Update app.py

app.py

@@ -23,16 +23,18 @@ import re
 APP_START_TIME = datetime.datetime.now(datetime.timezone.utc)
 os.environ["PYTORCH_JIT"] = "0"
 
+# Twilio Setup
+TWILIO_ACCOUNT_SID = os.getenv("TWILIO_ACCOUNT_SID")
+TWILIO_AUTH_TOKEN = os.getenv("TWILIO_AUTH_TOKEN")
+twilio_client = Client(TWILIO_ACCOUNT_SID, TWILIO_AUTH_TOKEN)
+
 # ---------------- PDF & DOCX & JSON Extraction ----------------
 def _extract_tables_from_page(page):
     tables = page.extract_tables()
     formatted_tables = []
     for table in tables:
-        formatted_table = []
-        for row in table:
-            formatted_row = [cell if cell is not None else "" for cell in row]
-            formatted_table.append(formatted_row)
-        formatted_tables.append(formatted_table)
+        formatted_row = [[cell if cell is not None else "" for cell in row] for row in table]
+        formatted_tables.append(formatted_row)
     return formatted_tables
 
 def extract_text_from_pdf(pdf_path):
@@ -46,48 +48,40 @@ def extract_text_from_pdf(pdf_path):
                 if text:
                     text_output.write(text + "\n\n")
     except Exception as e:
-        print(f"pdfplumber error: {e}")
         with open(pdf_path, 'rb') as file:
             extract_text_to_fp(file, text_output, laparams=LAParams(), output_type='text')
     return text_output.getvalue(), all_tables
 
 def _format_tables_internal(tables):
-    formatted_tables_str = []
+    formatted = []
     for table in tables:
         with StringIO() as csvfile:
             writer = csv.writer(csvfile)
             writer.writerows(table)
-            formatted_tables_str.append(csvfile.getvalue())
-    return "\n\n".join(formatted_tables_str)
+            formatted.append(csvfile.getvalue())
+    return "\n\n".join(formatted)
 
 def clean_extracted_text(text):
     return '\n'.join(' '.join(line.strip().split()) for line in text.splitlines() if line.strip())
 
-def extract_text_from_docx(docx_path):
+def extract_text_from_docx(path):
     try:
-        doc = docx.Document(docx_path)
-        return '\n'.join(para.text for para in doc.paragraphs)
+        doc = docx.Document(path)
+        return '\n'.join(p.text for p in doc.paragraphs)
     except:
         return ""
 
-def load_json_data(json_path):
+def load_json_data(path):
     try:
-        with open(json_path, 'r', encoding='utf-8') as f:
+        with open(path, 'r', encoding='utf-8') as f:
             data = json.load(f)
         if isinstance(data, dict):
-            # Flatten dictionary values (avoiding nested structures as strings)
-            return "\n".join(f"{key}: {value}" for key, value in data.items() if not isinstance(value, (dict, list)))
+            return "\n".join(f"{k}: {v}" for k, v in data.items() if not isinstance(v, (dict, list)))
         elif isinstance(data, list):
-            # Flatten list of dictionaries
-            all_items = []
-            for item in data:
-                if isinstance(item, dict):
-                    all_items.append("\n".join(f"{key}: {value}" for key, value in item.items() if not isinstance(value, (dict, list))))
-            return "\n\n".join(all_items)
+            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))
         else:
             return json.dumps(data, ensure_ascii=False, indent=2)
     except Exception as e:
-        print(f"JSON read error: {e}")
         return ""
 
 # ---------------- Chunking ----------------
@@ -99,7 +93,6 @@ def chunk_text(text, tokenizer, chunk_size=128, chunk_overlap=32):
         end = min(start + chunk_size, len(tokens))
         chunk = tokens[start:end]
         chunks.append(tokenizer.convert_tokens_to_string(chunk))
-        if end == len(tokens): break
         start += chunk_size - chunk_overlap
     return chunks
 
@@ -112,36 +105,18 @@ def retrieve_chunks(question, index, embed_model, text_chunks, k=3):
 def generate_answer_with_groq(question, context):
     url = "https://api.groq.com/openai/v1/chat/completions"
     api_key = os.environ.get("GROQ_API_KEY")
-    headers = {
-        "Authorization": f"Bearer {api_key}",
-        "Content-Type": "application/json",
-    }
-    prompt = (
-        f"Customer asked: '{question}'\n\n"
-        f"Here is the relevant information to help:\n{context}\n\n"
-        f"Respond in a friendly and helpful tone as a toy shop support agent, "
-        f"addressing the customer by their name if it's available in the context."
-    )
+    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 = {
         "model": "llama3-8b-8192",
         "messages": [
-            {
-                "role": "system",
-                "content": (
-                    "You are ToyBot, a friendly WhatsApp assistant for an online toy shop. "
-                    "Help customers with toys, delivery, and returns in a helpful tone. "
-                    "When responding, try to find the customer's name in the provided context "
-                    "and address them directly. If the context contains order details and status, "
-                    "include that information in your response."
-                )
-            },
+            {"role": "system", "content": "You are ToyBot, a friendly WhatsApp assistant..."},
             {"role": "user", "content": prompt},
         ],
         "temperature": 0.5,
         "max_tokens": 300,
     }
     response = requests.post(url, headers=headers, json=payload)
-    response.raise_for_status()
     return response.json()['choices'][0]['message']['content'].strip()
 
 # ---------------- Twilio Integration ----------------
@@ -150,101 +125,62 @@ def fetch_latest_incoming_message(client, conversation_sid):
         messages = client.conversations.v1.conversations(conversation_sid).messages.list()
         for msg in reversed(messages):
             if msg.author.startswith("whatsapp:"):
-                return {
-                    "sid": msg.sid,
-                    "body": msg.body,
-                    "author": msg.author,
-                    "timestamp": msg.date_created,
-                }
-    except TwilioRestException as e:
-        print(f"Twilio error: {e}")
-    return None
+                return {"sid": msg.sid, "body": msg.body, "author": msg.author, "timestamp": msg.date_created}
+    except TwilioRestException:
+        return None
 
 def send_twilio_message(client, conversation_sid, body):
-    return client.conversations.v1.conversations(conversation_sid).messages.create(
-        author="system", body=body
-    )
+    return client.conversations.v1.conversations(conversation_sid).messages.create(author="system", body=body)
 
 # ---------------- Knowledge Base Setup ----------------
 def setup_knowledge_base():
-    folder_path = "docs"
-    all_text = ""
-
-    for filename in os.listdir(folder_path):
-        file_path = os.path.join(folder_path, filename)
-        if filename.endswith(".pdf"):
-            text, tables = extract_text_from_pdf(file_path)
-            all_text += clean_extracted_text(text) + "\n"
-            all_text += _format_tables_internal(tables) + "\n"
-        elif filename.endswith(".docx"):
-            text = extract_text_from_docx(file_path)
-            all_text += clean_extracted_text(text) + "\n"
-        elif filename.endswith(".json"):
-            text = load_json_data(file_path)
-            all_text += text + "\n"
-        elif filename.endswith(".csv"):
-            try:
-                with open(file_path, newline='', encoding='utf-8') as csvfile:
-                    reader = csv.DictReader(csvfile)
-                    for row in reader:
-                        line = ' | '.join(f"{k}: {v}" for k, v in row.items())
-                        all_text += line + "\n"
-            except Exception as e:
-                print(f"CSV read error: {e}")
-
-    tokenizer = AutoTokenizer.from_pretrained('bert-base-uncased')
-    chunks = chunk_text(all_text, tokenizer)
-    model = SentenceTransformer('all-mpnet-base-v2')
-    embeddings = model.encode(chunks, show_progress_bar=False)
-    dim = embeddings[0].shape[0]
-    index = faiss.IndexFlatL2(dim)
-    index.add(np.array(embeddings).astype('float32'))
-    return index, model, chunks
-
-# ---------------- Monitor Twilio Conversations ----------------
-def start_conversation_monitor(client, index, embed_model, text_chunks):
-    processed_convos = set()
-    last_processed_timestamp = {}
-
-    def poll_convo(convo_sid):
-        while True:
-            latest_msg = fetch_latest_incoming_message(client, convo_sid)
-            if latest_msg:
-                msg_time = latest_msg["timestamp"]
-                if msg_time > APP_START_TIME:
-                    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"📩 New message from {sender}: {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)
-            time.sleep(5)
-
-    for convo in client.conversations.v1.conversations.list():
-    # convo.date_created is a datetime object in UTC, compare it with APP_START_TIME
-        if convo.date_created is not None and convo.date_created > APP_START_TIME:
-            if convo.sid not in processed_convos:
-                processed_convos.add(convo.sid)
-                threading.Thread(target=poll_convo, args=(convo.sid,), daemon=True).start()
-
-
-# ---------------- Main Entry ----------------
-if __name__ == "__main__":
-    st.title("🤖 ToyBot WhatsApp Assistant")
-    st.write("Initializing knowledge base...")
-
-    index, model, chunks = setup_knowledge_base()
-
-    st.success("Knowledge base loaded.")
-    st.write("Waiting for WhatsApp messages...")
-
-    account_sid = os.environ.get("TWILIO_ACCOUNT_SID")
-    auth_token = os.environ.get("TWILIO_AUTH_TOKEN")
-    if not account_sid or not auth_token:
-        st.error("❌ Twilio credentials not set.")
-    else:
-        client = Client(account_sid, auth_token)
-        start_conversation_monitor(client, index, model, chunks)
-        st.info("✅ Bot is now monitoring Twilio conversations.")
+    folder = "docs"
+    text = ""
+    for f in os.listdir(folder):
+        path = os.path.join(folder, f)
+        if f.endswith(".pdf"):
+            t, tables = extract_text_from_pdf(path)
+            text += clean_extracted_text(t) + "\n" + _format_tables_internal(tables) + "\n"
+        elif f.endswith(".docx"):
+            text += clean_extracted_text(extract_text_from_docx(path)) + "\n"
+        elif f.endswith(".json"):
+            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"
+    return text
+
+# ---------------- Message Processing Loop ----------------
+def process_messages_loop(conversation_sid, index, text_chunks, tokenizer, embed_model):
+    processed_sids = set()
+    while True:
+        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))
+            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.")