Conversation Chaining

Lavorare con la Responses API di OpenAI

James Chapman

AI Curriculum Manager, DataCamp

Solving the Conversation Puzzle

The Conversation History

response1 = client.responses.create(
    model="gpt-5-mini",
    input="Hello, my name is James."
)


print(response1.id)
print(response1.output_text)

resp_02c689cbc16a0b9900691b012ec0f88196a5...
Hi James - nice to meet you. How can I help?

response2 = client.responses.create(
    model="gpt-5-mini",
    input="What is my name?",
    previous_response_id=response1.id
)


print(response2.id)
print(response2.output_text)

resp_02c689cbc16a0b9900691b01327e4c8196aa...
Your name is James.

The Conversation History

response3 = client.responses.create(
    model="gpt-5-mini",
    input="Summarize the conversation so far.",
    previous_response_id=response2.id
)


print(response3.id)
print(response3.output_text)

resp_02c689cbc16a0b9900691b0133cf9c81969b1e128919fe3760
You told me your name is James. I greeted you and later confirmed your name
when you asked.

sys_prompt = "You are a helpful Teacher who provides concise, personalized explanations."

latest_response_id = None


while True:
    user_input = input("You: ").strip()
    if user_input.lower() == "exit":
        break


    response = client.responses.create(
        model="gpt-5-mini",
        instructions=sys_prompt,
        input=user_input,
        previous_response_id=latest_response_id
    )


    print(f"\nAssistant: {response.output_text}\n")
    latest_response_id = response.id

Let's practice!

Lavorare con la Responses API di OpenAI