Update app.py

app.py

@@ -13,16 +13,18 @@ import PyPDF2
 import requests
 from streamlit_autorefresh import st_autorefresh
 
-# --- Text Extraction ---
+# 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:
-                content = page.extract_text()
-                if content:
-                    text += content
+            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
         return text
     except:
         return extract_text(pdf_path)
@@ -34,7 +36,6 @@ def extract_text_from_docx(docx_path):
     except:
         return ""
 
-# --- Chunking ---
 def chunk_text(text, tokenizer, chunk_size=150, chunk_overlap=30):
     tokens = tokenizer.tokenize(text)
     chunks, start = [], 0
@@ -45,13 +46,12 @@ def chunk_text(text, tokenizer, chunk_size=150, chunk_overlap=30):
         start += chunk_size - chunk_overlap
     return chunks
 
-# --- Retrieval ---
 def retrieve_chunks(question, index, embed_model, text_chunks, k=3):
     question_embedding = embed_model.encode([question])[0]
     D, I = index.search(np.array([question_embedding]), k)
     return [text_chunks[i] for i in I[0]]
 
-# --- Answer Generation ---
+# 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")
@@ -100,7 +100,7 @@ def generate_answer_with_groq(question, context, retries=3, delay=2):
         except Exception as e:
             return f"⚠️ Groq API Error: {e}"
 
-# --- Twilio Messaging ---
+# 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)
@@ -117,59 +117,59 @@ def send_twilio_message(account_sid, auth_token, conversation_sid, body):
     except Exception as e:
         return str(e)
 
-# --- Streamlit UI ---
+# 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
 
-# --- Credentials ---
 account_sid = st.secrets.get("TWILIO_SID")
 auth_token = st.secrets.get("TWILIO_TOKEN")
 GROQ_API_KEY = st.secrets.get("GROQ_API_KEY")
 
-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 "")
-conversation_sid = st.text_input("💬 Twilio Conversation SID")
+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 "")
+
+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, GROQ_API_KEY, conversation_sid]):
     os.environ["GROQ_API_KEY"] = GROQ_API_KEY
 
-    @st.cache_resource(show_spinner=True)
+    @st.cache_data(show_spinner=False)
     def setup_knowledge_base():
         folder_path = "docs"
         all_text = ""
-        for file in os.listdir(folder_path):
-            full_path = os.path.join(folder_path, file)
-            if file.endswith(".pdf"):
-                all_text += extract_text_from_pdf(full_path) + "\n"
-            elif file.endswith((".docx", ".doc")):
-                all_text += extract_text_from_docx(full_path) + "\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
-
-    st.info("⚙️ Preparing knowledge base...")
-    try:
-        index, embedding_model, text_chunks = setup_knowledge_base()
-        st.success("✅ Knowledge base ready. Monitoring WhatsApp...")
-    except Exception as e:
-        st.error(f"❌ Failed to prepare knowledge base: {e}")
+        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()
 
-    # --- Auto Refresh ---
-    enable_autorefresh = st.checkbox("🔄 Enable Auto-Refresh", value=True)
-    interval_seconds = st.selectbox("Refresh Interval (seconds)", options=[5, 10, 15, 30, 60], index=4)
-    if enable_autorefresh:
-        st_autorefresh(interval=interval_seconds * 1000, key="auto-refresh")
+    st.success("✅ Knowledge base ready. Monitoring WhatsApp...")
 
     with st.spinner("⏳ Checking for new WhatsApp messages..."):
         question, sender, msg_index = fetch_latest_incoming_message(account_sid, auth_token, conversation_sid)
@@ -185,4 +185,4 @@ if all([account_sid, auth_token, GROQ_API_KEY, conversation_sid]):
         else:
             st.caption("✅ No new message yet. Waiting for refresh...")
 else:
-    st.warning("❗ Please provide all required credentials and conversation SID.")
+    st.warning("❗ Please provide all required credentials and conversation SID.")