Search icon
Arrow left icon
All Products
Best Sellers
New Releases
Books
Videos
Audiobooks
Learning Hub
Newsletters
Free Learning
Arrow right icon
Engineering MLOps

You're reading from  Engineering MLOps

Product type Book
Published in Apr 2021
Publisher Packt
ISBN-13 9781800562882
Pages 370 pages
Edition 1st Edition
Languages
Author (1):
Emmanuel Raj Emmanuel Raj
Profile icon Emmanuel Raj

Table of Contents (18) Chapters

Preface Section 1: Framework for Building Machine Learning Models
Chapter 1: Fundamentals of an MLOps Workflow Chapter 2: Characterizing Your Machine Learning Problem Chapter 3: Code Meets Data Chapter 4: Machine Learning Pipelines Chapter 5: Model Evaluation and Packaging Section 2: Deploying Machine Learning Models at Scale
Chapter 6: Key Principles for Deploying Your ML System Chapter 7: Building Robust CI/CD Pipelines Chapter 8: APIs and Microservice Management Chapter 9: Testing and Securing Your ML Solution Chapter 10: Essentials of Production Release Section 3: Monitoring Machine Learning Models in Production
Chapter 11: Key Principles for Monitoring Your ML System Chapter 12: Model Serving and Monitoring Chapter 13: Governing the ML System for Continual Learning Other Books You May Enjoy

Old is gold – REST API-based microservices

Old is gold. Plus, it's better to start somewhere where there are various API protocols. The Representational State Transfer (REST) protocol has become a gold standard for many applications over the years, and it's not so very different for ML applications today. The majority of companies prefer developing their ML applications based on the REST API protocol. 

A REST API or RESTful API is based on REST, an architectural method used to communicate mainly in web services development.

RESTful APIs are widely used; companies such as Amazon, Google, LinkedIn, and Twitter use them. Serving our ML models via RESTful APIs has many benefits, such as the following: 

  • Serve predictions on the fly to multiple users.
  • Add more instances to scale up the application behind a load balancer.
  • Possibly combine multiple models using different API endpoints.
  • Separate our model operating environment from the user...
lock icon The rest of the chapter is locked
Register for a free Packt account to unlock a world of extra content!
A free Packt account unlocks extra newsletters, articles, discounted offers, and much more. Start advancing your knowledge today.
Unlock this book and the full library FREE for 7 days
Get unlimited access to 7000+ expert-authored eBooks and videos courses covering every tech area you can think of
Renews at $15.99/month. Cancel anytime}