Chapter 4 Python Code - API Out of date

[danielithomas]

Code does not follow the current way the current openai API operates:

response = openai.ChatCompletion.create(
    engine="gpt-3.5-turbo", # engine = "deployment_name".
    messages=[
        {"role": "system", "content": system_message},
        {"role": "user", "content": instructions},
    ]
)

#print(response)
print(response['choices'][0]['message']['content'])

Should change to something like:

gpt_model = "gpt-4o"
messages=[
    {"role": "system", "content": system_message},
    {"role": "user", "content": instructions},
]

response = client.chat.completions.create(
    model=gpt_model, 
    messages=messages,
    temperature=0
)

response_message = response.choices[0].message.content
print(response_message)

Credit to a combo of the OpenAI https://github.com/openai/openai-python and a few StackOverflow answers, namely https://stackoverflow.com/questions/77444332/openai-python-package-error-chatcompletion-object-is-not-subscriptable