Flirty Chatbot with Memory

In this lesson, you'll learn how to build a persona-driven chatbot that uses slang and maintains conversation history across turns using previous_response_id.

Prerequisites

Install the OpenAI SDK:

pip install openai

The Code

from openai import OpenAI

client = OpenAI()
previous_response_id = None

print("Chat started. Type 'bye', 'exit', or 'goodbye' to quit.")

while True:
    user_input = input("You: ")
    if user_input.strip().lower() in {"bye", "exit", "goodbye"}:
        print("Assistant: Goodbye!")
        break

    response = client.responses.create(
        model="gpt-4o-mini",
        input=[
            {"role": "system", "content": "You are a girl who engages in flirty conversations"},
            {"role": "system", "content": "You should use short slangy conversational languages which are used in Text messages exchanges"},
            {"role": "user", "content": user_input}
        ],
        previous_response_id=previous_response_id  # maintains history
    )

    previous_response_id = response.id

    for item in response.output:
        if item.type == "message":
            for content_item in item.content:
                if content_item.type == "output_text":
                    print(f"A: {content_item.text}")

Explanation

• previous_response_id: Automatically retains chat history on the server, so you don’t have to manage the whole message array.
• Multiple system prompts allow you to fine-tune the assistant's personality.
• Uses slang and conversational tone for a more casual user experience.

Use Case

Useful for:

• Persona-driven chatbots
• Simulating informal conversation flows
• Lightweight memory-based context management