Skip to main content

Building a Multi-Turn Chatbot

In this lesson, you’ll learn how to build a conversational chatbot using the OpenAI Chat Completions API. This chatbot will retain context across turns, making interactions more natural and coherent.

Prerequisites​

Make sure you have:

  • Python 3.8 or later
  • Installed the OpenAI Python SDK:
pip install openai

The Code​

from openai import OpenAI

client = OpenAI()

# Initialize message history with a system prompt
messages = [
    {"role": "system", "content": "You are a helpful assistant that answers concisely."}
]

# Run conversation loop
while True:
    user_input = input("You: ")

    if user_input.lower() in ["bye", "exit", "goodbye", "quit"]:
        print("Assistant: Goodbye!")
        break

    messages.append({"role": "user", "content": user_input})

    response = client.chat.completions.create(
        model="gpt-4o-mini",
        messages=messages
    )

    assistant_reply = response.choices[0].message.content
    print("Assistant:", assistant_reply)

    # Append assistant reply to message history for context
    messages.append({"role": "assistant", "content": assistant_reply})

Explanation​

  • Maintains a conversation loop using a while True block.
  • Tracks the conversation using a messages list.
  • Exits cleanly if user types bye, exit, or similar.
  • Appends each user and assistant message to the history to retain context.
  • Uses chat.completions.create for each new turn.

Use Case​

This is perfect for creating persistent, intelligent agents like:

  • Customer support bots
  • Personal assistants
  • Educational tutors