Update app.py

app.py

@@ -50,19 +50,72 @@ 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]]
 
-# --- GROQ Answer Generator ---
+# 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_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)
+
+def extract_text_from_docx(docx_path):
+    try:
+        doc = docx.Document(docx_path)
+        return '\n'.join(para.text for para in doc.paragraphs)
+    except:
+        return ""
+
+def chunk_text(text, tokenizer, chunk_size=150, chunk_overlap=30):
+    tokens = tokenizer.tokenize(text)
+    chunks, start = [], 0
+    while start < len(tokens):
+        end = min(start + chunk_size, len(tokens))
+        chunk_tokens = tokens[start:end]
+        chunks.append(tokenizer.convert_tokens_to_string(chunk_tokens))
+        start += chunk_size - chunk_overlap
+    return chunks
+
+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]]
+
+# 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["GROQ_API_KEY"]
+    api_key = os.environ.get("GROQ_API_KEY")
+    if not api_key:
+        return "⚠️ GROQ_API_KEY not set."
+
     headers = {
         "Authorization": f"Bearer {api_key}",
         "Content-Type": "application/json",
     }
-    prompt = f"Based on the following context, answer the question: '{question}'\n\nContext:\n{context}"
+    prompt = (
+        f"Customer asked: '{question}'\n\n"
+        f"Here is the relevant product or policy info to help:\n{context}\n\n"
+        f"Respond in a friendly and helpful tone as a toy shop support agent."
+    )
     payload = {
         "model": "llama3-8b-8192",
         "messages": [
-            {"role": "system", "content": "You are a real human and you will respond as real human. You will be asked questions and you will respond like a human."},
+            {
+                "role": "system",
+                "content": (
+                    "You are ToyBot, a friendly and helpful WhatsApp assistant for an online toy shop. "
+                    "Your goal is to politely answer customer questions, help them choose the right toys, "
+                    "provide order or delivery information, explain return policies, and guide them through purchases. "
+                    "Always sound warm, helpful, and trustworthy like a professional customer support agent."
+                )
+            },
             {"role": "user", "content": prompt},
         ],
         "temperature": 0.5,
@@ -71,15 +124,18 @@ def generate_answer_with_groq(question, context, retries=3, delay=2):
 
     for attempt in range(retries):
         try:
-            response = requests.post(url, headers=headers, json=payload)
+            response = requests.post(url, headers=headers, json=payload, timeout=10)
+            response.raise_for_status()
             result = response.json()
             return result['choices'][0]['message']['content'].strip()
-        except Exception as e:
-            if "503" in str(e) and attempt < retries - 1:
+        except requests.exceptions.HTTPError as e:
+            if response.status_code == 503 and attempt < retries - 1:
                 time.sleep(delay)
                 continue
             else:
-                return f"⚠️ Groq API Error: {str(e)}"
+                return f"⚠️ Groq API HTTPError: {e}"
+        except Exception as e:
+            return f"⚠️ Groq API Error: {e}"
 
 # --- Twilio Chat Handlers ---
 def fetch_latest_incoming_message(account_sid, auth_token, conversation_sid):