Error with Few-shot prompting using gpt 3.5

Question

I am trying to train GPT 3.5 model with few-shot prompting using messages argument instead of prompt argument. It throws an error even though it's clearly mentioned in OpenAI documentation that we can train a model this way.

import openai

conversation=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Who won the world series in 2020?"},
        {"role": "assistant", "content": "The Los Angeles Dodgers won the World Series in 2020."},
    ]

def askGPT(question):
    conversation.append({"role": "user", "content": question})
    openai.api_key = "openai key"
    response = openai.Completion.create(
        model = "gpt-3.5-turbo",
        messages = conversation,
        temperature = 0.6
        #max_tokens = 150,
    )
    #conversation.append({"role": "assistant","content":response})
    #print(response)
    #print(response["choices"][0]["message"]["content"])

    
    conversation.append({"role": "assistant", "content": response.choices[0].message.content})
    print(response.choices[0].message.content)

def main():
    while True:
        print('GPT: Ask me a question\n')
        myQn = input()
        askGPT(myQn)
        print('\n')


main()

Error:

openai.error.InvalidRequestError: Unrecognized request argument supplied: messages

I tried to give "conversations" to the model inside "responses" but it soesn't seem to work.

Answer 1

You made a mistake between chat completion and completion. See documentation.

completion: https://platform.openai.com/docs/api-reference/completions/create

chat completion: https://platform.openai.com/docs/api-reference/chat/create