Update app.py

app.py

@@ -1,121 +1,108 @@
 import gradio as gr
-import requests
-import os
 import json
-from langdetect import detect
 import pandas as pd
 from datetime import datetime
 
-HF_TOKEN = os.getenv("HF_TOKEN")
-API_URL = "https://api-inference.huggingface.co/models/HuggingFaceH4/zephyr-7b-beta"
-headers = {"Authorization": f"Bearer {HF_TOKEN}"}
-
-# Load FAQ
-with open("faq.json", "r") as f:
-    faq_data = json.load(f)
-
-# Load memory
-if os.path.exists("memory.json"):
-    with open("memory.json", "r") as f:
-        memory = json.load(f)
-else:
-    memory = {}
-
-business_info = """
-Business Name: SevaBot AI Support
-Location: Hyderabad
-Working Hours: 10 AM - 9 PM
-Return Policy: 7 days replacement only
-Delivery Time: 2-3 working days
-"""
-
-def check_faq(question):
-    for item in faq_data:
-        if question.lower() in item["question"].lower():
-            return item["answer"]
-    return None
-
-def save_memory(user, message, response):
-    if user not in memory:
-        memory[user] = []
-    memory[user].append({
-        "time": str(datetime.now()),
-        "message": message,
-        "response": response
-    })
-    with open("memory.json", "w") as f:
-        json.dump(memory, f, indent=4)
-
-def ai_response(message):
-    prompt = f"""
-You are a helpful customer support assistant.
-
-Business Info:
-{business_info}
-
-Customer Question:
-{message}
-"""
-
-    payload = {
-        "inputs": prompt,
-        "parameters": {"max_new_tokens": 200, "temperature": 0.5}
-    }
-
-    response = requests.post(API_URL, headers=headers, json=payload)
-
-    if response.status_code != 200:
-        return "Sorry, AI service unavailable."
-
-    result = response.json()
-    return result[0]["generated_text"]
-
-def respond(message, history, user_id):
-    try:
-        language = detect(message)
-    except:
-        language = "en"
-
-    # Check FAQ first
-    faq_answer = check_faq(message)
-    if faq_answer:
-        response = faq_answer
-    else:
-        response = ai_response(message)
-
-    # Telugu auto handling (basic)
-    if language == "te":
-        response = "మీ ప్రశ్నకు సమాధానం:\n" + response
-
-    save_memory(user_id, message, response)
-    return response
-
-def admin_dashboard():
-    data = []
-    for user, chats in memory.items():
-        for chat in chats:
-            data.append({
-                "User": user,
-                "Time": chat["time"],
-                "Message": chat["message"]
+# Load products
+with open("products.json", "r") as f:
+    products = json.load(f)
+
+cart = []
+
+def filter_products(category):
+    return [
+        f"{p['id']} - {p['name']} ({p['brand']}) | ₹{p['price']} per {p['unit']} | Stock: {p['stock']}"
+        for p in products if p["category"] == category
+    ]
+
+def add_to_cart(product_id, quantity):
+    for p in products:
+        if p["id"] == int(product_id):
+            if quantity > p["stock"]:
+                return "Not enough stock available!"
+
+            total = quantity * p["price"]
+
+            cart.append({
+                "Product": p["name"],
+                "Brand": p["brand"],
+                "Quantity": quantity,
+                "Unit": p["unit"],
+                "Price": p["price"],
+                "Total": total
             })
-    df = pd.DataFrame(data)
-    return df
+
+            p["stock"] -= quantity
+            return f"{p['name']} added to cart!"
+
+    return "Product not found!"
+
+def view_cart():
+    if not cart:
+        return pd.DataFrame()
+
+    return pd.DataFrame(cart)
+
+def generate_bill():
+    if not cart:
+        return "Cart is empty!"
+
+    df = pd.DataFrame(cart)
+    grand_total = df["Total"].sum()
+
+    bill_text = "🧾 Supermarket Bill\n"
+    bill_text += "---------------------------------\n"
+
+    for item in cart:
+        bill_text += f"{item['Product']} - {item['Quantity']} {item['Unit']} = ₹{item['Total']}\n"
+
+    bill_text += "---------------------------------\n"
+    bill_text += f"Grand Total: ₹{grand_total}\n"
+    bill_text += f"Date: {datetime.now()}\n"
+
+    return bill_text
+
 
 with gr.Blocks() as demo:
-    gr.Markdown("## 🤖 SevaBot AI - Smart Customer Support")
+    gr.Markdown("# 🛒 Smart Supermarket System")
 
-    user_id = gr.Textbox(label="Enter Customer ID")
+    category = gr.Dropdown(
+        choices=["Groceries", "Personal Care", "Cleaning"],
+        label="Select Category"
+    )
+
+    product_list = gr.Dropdown(label="Products")
+
+    quantity = gr.Number(label="Quantity", value=1)
+
+    add_btn = gr.Button("Add to Cart")
+
+    cart_table = gr.Dataframe(label="Cart")
+
+    bill_output = gr.Textbox(label="Generated Bill")
 
-    chatbot = gr.ChatInterface(
-        fn=lambda msg, hist: respond(msg, hist, user_id.value),
-        title="Customer Chat"
+    bill_btn = gr.Button("Generate Bill")
+
+    category.change(
+        lambda x: filter_products(x),
+        inputs=category,
+        outputs=product_list
     )
 
-    gr.Markdown("## 📊 Admin Dashboard")
-    admin_btn = gr.Button("View Customer Data")
-    output_table = gr.Dataframe()
+    add_btn.click(
+        add_to_cart,
+        inputs=[product_list, quantity],
+        outputs=bill_output
+    )
 
-    admin_btn.click(admin_dashboard, outputs=output_table)
+    add_btn.click(
+        view_cart,
+        outputs=cart_table
+    )
+
+    bill_btn.click(
+        generate_bill,
+        outputs=bill_output
+    )
 
 demo.launch()