From the course: MLOps Essentials: Model Deployment and Monitoring
Join today to access over 24,400 courses taught by industry experts.
Serving multiple models
From the course: MLOps Essentials: Model Deployment and Monitoring
Serving multiple models
- [Instructor] Let's look at scenarios where multiple models are used in an ML solution. An ML solution may use multiple related models to provide overall user experience. Solution design and deployment should consider this case and optimize across all models. There are multiple ways in which models can be deployed together. Let's review some of the popular configurations. First is the chained models pattern. Here models are chained in sequence. The output of one model becomes the input to the next model. For example, let's consider a chatbot that is answering questions asked by the user. After the user enters their query, the first model would try to understand the context or intent of the user. This is then provided as input to the next model, which would extract information that is relevant to the context. Finally, the information and context are provided to another model that will pull out the best answer to the…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.
