Update app.py

app.py

@@ -78,7 +78,7 @@ def load_json_data(path):
         if isinstance(data, dict):
             return "\n".join(f"{k}: {v}" for k, v in data.items() if not isinstance(v, (dict, list)))
         elif isinstance(data, list):
-            return "\n\n".join("\n".join(f"{k}: {v}" for k, v in item.items() if not isinstance(v, (dict, list))) for item in data if isinstance(item, dict))
+            return "\n\n".join("\n".join(f"{k}: {v}" for k, v in item.items() if isinstance(item, dict)) for item in data)
         else:
             return json.dumps(data, ensure_ascii=False, indent=2)
     except Exception as e:
@@ -104,7 +104,7 @@ def retrieve_chunks(question, index, embed_model, text_chunks, k=3):
 # ---------------- Groq Answer Generator ----------------
 def generate_answer_with_groq(question, context):
     url = "https://api.groq.com/openai/v1/chat/completions"
-    api_key = os.environ.get("GROQ_API_KEY")
+    api_key = os.getenv("GROQ_API_KEY")
     headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
     prompt = f"Customer asked: '{question}'\n\nHere is the relevant information to help:\n{context}"
     payload = {
@@ -132,6 +132,17 @@ def fetch_latest_incoming_message(client, conversation_sid):
 def send_twilio_message(client, conversation_sid, body):
     return client.conversations.v1.conversations(conversation_sid).messages.create(author="system", body=body)
 
+def get_latest_whatsapp_conversation_sid(client):
+    try:
+        conversations = client.conversations.v1.conversations.list(limit=20)
+        for convo in sorted(conversations, key=lambda c: c.date_created, reverse=True):
+            messages = convo.messages.list(limit=1)
+            if messages and any(m.author.startswith("whatsapp:") for m in messages):
+                return convo.sid
+    except Exception as e:
+        print("Error fetching latest conversation SID:", e)
+    return None
+
 # ---------------- Knowledge Base Setup ----------------
 def setup_knowledge_base():
     folder = "docs"
@@ -147,40 +158,42 @@ def setup_knowledge_base():
             text += load_json_data(path) + "\n"
         elif f.endswith(".csv"):
             with open(path, newline='', encoding='utf-8') as csvfile:
-                reader = csv.DictReader(csvfile)
-                for row in reader:
-                    text += ' | '.join(f"{k}: {v}" for k, v in row.items()) + "\n"
+                reader = csv.reader(csvfile)
+                text += "\n".join(", ".join(row) for row in reader) + "\n"
     return text
 
-# ---------------- Message Processing Loop ----------------
-def process_messages_loop(conversation_sid, index, text_chunks, tokenizer, embed_model):
-    processed_sids = set()
+# ---------------- App Logic ----------------
+def process_messages_loop():
+    embed_model = SentenceTransformer("sentence-transformers/all-MiniLM-L6-v2")
+    tokenizer = AutoTokenizer.from_pretrained("bert-base-uncased")
+    knowledge_text = setup_knowledge_base()
+    text_chunks = chunk_text(knowledge_text, tokenizer)
+    embeddings = embed_model.encode(text_chunks)
+    index = faiss.IndexFlatL2(embeddings.shape[1])
+    index.add(embeddings)
+
+    seen_sids = set()
+
     while True:
+        conversation_sid = get_latest_whatsapp_conversation_sid(twilio_client)
+        if not conversation_sid:
+            time.sleep(5)
+            continue
+
         message = fetch_latest_incoming_message(twilio_client, conversation_sid)
-        if message and message['sid'] not in processed_sids and message['timestamp'] > APP_START_TIME:
-            question = message['body']
-            relevant = retrieve_chunks(question, index, embed_model, text_chunks)
-            answer = generate_answer_with_groq(question, '\n'.join(relevant))
+        if message and message["sid"] not in seen_sids and message["timestamp"] > APP_START_TIME:
+            seen_sids.add(message["sid"])
+            question = message["body"]
+            chunks = retrieve_chunks(question, index, embed_model, text_chunks)
+            answer = generate_answer_with_groq(question, "\n\n".join(chunks))
             send_twilio_message(twilio_client, conversation_sid, answer)
-            processed_sids.add(message['sid'])
+
         time.sleep(5)
 
 # ---------------- Streamlit UI ----------------
-st.title("📱 ToyShop WhatsApp Chatbot")
-kb_text = setup_knowledge_base()
-tokenizer = AutoTokenizer.from_pretrained("bert-base-uncased")
-embed_model = SentenceTransformer("all-MiniLM-L6-v2")
-chunks = chunk_text(kb_text, tokenizer)
-embeddings = embed_model.encode(chunks)
-index = faiss.IndexFlatL2(len(embeddings[0]))
-index.add(np.array(embeddings))
-
-# Automatically fetch conversation SID
-conversations = twilio_client.conversations.v1.conversations.list(limit=5)
-conversation_sid = conversations[0].sid if conversations else None
-
-if conversation_sid:
-    st.success(f"Monitoring Twilio conversation SID: {conversation_sid}")
-    threading.Thread(target=process_messages_loop, args=(conversation_sid, index, chunks, tokenizer, embed_model), daemon=True).start()
-else:
-    st.error("No active Twilio conversation found.")
+st.title("ToyShop WhatsApp Assistant (Groq + Twilio)")
+
+if st.button("Start WhatsApp Bot"):
+    thread = threading.Thread(target=process_messages_loop)
+    thread.start()
+    st.success("WhatsApp assistant started and monitoring for new messages.")