp_conversation_sid(client)
 
-    st.success("🟢 Monitoring new WhatsApp conversations... Waiting for messages.")
-index, model, chunks = setup_knowledge_base()
-threading.Thread(target=start_conversation_monitor, args=(client, index, model, chunks), daemon=True).start()
+    st.success("🟢 Monitoring new WhatsApp conversations...")
+    index, model, chunks = setup_knowledge_base()
+    threading.Thread(target=start_conversation_monitor, args=(client, index, model, chunks), daemon=True).start()
+    st.info("⏳ Waiting for new messages...")