Update app.py

app.py

@@ -58,61 +58,14 @@ def construct_index(directory_path):
 #import streamlit as st
 # Include other necessary imports here
 
-# Add the cashback calculator
-def cashback_calculator(segment, total_spent, international_transactions, local_transactions):
-    cashback = 0
-
-    if find_similar(segment, ['almassy', 'alsafwa_plus', 'safwa', 'w', 'W']):
-        if total_spent < 3000:
-            cashback = total_spent * 0.03
-        else:
-            cashback = international_transactions * 0.06 + local_transactions * 0.03
-            
-        if find_similar(segment, ['almassy', 'alsafwa_plus', 'safwa']):
-            max_cashback = 500
-        else:  # segment == 'w'
-            max_cashback = 300
-            
-        cashback = min(cashback, max_cashback)
-        
-    elif similar(segment, 'normal'):
-        cashback = total_spent * 0.01
-        cashback = min(cashback, 150)
-    
-    return cashback
-
-# Helper functions
-def similar(a, b, threshold=0.5):
-    return SequenceMatcher(None, a, b).ratio() > threshold
-
-def find_similar(segment, segments):
-    return any(similar(segment, s) for s in segments)
-
-def is_query_about_cashback(query):
-    cashback_keywords = ["cashback", "calculate", "calculation", "reward", "points"]
-    return any(word.lower() in query.lower() for word in cashback_keywords)
-
-# Main language model function
 def ask_ai(query):
-    if is_query_about_cashback(query):
-        # Extract the required information from the query or ask the user for more information if needed
-        segment = input("Enter your card segment: ")
-        total_spent = float(input("Enter your total spent amount: "))
-        international_transactions = float(input("Enter your international transactions amount: "))
-        local_transactions = float(input("Enter your local transactions amount: "))
-
-        cashback = cashback_calculator(segment, total_spent, international_transactions, local_transactions)
-        return f"The cashback amount for your card is: {cashback:.2f}"
-    else:
-        index = GPTSimpleVectorIndex.load_from_disk('index.json')
-        response = index.query(query, response_mode="compact")
-        return response.response   
-
-
-# Gradio interface
-import gradio as gr
-iface = gr.Interface(fn=ask_ai, inputs="text", outputs="text", title="The following is a conversation with a human called Shegardi. Shegardi is helpful, precise, truthful, and very friendly. Also, Shegardi is an employee of Warba Bank, located in Kuwait. Shegardi will only use the information provided to him.",
+    index = GPTSimpleVectorIndex.load_from_disk('index.json')
+    response = index.query(query, response_mode="compact")
+    return response.response
+    
+iface = gr.Interface(fn=ask_ai, inputs="text", outputs="text", title="The following is a conversation with a human called Shegardi. Shegardi is helpful, precise, truthful, and very friendly.  Also, Shegardi is an employee of Warba Bank, located in Kuwait. Shegardi will only use the information provided to him. ", 
                      description="Enter a question and get an answer from Shegardi.")
+
 iface.launch()