Are you using the OpenAI API in your projects?
If so, then I'm going to tell you right now that there is probably a better way to do that.
In this video, I share everything that you need to know about getting structured output from OpenAI in order to build more reliable systems with LLMs.
We compare prompting techniques, JSON mode, function calling, and the Instructor library to find the best way to integrate OpenAI models into applications.
The video is linked below. I hope you find it helpful. If you do, consider subscribing :)