Update app.py

app.py

@@ -5,38 +5,33 @@ import warnings
 import time
 import sqlite3
 import shutil
-import asyncio  # <--- NEW IMPORT
+import asyncio
 
 # ==========================================
 # 0. ASYNC FIX (CRITICAL FOR STREAMLIT)
 # ==========================================
-# This fixes "There is no current event loop" errors
+# Fixes "No event loop" errors
 try:
     asyncio.get_running_loop()
 except RuntimeError:
     asyncio.set_event_loop(asyncio.new_event_loop())
 
 # ==========================================
-# 1. PAGE CONFIG (MUST BE FIRST STREAMLIT CMD)
+# 1. PAGE CONFIG
 # ==========================================
-st.set_page_config(page_title="Bank Loan Agent (Multi-Model)", layout="wide")
-
-# Suppress warnings
+st.set_page_config(page_title="Bank Loan Agent", layout="wide")
 warnings.filterwarnings("ignore")
 
 # ==========================================
-# 2. GLOBAL CONSTANTS & IMPORTS
+# 2. 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:
-    # PROVIDER IMPORTS
     from langchain_groq import ChatGroq
     from langchain_google_genai import ChatGoogleGenerativeAI, GoogleGenerativeAIEmbeddings
-    
-    # SHARED IMPORTS
     from langchain_huggingface import HuggingFaceEmbeddings
     from langchain_community.vectorstores import FAISS
     from langchain_community.callbacks import StreamlitCallbackHandler
@@ -47,26 +42,17 @@ try:
     from langchain_core.output_parsers import StrOutputParser
     from langchain_core.tools import tool
     from langchain.agents import AgentExecutor, create_tool_calling_agent
-
 except ImportError as e:
     st.error(f"❌ Critical Import Error: {e}")
-    st.info("💡 Suggestion: Check requirements.txt contains 'langchain-google-genai'")
     st.stop()
 
 # ==========================================
 # 3. DATABASE SETUP
 # ==========================================
 def init_db():
-    """Converts CSV files to SQLite DB."""
     if os.path.exists(DB_FILE): return
-
     conn = sqlite3.connect(DB_FILE)
-    csv_files = {
-        "credit_score": "credit_score.csv",
-        "account_status": "account_status.csv",
-        "pr_status": "pr_status.csv"
-    }
-
+    csv_files = {"credit_score": "credit_score.csv", "account_status": "account_status.csv", "pr_status": "pr_status.csv"}
     try:
         for table, file in csv_files.items():
             if os.path.exists(file):
@@ -75,9 +61,7 @@ def init_db():
                 if 'ID' in df.columns: df['ID'] = df['ID'].astype(str)
                 try: df.to_sql(table, conn, if_exists='replace', index=False)
                 except: pass 
-    finally:
-        conn.close()
-
+    finally: conn.close()
 init_db()
 
 def run_query(query, params=()):
@@ -89,7 +73,7 @@ def run_query(query, params=()):
     except Exception as e: return f"DB Error: {e}"
 
 # ==========================================
-# 4. DEFINE TOOLS
+# 4. TOOLS
 # ==========================================
 @tool
 def get_credit_score(user_id: str) -> str:
@@ -117,128 +101,133 @@ def check_pr_status(user_id: str) -> str:
     return f"PR Status: {row[0]}" if (row and not isinstance(row, str)) else "PR Status: False."
 
 # ==========================================
-# 5. STREAMLIT APP UI
+# 5. UI & AUTH
 # ==========================================
 st.title("🤖 Multi-Model Loan Assessor")
-st.markdown("Agent connects to **SQLite Database** and **Persistent Vector Store**")
 pdfs_missing = [f for f in REQUIRED_PDFS if not os.path.exists(f)]
 
 def update_metrics(placeholder):
-    manual_time = 15 * 60  
     if 'execution_time' in st.session_state:
         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")
+        col1, col2 = placeholder.columns(2)
+        col1.metric("Processing Time", f"{ai_time:.2f}s")
+        col2.metric("Efficiency", "High")
 
 # --- SIDEBAR ---
 with st.sidebar:
     st.header("🔐 Authentication")
     
-    # 1. Select Provider
-    provider_option = st.radio("Select AI Model:", ["Groq (Llama-3)", "Google (Gemini)"])
+    # Provider Selection
+    provider_option = st.radio("Select Model:", ["Groq (Llama-3)", "Google (Gemini)"])
     
-    # State Management
+    # Init State
     if 'auth_status' not in st.session_state:
         st.session_state['auth_status'] = False
         st.session_state['api_key'] = None
         st.session_state['provider'] = None
 
+    # Reset on Switch
     if st.session_state.get('provider') != provider_option:
         st.session_state['auth_status'] = False
         st.session_state['api_key'] = None
         st.session_state['provider'] = provider_option
 
-    # 2. Auth Logic
+    # Auth Logic
     if not st.session_state['auth_status']:
         api_key_input = st.text_input(f"Enter {provider_option} API Key", type="password")
+        
         if st.button("Validate Key"):
             if not api_key_input:
-                st.error("⚠️ Please enter a key.")
+                st.error("⚠️ Enter a key.")
             else:
                 try:
-                    with st.spinner(f"Contacting {provider_option}..."):
-                        # DYNAMIC VALIDATION
+                    with st.spinner(f"Connecting to {provider_option}..."):
+                        # --- VALIDATION LOGIC ---
                         if "Groq" in provider_option:
                             test_llm = ChatGroq(api_key=api_key_input, model_name="llama-3.3-70b-versatile")
                         else:
-                            test_llm = ChatGoogleGenerativeAI(google_api_key=api_key_input, model="gemini-1.5-flash")
+                            # FORCE REST TRANSPORT TO FIX SPINNING
+                            test_llm = ChatGoogleGenerativeAI(
+                                google_api_key=api_key_input, 
+                                model="gemini-1.5-flash",
+                                transport="rest" # <--- THIS IS THE FIX
+                            )
+                        
+                        # Simple Invoke to test connection
+                        test_llm.invoke("Hello")
                         
-                        test_llm.invoke("Test")
                         st.session_state['auth_status'] = True
                         st.session_state['api_key'] = api_key_input
-                        st.success("✅ Valid Key!")
+                        st.success("✅ Connected!")
                         time.sleep(0.5)
                         st.rerun()
                 except Exception as e:
-                    st.error(f"❌ Connection Failed: {e}")
+                    st.error(f"❌ Error: {e}")
     else:
-        st.success(f"✅ {st.session_state['provider']} Active")
+        st.success(f"✅ {st.session_state['provider']} Ready")
         if st.button("🔴 Logout"):
             st.session_state['auth_status'] = False
-            st.session_state['api_key'] = None
             st.rerun()
 
     st.divider()
-    if st.button("♻️ Rebuild DB/RAG"):
+    if st.button("♻️ Rebuild Database"):
         if os.path.exists(INDEX_PATH): shutil.rmtree(INDEX_PATH)
         st.cache_resource.clear()
+        st.success("Reset Complete.")
+        time.sleep(1)
         st.rerun()
 
+    st.divider()
     if os.path.exists(DB_FILE) and not pdfs_missing:
         st.success("✅ System Ready")
     else:
         st.warning(f"⚠️ Missing: {pdfs_missing}")
     
-    st.header("📊 Metrics")
+    st.header("Metrics")
     metrics_placeholder = st.empty()
     update_metrics(metrics_placeholder)
 
-# --- MAIN LOGIC ---
+# ==========================================
+# 6. MAIN APP LOGIC
+# ==========================================
 if st.session_state.get('auth_status', False):
     
     current_key = st.session_state['api_key']
     current_provider = st.session_state['provider']
 
-    # --- DYNAMIC RAG SETUP ---
+    # --- RAG SETUP ---
     @st.cache_resource
-    def setup_rag(_provider, _key): # Arguments included to force refresh on switch
+    def setup_rag(_provider, _key):
         if pdfs_missing: st.stop()
         
-        # Use Google Embeddings if Gemini, else HuggingFace
-        if "Google" in _provider:
-            embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001", google_api_key=_key)
-        else:
-            embeddings = HuggingFaceEmbeddings(model_name="all-MiniLM-L6-v2")
+        # Use HuggingFace embeddings for stability across both models
+        embeddings = HuggingFaceEmbeddings(model_name="all-MiniLM-L6-v2")
 
         if os.path.exists(INDEX_PATH):
-            # Attempt load. If schema mismatch (different embeddings), rebuild.
-            try:
-                return FAISS.load_local(INDEX_PATH, embeddings, allow_dangerous_deserialization=True).as_retriever()
-            except:
-                pass # Fall through to rebuild
-
-        # Build Index
-        documents = []
-        for pdf_file in REQUIRED_PDFS:
-            documents.extend(PyPDFLoader(pdf_file).load())
-        splits = CharacterTextSplitter(chunk_size=600, chunk_overlap=50).split_documents(documents)
-        vectorstore = FAISS.from_documents(splits, embeddings)
-        vectorstore.save_local(INDEX_PATH)
-        return vectorstore.as_retriever()
-
-    with st.spinner("Initializing Knowledge Base..."):
-        # We pass args so Streamlit sees them as dependencies
+            return FAISS.load_local(INDEX_PATH, embeddings, allow_dangerous_deserialization=True).as_retriever()
+        else:
+            documents = []
+            for pdf_file in REQUIRED_PDFS:
+                documents.extend(PyPDFLoader(pdf_file).load())
+            splits = CharacterTextSplitter(chunk_size=600, chunk_overlap=50).split_documents(documents)
+            vectorstore = FAISS.from_documents(splits, embeddings)
+            vectorstore.save_local(INDEX_PATH)
+            return vectorstore.as_retriever()
+
+    with st.spinner("Loading Knowledge Base..."):
         retriever = setup_rag(current_provider, current_key)
 
-    # --- LLM INSTANTIATION ---
+    # --- LLM SETUP ---
     if "Groq" in current_provider:
         llm = ChatGroq(api_key=current_key, temperature=0, model_name="llama-3.3-70b-versatile")
     else:
-        llm = ChatGoogleGenerativeAI(google_api_key=current_key, temperature=0, model="gemini-1.5-flash")
+        # FORCE REST TRANSPORT HERE TOO
+        llm = ChatGoogleGenerativeAI(
+            google_api_key=current_key, 
+            temperature=0, 
+            model="gemini-1.5-flash",
+            transport="rest" # <--- CRITICAL FIX
+        )
 
     # --- AGENT SETUP ---
     rag_chain = (
@@ -252,6 +241,7 @@ if st.session_state.get('auth_status', False):
         return rag_chain.invoke(query)
 
     tools = [get_credit_score, get_account_status, check_pr_status, consult_policy_doc]
+    
     prompt = ChatPromptTemplate.from_messages([
         ("system", "Act as a Loan Officer. Query SQL DB for info. Check Policies via tool. Output Markdown report."),
         ("human", "{input}"),
@@ -260,10 +250,9 @@ if st.session_state.get('auth_status', False):
     
     agent_executor = AgentExecutor(agent=create_tool_calling_agent(llm, tools, prompt), tools=tools, verbose=True, return_intermediate_steps=True)
 
-    # --- UI ---
+    # --- INPUT UI ---
     col1, col2 = st.columns([1, 2])
     with col1:
-        st.subheader("1. Details")
         uid = st.text_input("Customer ID", "1111")
         use_sim = st.checkbox("Simulation Mode")
         sim_score = st.slider("Score", 300, 900, 450) if use_sim else 0
@@ -291,15 +280,16 @@ if st.session_state.get('auth_status', False):
 
             st.success("### 📋 Final Report")
             st.markdown(res['output'])
+            
             with st.expander("Trace"):
                 for action, obs in res.get("intermediate_steps", []):
-                    st.markdown(f"**Tool:** `{action.tool}` -> `{obs}`")
+                    st.markdown(f"**Tool:** `{action.tool}`\n**Result:** `{obs}`")
 
             if not use_sim:
                 st.divider()
                 with st.expander("✉️ Email Draft"):
-                    email = llm.invoke(f"Draft formal email for: {res['output']}").content
+                    email = llm.invoke(f"Draft email for: {res['output']}").content
                     st.text_area("Draft", value=email, height=200)
 
 elif not st.session_state.get('auth_status', False):
-    st.info("👈 Select AI Provider & Validate Key in Sidebar")
+    st.info("👈 Please Select Provider & Validate Key in Sidebar")