Project Overview Creating a Chatbot for a Restaurant

User: Hello
Assistant: Hello there! Welcome to Burger Bliss. How can I assist you today?
User: I want to order a chicken burger.
Assistant: We have two options: Crispy Chicken Burger and BB Grilled Chicken Burger. Which one would you like?
User: I’ll have the Spicy Crispy Chicken Burger.
Assistant: Excellent choice! Anything else you’d like to add, like extra fries or a drink?
User: Can I have extra fries please?
Assistant: Of course! Would you like anything to drink? We have Coke, Fanta, Sprite, and Bottled Water.
User: I am done.
Assistant: Alright, that’s a Spicy Crispy Chicken Burger with extra fries. Pickup or delivery?
User: It’s for pickup.
Assistant: Great! When would you like to pick it up?
User: In 10 minutes.
Assistant: Perfect. Your order will be ready for pickup in 10 minutes. Thank you for choosing Burger Bliss!

import os
import openai
import panel as pn

# Load your OpenAI API key from an environment variable
openai.api_key = os.getenv("OPENAI_API_KEY")

def get_chat_completion(messages):
    """
    Sends a list of messages to OpenAI’s ChatCompletion API
    and returns the assistant’s response text.
    """
    response = openai.ChatCompletion.create(
        model="gpt-3.5-turbo",
        messages=messages
    )
    return response.choices[0].message.content

bot_instructions = """
You are BurgerBot, an automated service to collect orders at Burger Bliss.
1. Greet the customer.
2. Gather the full order; summarize before confirmation.
3. Ask for pickup or delivery (if delivery, request address).
4. Confirm payment details.
5. Clarify menu options with unique item identifiers.
"""

# Starting context with system instructions
context = [{"role": "system", "content": bot_instructions}]

# TextInput widget for user messages
user_input = pn.widgets.TextInput(
    placeholder="Type your message here...", width=400
)

# List to hold UI panels for each message
panels = []

def collect_messages():
    prompt = user_input.value
    user_input.value = ""  # Clear the input field

    # Add user prompt to context and fetch assistant response
    context.append({"role": "user", "content": prompt})
    response = get_chat_completion(context)
    context.append({"role": "assistant", "content": response})

    # Display the user’s message
    panels.append(pn.Row("User:", pn.pane.Markdown(prompt, width=600)))
    # Display the assistant’s reply
    panels.append(
        pn.Row(
            "Assistant:",
            pn.pane.Markdown(
                response,
                width=600,
                styles={"background-color": "#F6F6F6"}
            )
        )
    )

    return pn.Column(*panels)

# Button to send messages
chat_button = pn.widgets.Button(name="Send", button_type="primary")

# Bind the function to the button click
interactive_chat = pn.bind(collect_messages, chat_button)

# Layout the dashboard
dashboard = pn.Column(
    user_input,
    pn.Row(chat_button),
    pn.panel(interactive_chat, loading_indicator=True, height=300),
)

dashboard