From the course: Understanding Generative AI in Cloud Computing: Services and Use Cases

Unlock this course with a free trial

Join today to access over 24,800 courses taught by industry experts.

Introduction to cloud-based APIs for generative AI

Introduction to cloud-based APIs for generative AI

From the course: Understanding Generative AI in Cloud Computing: Services and Use Cases

Start my 1-month free trial Buy for my team

Introduction to cloud-based APIs for generative AI

“

- [Narrator] APIs or application programming interfaces give applications the ability to interact and leverage generative AI systems in the cloud with minimal effort. An analogy would be leveraging a TV remote to interact with and control your TV, which is like an API. Rather than removing and maintaining your TV by rebuilding its components. As you can see, one is much easier than the other. APIs are a much easier method of interacting with generative AI systems in that we're not recreating the functionality of the system, just accessing the functionality using a well-defined interface that applications can communicate with. The developers do not need to understand the details of how generative AI systems work. They only need to find and leverage the correct interface to access the functionality required explicitly by the application. Cloud-based generative AI systems, including the APIs that define how they interact with each other, can scale up to huge loads, considering they can…

Contents