tailored recommendations

def financial_advisor_chatbot(customer_data, conversation_history, user_input):
    prompt = f"""
    You are a financial advisor chatbot for a bank. Use the following customer data and conversation history to provide personalized financial advice:

    Customer Data:
    - Income: ${customer_data['income']}
    - Savings: ${customer_data['savings']}
    - Debt: ${customer_data['debt']}
    - Financial Goals: {', '.join(customer_data['financial_goals'])}

    Conversation History:
    {conversation_history}

    Customer's Latest Question: {user_input}

    Provide a personalized response that addresses the customer's question and offers relevant financial advice based on their profile.
    """

    response = llm.generate(prompt)
    return response.text

# Example usage
customer = {
    "income": 75000,
    "savings": 50000,
    "debt": 20000,
    "financial_goals": ["buy a house", "save for retirement"]
}

conversation_history = [
    "Customer: What's the best way to save for a down payment on a house?",
    "Bot: Based on your current savings and income, I'd recommend...",
    "Customer: How much should I be saving each month?",
    "Bot: Considering your goal to buy a house and save for retirement..."
]

user_input = "Should I focus on paying off my debt or saving for a house down payment?"

response = financial_advisor_chatbot(customer, conversation_history, user_input)
print(response)