Azure OpenAI Service for Cloud Native Applications

Preface

I cannot hide my excitement. The 2022–2024 period has been one of the most amazing moments of the modern technology era. Some call it the “iPhone moment” of artificial intelligence, and a lot of people are now discovering the actual potential of AI. But I don’t think that’s all it is. I believe we are entering an exponential phase where all technological advancements move so fast that it is difficult to keep track of them. But that is wonderful. Several years of progress and industry competition in just a few months. What was often thought of as impossible (or even magic) is now a reality…and it’s just getting started.

That sense of innovation and complete disruption is how I felt the first time I tried the Azure OpenAI Studio. I got early access as an AI Specialist at Microsoft. It was a very early version, and definitively not the Studio and related features and models we have today, but it was very promising. Little did we know that this cloud-enabled service was about to become the superstar of the generative AI era. And it was a reality, not a concept or a future product. It was something we could use to create our very own GPT-style implementations, with different models and cost/performance trade-offs, but also with relatively low implementation and deployment complexity.

After a few months of testing and tracking new functionalities, OpenAI released ChatGPT. Boom. I have never seen such a viral moment related to AI technologies. Even at Microsoft, the feeling ...