OpenAI Chat Completions API: How do I solve the APIRemovedInV1 error when using the OpenAI Python library for GPT-4?

Question

This is a snippet where I have been encountering the problem:

def generate_response(prompt):
    response = openai.chatcompletion.create(
        model="gpt-4",  # Use "gpt-4" as the model identifier if "gpt-4o" is deprecated
        messages=[
            {"role": "system", "content": "You are a helpful assistant."},
            {"role": "user", "content": prompt}
        ],
        max_tokens=150
    )
    return response.choices[0].message['content'].strip()

I tried the following to solve the APIRemovedInV1 error:

1. I have tried downgrading the library version.
2. I have gone through the OpenAI documentation and tried the asynchronous method too but didn't work.

Answer 1

You have a double typo. You're missing a dot and the letter s.

Change this...

openai.chatcompletion.create

...to this.

openai.chat.completions.create

The full code is:

from openai import OpenAI
client = OpenAI()

completion = client.chat.completions.create()
  model="gpt-4",
  messages=[
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Hello!"}
  ]
)

print(completion.choices[0].message)