structured output completion example

[akshana-aravind]

Purpose

• Structured outputs allow you to enforce a specific JSON Schema definition when making an inference API call. This means you can dictate exactly what the output should look like, ensuring that it conforms to the structure you expect.
  This feature is particularly beneficial for scenarios where you need to call specific functions based on the output. By using structured outputs, you can be confident that the necessary parameters and formats are adhered to, facilitating smoother integration with your applications.

Does this introduce a breaking change?

[ ] Yes
[X] No

Pull Request Type

What kind of change does this Pull Request introduce?

[ ] Bugfix
[X] Feature
[ ] Code style update (formatting, local variables)
[ ] Refactoring (no functional changes, no api changes)
[ ] Documentation content changes
[ ] Other... Please describe:

How to Test

• Get the code

git clone https://github.com/akshana-aravind/azureopenai.git
cd azureopenai
git checkout main
npm install

Test the code

Run it as a normal colab Notebook in any  compatible environment or IDE i.e  VS code, pycharm etc. -

What to Check

Verify that the following are valid

• Standard Azure OpenAI credentials are correct .

Other Information

[akshana-aravind]

@microsoft-github-policy-service agree

[akshana-aravind]

@colombod can I please get a review on this when you get a chance. Thanks.