OpenAI SDK v1.0 API error: "AttributeError: 'OpenAI' object has no attribute 'Completion'"

Question

So I've got some ganky code for writing a business plan, and it was working but is dead now as of v1.0, I can't work out how to properly re-code it without AttributeError: 'OpenAI' object has no attribute 'Completion' error occurring. Anyone able to help?

# Function to generate text for each section using OpenAI's API
def generate_text_for_section(section_name, user_input):
response = openai.Completion.create(
    model="text-davinci-003",
    prompt=f"Write a detailed description for a business plan section titled '{section_name}'. Project idea: {user_input}.",
    max_tokens=500
)
return response.choices[0].text.strip()

Answer 1

Problem

The method name you're trying to use doesn't work with the OpenAI Python SDK version 1.0.0 or newer.

The old SDK (i.e., version 0.28) works with the following method name:

client.Completion.create

The new SDK (i.e., version 1.0.0 or newer) works with the following method name:

client.completions.create

Note: Be careful because the API is case-sensitive (i.e., client.Completions.create will not work with the new SDK version).

Solution

Try this:

import os
from openai import OpenAI
client = OpenAI()
OpenAI.api_key = os.getenv('OPENAI_API_KEY')

completion = client.completions.create(
  model="gpt-3.5-turbo-instruct",
  prompt="Say this is a test",
  max_tokens=7,
  temperature=0
)

print(completion.choices[0].text)