Upload app.py with huggingface_hub

app.py

@@ -3,10 +3,6 @@ FoodHub - AI-Powered Food Delivery Chatbot with Streamlit UI
 Complete implementation with SQL Agent, Guardrails, and Interactive Interface
 """
 
-# ==============================================
-# 📦 Install Required Libraries for SQL + LLM Agent
-# ==============================================
-
 import streamlit as st
 import json
 import os
@@ -21,8 +17,6 @@ from langchain_core.messages import SystemMessage, HumanMessage
 from langchain.sql_database import SQLDatabase
 from langchain.agents.agent_toolkits import SQLDatabaseToolkit
 from langchain_groq import ChatGroq
-from langchain.agents import Tool
-from langchain.agents import initialize_agent
 
 # ============================================================================
 # CONFIGURATION & SETUP
@@ -208,13 +202,7 @@ def guardrail_with_llm(user_query: str, llm) -> str:
     return "unsafe" if any(word in result for word in unsafe_keywords) else "safe"
 
 def simple_authenticate(cust_id: str, db_agent) -> bool:
-    """
-    Authenticate a customer by checking if cust_id exists in the orders table.
-    Returns True if the customer exists, False otherwise.
-    Validation rule:
-      - Output must match the same cust_id as in the query result.
-      - Any other type of output or structure → invalid (False).
-    """
+    """Authenticate customer by checking if cust_id exists"""
     try:
         query = f"SELECT cust_id FROM orders WHERE cust_id = '{cust_id}';"
         result = db_agent.invoke({"input": query})
@@ -261,197 +249,86 @@ def handle_cancellation(user_query: str, raw_orders: str, order_status: str) ->
 
     return "Your order cannot be canceled. We hope to serve you again!"
 
-#######################################################################################################################
-
-# --- TOOL 1: Order Query Tool ---
-def order_chatbot(input_string: str) -> str:
-    """
-    Accepts a stringified dict input like:
-    "{'cust_id': 'C1016', 'user_message': 'Where is my order?'}"
-    Parses it, authenticates, fetches data, and returns structured info.
-    """
-    try:
-        data = ast.literal_eval(input_string)
-        cust_id = data.get("cust_id")
-        user_message = data.get("user_message")
-    except Exception:
-        return "⚠️ Invalid input format for OrderQueryTool."
-
-    # Step 1:Fetch order details
-    try:
-        order_result = db_agent.invoke(f"SELECT * FROM orders WHERE cust_id = '{cust_id}';")
-        raw_orders = order_result.get("output") if order_result else None
-    except Exception:
-        return "🚫 Sorry, we cannot fetch your order details right now. Please try again later."
-
-    # ✅ Return structured dictionary string for next tool
-    print(raw_orders)
-    return str({
-        "cust_id": cust_id,
-        "user_query": user_message,
-        "raw_orders": raw_orders
-    })
-
-# --- Register Tools ---
-
-Order_Query_Tool = Tool(
-    name="OrderQueryTool",
-    func=order_chatbot,
-    description="Fetches order details safely and returns structured output as a stringified dictionary."
-)
-
-#######################################################################################################################
-# --- TOOL 2: Answer Tool ---
-def format_customer_response(input_string: str) -> str:
-    """
-    Receives the output from OrderQueryTool as stringified dict,
-    parses it, and generates the final friendly message.
-    """
-    try:
-        data = ast.literal_eval(input_string)
-        cust_id = data.get("cust_id", "Unknown")
-        user_query = data.get("user_query", "")
-        raw_orders = data.get("raw_orders", "No order details found.")
-    except Exception:
-        return "⚠️ Error: Could not parse order data properly."
-
+def format_customer_response(cust_id: str, raw_orders: str, user_query: str, llm) -> str:
+    """Format final customer-facing response"""
     order_status = None
-    item_in_order = None
     preparing_eta = None
     delivery_time = None
 
-    # 🔹 Parse the raw order details line by line
+    # Parse order details
     for line in raw_orders.splitlines():
-        if "Order Status" in line:
+        if "Order Status" in line or "order_status" in line:
             order_status = line.split(":", 1)[1].strip()
-        elif "Preparing ETA" in line:
+        elif "Preparing ETA" in line or "preparing_eta" in line:
             preparing_eta = line.split(":", 1)[1].strip()
-        elif "Delivery Time" in line:
+        elif "Delivery Time" in line or "delivery_time" in line:
             delivery_time = line.split(":", 1)[1].strip()
 
-    # 🔹 Check if user query needs escalation (e.g., delayed order or major issue)
+    # Check escalation
     escalation_var = detect_escalation(user_query)
     if escalation_var == "Escalated":
         return (
-            f"Present status of your order is : {order_status.lower()}." +
-            "⚠️ Your issue requires immediate attention. " +
+            f"Present status of your order is: {order_status.lower()}. "
+            "⚠️ Your issue requires immediate attention. "
             "We have escalated your query to a human agent who will contact you shortly."
         )
 
-    # 🔹 Handle cancellation requests (calls the function)
+    # Check cancellation
     cancel_response = handle_cancellation(user_query, raw_orders, order_status)
-    if cancel_response:  # If function returns a valid message
+    if cancel_response:
         return cancel_response
 
-
-    # 🔹 Format normal order response using LLM
+    # Generate normal response using LLM
     system_prompt = f"""
     You are a friendly customer support assistant for FoodHub.
+
     Customer ID: {cust_id}
-    Here is the customer's order data from the database:
-    {raw_orders}
-    Sample of raw_orders :
-    order_id: O12501,
-    cust_id: C1026,
-    order_time: 12:59,
-    order_status: preparing food,
-    payment_status: COD,
-    item_in_order: Burger, Fries, Soda,
-    preparing_eta: 13:14,
-    prepared_time: None,
-    delivery_eta: None,
-    delivery_time: None
+    Order data: {raw_orders}
+
     Instructions:
-    1. Respond naturally and conversationally in a very short response.
-    2. Use only raw_oreders data to answer the user's query.
-    2. Interpret the raw_orders into polite, concise, and customer-friendly responses.
-    3. If order_status = 'preparing food', include ETA from 'preparing_eta' and also include ETA from 'delivery_eta'.
-       - If 'delivery_eta' is missing or None, say: "Your order is being prepared, and Delivery ETA will be available soon."
-    4. If order_status = 'delivered', mention 'delivery_time'.
-    5. If order_status = 'canceled', explain politely.
-    6. If order_status = 'picked up', include ETA from 'delivery_eta'.
-       - If 'delivery_eta' is missing or None, say: "Your order has been picked up, delivery ETA will be available soon."
-    7. If user_query contains 'Where is my order' then provide the order_status from the raw_orders.
-    8. If user_query contains 'How many items' then provide the 'Items in Order' from the raw_orders and return only that number in a friendly way (e.g., “Your order contains 3 items.”).
+    1. Respond naturally and conversationally in a short response
+    2. Use only the order data to answer
+    3. If order_status = 'preparing food', include preparing_eta and delivery_eta
+    4. If order_status = 'delivered', mention delivery_time
+    5. If order_status = 'picked up', include delivery_eta
+    6. For "Where is my order" queries, provide order_status
+    7. For "How many items" queries, count items in item_in_order
     """
 
-    # Build user-specific prompt
     user_prompt = f"User Query: {user_query}"
 
-    # 🔹 Generate response using LLM (system + user messages)
     response_msg = llm.predict_messages([
         SystemMessage(content=system_prompt),
         HumanMessage(content=user_prompt)
     ])
 
-    # Clean and return the final LLM response
     response = response_msg.content.strip()
+    return response if response else "Sorry, we could not retrieve your order details at this time."
 
-    # Return fallback message if no response is generated
-    if not response:
-        return "Sorry, we could not retrieve your order details at this time."
-    return response
-
-# # --- Register Tools ---
-
-Answer_Tool = Tool(
-    name="AnswerTool",
-    func=format_customer_response,
-    description="Takes the output from OrderQueryTool and returns a customer-facing message."
-)
-
-#######################################################################################################################
-import os
-
-# Fetch the API key from Hugging Face Secrets
-api_key = os.getenv("GROQ_API_KEY")
-if api_key is None:
-    raise ValueError("GROQ_API_KEY not found. Please set it in Hugging Face Secrets.")
-
-# Now you can initialize your LLM
-llm = initialize_llm(api_key)
-
-#######################################################################################################################
-# --- Initialize Agent ---
-tools = [Order_Query_Tool, Answer_Tool]
-
-agent = initialize_agent(
-    tools=tools,
-    llm=llm,
-    #llm=st.session_state.llm,
-    agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION,
-    verbose=True,
-    max_iterations=10,
-    max_execution_time=60
-)
+def order_chatbot(cust_id: str, user_message: str, llm, db_agent) -> str:
+    """Main chatbot function to handle customer queries"""
 
-#######################################################################################################################
+    # Step 1: Security guardrail
+    guardrail_response = guardrail_with_llm(user_message, llm)
+    if "unsafe" in guardrail_response.lower():
+        return "🚫 Unauthorized or irrelevant query. Please ask something related to your order only."
 
-# --- AGENT CONTROLLER ---
-def agent_tool_response(cust_id: str, user_query: str, llm, db_agent) -> str:
+    # Step 2: Authentication
+    if not simple_authenticate(cust_id, db_agent):
+        return "🚫 Invalid customer ID. Please provide a valid customer ID."
 
-    """
-    Executes tools in correct sequence: OrderQueryTool → AnswerTool.
-    """
-    agent_prompt = f"""
-    You are FoodHub's Order Assistant.
-    Sequence of execution:
-    1️⃣ Use 'OrderQueryTool' with:
-        input_string = str({{"cust_id": "{cust_id}", "user_message": "{user_query}"}})
-       → Output: stringified dict containing 'cust_id', 'user_query', and 'raw_orders'.
-    2️⃣ Use 'AnswerTool' with:
-        input_string = output of OrderQueryTool.
-    3️⃣ Return **only** the exact output from AnswerTool as the final user response — no rewording or summary.
-    """
-
-    final_answer = agent.run(agent_prompt)
-
-    print("\n======= ✅ FINAL RESPONSE =======")
-    print(final_answer)
-    return final_answer
-
-#######################################################################################################################
+    # Step 3: Fetch order details
+    try:
+        order_result = db_agent.invoke(
+            f"SELECT * FROM orders WHERE cust_id = '{cust_id}';"
+        )
+        raw_orders = order_result.get("output") if order_result else None
+    except Exception:
+        return "🚫 Sorry, we cannot fetch your order details right now. Please try again later."
 
+    # Step 4: Generate response
+    final_response = format_customer_response(cust_id, raw_orders, user_message, llm)
+    return final_response
 
 # ============================================================================
 # STREAMLIT UI COMPONENTS
@@ -473,8 +350,6 @@ def render_sidebar():
             help="Enter your Groq API key to use the chatbot"
         )
 
-
-
         # Database Path Input
         db_path = st.text_input(
             "Database Path",
@@ -605,7 +480,7 @@ def render_chat_interface():
 
             # Get bot response
             with st.spinner("🤔 Thinking..."):
-                bot_response = agent_tool_response(
+                bot_response = order_chatbot(
                     st.session_state.customer_id,
                     user_input,
                     st.session_state.llm,