Quick start OpenAI API example using Python

OpenAI has a simple and friendly API, let’s take a quick look at how to start using it with Python.

Installing libs

The only thing we need to install is openai Python module:

pip install openai

Getting API key

The second thing we need to do is to get the API key for our app from this page:

Creating key for OpenAI API

Testing API

Now we can use API to get answers from OpenAI using prompts. The only thing we need to define is the model we’re going to use. We’ve picked text-davinci-003 for our example:

import openai

def ask(prompt):
  openai.api_key = '<YOUR-API_KEY>'
  return openai.Completion.create(

print(ask('pi number value, 25 decimals'))

This will be it. It’s an extremely simple example, but that is what makes OpenAI API so cool - it’s that easy. Now let’s take a look at a more advanced example we can use in practice.

Practical example - generating test data

One of the powerful OpenAI features is that we can ask to use a certain format for output. For example, we can ask API to generate various user data and format it suitably (e.g., CSV), so our script can understand it.

Let’s create a function to generate a given number of user-related data records. We’ll add the following code to our previous example:

from io import StringIO
import csv

def gen_test(n = 5, fields = ['phone', 'first name', 'last name', 'address', 'email']):
  prompt = 'generate a CSV list of ' + str(n) + ' random records including: ' + ', '.join(fields);

  csv_data = ask(prompt)

  f = StringIO(csv_data)
  reader = csv.reader(f, delimiter=',')

  return [row for row in reader]

[['613-456-2264', 'John', 'Smith', '12 Main Street, Ottawa, ON', ' johnsm@example.com'], ['416-213-7648', 'Bob', 'Taylor', '321 Anywhere Street, Toronto, ON', ' btayl@example.com'], ['905-522-9637', 'Jane', 'Davis', '14 Maple Street, Hamilton, ON', ' jdavis@example.com'], ['250-546-6315', 'Rick', 'Jones', '5 Central Avenue, Vancouver, BC', ' rjones@example.com'], ['514-867-0912', 'Sarah', 'Millar', '7 West Street, Montreal, QC', ' smillar@example.com']]

Now we can try generating data with custom arguments:

print(gen_test(10, ['email', 'username', 'password']))
[['email', 'username', 'password'], ['sales@hotmail.com', 'salesperson', 'xhA6sdk4'], ['media@gmail.com', 'mediaperson', '$q3YUjXa'], ['outreach@outlook.com', 'outreach', 'CgE5i#Nj'], ['trade@yahoo.com', 'trader', 'X5nd*bz0'], ['accounting@gmail.com', 'accountant', 'wF0$Dol7'], ['hr@outlook.com', 'hrmanager', 'gF2yD3*h'], ['marketing@hotmail.com', 'marketer', 'K5hM1#r9'], ['consulting@yahoo.com', 'consultant', 'd!$92Hp1'], ['businessdev@gmail.com', 'bdmanager', '2t#Gopn0'], ['engineering@outlook.com', 'engineer', 'TfT%V7au']]

The cool thing here is we can put any imaginable fields as we work with a very smart AI:

print(gen_test(3, ['First Name', 'Birth Year', 'Credit Card Number', 'Favorite Movie']))
[['Katie', '1986', '4916287068583236', 'Up'], ['Matthew', '1988', '4485709366735621', 'Toy Story'], ['Mia', '1976', '6011938424765310', 'The Godfather']]

Further reading

Published a year ago in #machinelearning about #python and #openai by Denys Golotiuk

Edit this article on Github
Denys Golotiuk in 2024

I'm a database architect, focused on OLAP databases for storing & processing large amounts of data in an efficient manner. Let me know if you have questions or need help.

Contact me via golotyuk@gmail.com or mrcrypster @ github