IT wizard

Getting Started – It Looks Simpler Than You Think

25.02.2025

f you already have a basic understanding of any programming language, you can easily tap into the power of the OpenAI API with just a few lines of code. All you need is:

  1. A Python development environment (such as PyCharm, Visual Studio Code, or Jupyter Notebook)
  2. An OpenAI API key, which you can obtain by registering at OpenAI's API keys page.

That's all it takes! Now, let's dive into writing our very first simple program.

  1. from openai import OpenAI
  2. client = OpenAI(api_key='sk-proj-.....)
  3. completion = client.chat.completions.create(
  4.           model="gpt-4o-mini",
  5.           messages=[
  6.                    {"role": "system", "content": "You are a helpful assistant."},
  7.                    {
  8.                         "role": "user",
  9.                         "content": "Write a haiku about recursion in programming."
  10.                   }
  11.        ]
  12. )
  13. print(completion.choices[0].message)

And the response is:

ChatCompletionMessage(content='In code's deep embrace, \nFunctions call themselves again, \nDepths of logic's grace.', refusal=None, role='assistant', audio=None, function_call=None, tool_calls=None)

Simple, right? Now you can have some fun by experimenting with different aspects of your API calls. Try switching out the model type (line 4), testing various query formats (line 9), or tweaking the chat properties (line 6) to see how each change affects the output. This hands-on approach lets you quickly iterate and refine your project, making the development process both educational and engaging for anyone stepping into the world of smart APIs.

Happy testing! Enjoy exploring the endless possibilities of the OpenAI API, and don't hesitate to experiment with different models and parameters to tailor your project exactly to your needs.


Share