From the course: GenAIOps Foundations

Unlock this course with a free trial

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

GenAI deployment patterns

GenAI deployment patterns

- [Instructor] What are the common patterns for Gen AI apps deployment? Like general software applications, gen AI can also be either deployed in local clusters or in public clouds. It can also be a hybrid deployment. Let's explore these options in this video. We begin with the local deployment pattern. This pattern is typically used for deploying the Gen AI app on enterprise networks. The app has three substacks, namely the business application, data, and the Gen AI model. In the local deployment mode, all three substack are deployed in the local data center. The entire stack is deployed and managed by the enterprise, so they can exercise more control on the deployment, scaling, and operations, data and model protection are also taken care by the enterprise. However, it comes at a higher operations cost to run the application. Some enterprises are willing to take on the additional cost as it provides more control over security and privacy. Private clouds on cloud platforms like AWS…

Contents