Update app.py

fix the pdf missing error

app.py

@@ -15,8 +15,12 @@ st.set_page_config(page_title="Bank Loan Agent (SQL)", layout="wide")
 warnings.filterwarnings("ignore")
 
 # ==========================================
-# 2. ROBUST IMPORTS
+# 2. GLOBAL CONSTANTS & IMPORTS
 # ==========================================
+DB_FILE = "bank.db"
+INDEX_PATH = "faiss_index"
+REQUIRED_PDFS = ["Bank Loan Overall Risk Policy.pdf", "Bank Loan Interest Rate Policy.pdf"]
+
 try:
     from langchain_groq import ChatGroq
     from langchain_huggingface import HuggingFaceEmbeddings
@@ -37,17 +41,12 @@ except ImportError as e:
 # ==========================================
 # 3. DATABASE SETUP
 # ==========================================
-DB_FILE = "bank.db"
-INDEX_PATH = "faiss_index"
-
 def init_db():
-    """Converts CSV files to SQLite DB. Handles 'replace' errors gracefully."""
-    # Only run if DB doesn't exist to avoid redundant overwrites
+    """Converts CSV files to SQLite DB. Handles errors gracefully."""
     if os.path.exists(DB_FILE):
         return
 
     conn = sqlite3.connect(DB_FILE)
-    
     csv_files = {
         "credit_score": "credit_score.csv",
         "account_status": "account_status.csv",
@@ -58,27 +57,23 @@ def init_db():
         for table, file in csv_files.items():
             if os.path.exists(file):
                 df = pd.read_csv(file)
-                df.columns = [c.strip() for c in df.columns] # Clean headers
+                df.columns = [c.strip() for c in df.columns] 
                 if 'ID' in df.columns:
                     df['ID'] = df['ID'].astype(str)
                 
-                # Robust SQL Write
                 try:
                     df.to_sql(table, conn, if_exists='replace', index=False)
-                except Exception as sql_err:
-                    # Fallback: if 'replace' fails on missing table, try creating it fresh
-                    print(f"⚠️ SQL Warning for {table}: {sql_err}")
+                except Exception:
                     pass 
-                    
     except Exception as e:
         st.error(f"DB Init Error: {e}")
     finally:
         conn.close()
 
-# Initialize DB 
+# Initialize DB on startup
 init_db()
 
-# Helper for tools
+# Helper for SQL tools
 def run_query(query, params=()):
     try:
         with sqlite3.connect(DB_FILE) as conn:
@@ -119,7 +114,6 @@ def check_pr_status(user_id: str) -> str:
     clean_id = ''.join(filter(str.isdigit, str(user_id)))
     row = run_query("SELECT PR_Status FROM pr_status WHERE ID = ?", (clean_id,))
     
-    # Fallback for column naming differences
     if not row or (isinstance(row, str) and "no such column" in row.lower()):
          row = run_query("SELECT Is_PR FROM pr_status WHERE ID = ?", (clean_id,))
 
@@ -133,6 +127,9 @@ def check_pr_status(user_id: str) -> str:
 st.title("🤖 Multi-Policy Loan Assessor (SQL + RAG)")
 st.markdown("Agent connects to **SQLite Database** and **Persistent Vector Store**")
 
+# Calculate missing PDFs globally so everyone can see it
+pdfs_missing = [f for f in REQUIRED_PDFS if not os.path.exists(f)]
+
 # --- METRICS FUNCTION ---
 def update_metrics(placeholder):
     manual_time = 15 * 60  
@@ -140,26 +137,21 @@ def update_metrics(placeholder):
         ai_time = st.session_state.execution_time
         time_saved = manual_time - ai_time
         saved_pct = (time_saved / manual_time) * 100
-        
         with placeholder.container():
             col_kpi1, col_kpi2 = st.columns(2)
             col_kpi1.metric("AI Processing", f"{ai_time:.1f}s")
-            col_kpi2.metric(
-                "Time Saved", 
-                f"{time_saved/60:.1f} min", 
-                delta=f"{saved_pct:.1f}% faster"
-            )
+            col_kpi2.metric("Time Saved", f"{time_saved/60:.1f} min", delta=f"{saved_pct:.1f}% faster")
 
 # --- SIDEBAR ---
 with st.sidebar:
     st.header("🔐 Authentication")
     
-    # 1. Check if Key exists in Secrets (Env Var)
+    # Check Secrets
     if "GROQ_API_KEY" in st.secrets:
         st.session_state['groq_api_key'] = st.secrets["GROQ_API_KEY"]
         st.session_state['is_key_valid'] = True
     
-    # 2. Manual Entry Logic
+    # Manual Entry
     if 'is_key_valid' not in st.session_state:
         st.session_state['is_key_valid'] = False
 
@@ -206,9 +198,6 @@ with st.sidebar:
         
     st.divider()
     
-    required_pdfs = ["Bank Loan Overall Risk Policy.pdf", "Bank Loan Interest Rate Policy.pdf"]
-    pdfs_missing = [f for f in required_pdfs if not os.path.exists(f)]
-    
     if os.path.exists(DB_FILE) and not pdfs_missing:
         st.success("✅ System Ready")
     else:
@@ -226,19 +215,24 @@ if st.session_state.get('is_key_valid', False):
     # --- RAG SETUP ---
     @st.cache_resource
     def setup_rag():
+        # Check global variable here
+        if pdfs_missing:
+            st.error(f"Missing PDFs: {pdfs_missing}")
+            st.stop()
+            
         embeddings = HuggingFaceEmbeddings(model_name="all-MiniLM-L6-v2")
+        
         if os.path.exists(INDEX_PATH):
             return FAISS.load_local(INDEX_PATH, embeddings, allow_dangerous_deserialization=True).as_retriever()
         else:
-            if pdfs_missing:
-                st.error("Missing PDFs.")
-                st.stop()
             documents = []
-            for pdf_file in required_pdfs:
+            for pdf_file in REQUIRED_PDFS:
                 loader = PyPDFLoader(pdf_file)
                 documents.extend(loader.load())
+            
             text_splitter = CharacterTextSplitter(chunk_size=600, chunk_overlap=50)
             final_docs = text_splitter.split_documents(documents)
+            
             vectorstore = FAISS.from_documents(final_docs, embeddings)
             vectorstore.save_local(INDEX_PATH)
             return vectorstore.as_retriever()
@@ -248,7 +242,6 @@ if st.session_state.get('is_key_valid', False):
 
     llm = ChatGroq(temperature=0, model_name="llama-3.3-70b-versatile")
     
-    # RAG Chain
     rag_prompt = ChatPromptTemplate.from_template("Answer based on context:\n{context}\nQuestion: {question}")
     rag_chain = (
         {"context": retriever | (lambda d: "\n".join([x.page_content for x in d])), "question": RunnablePassthrough()}