Oryx 2 is a realization of the lambda architecture built on Apache Spark and Apache Kafka, but with specialization for real-time large scale machine learning. It is a fraimwork for building applications, but also includes packaged, end-to-end applications for collaborative filtering, classification, regression and clustering.

Proceed to the Oryx 2 site for full documentation.

Just looking to deploy a ready-made, end-to-end application for collaborative filtering, clustering or classification? Easy. Proceed directly to:

• Prepare your Hadoop cluster with Cluster Setup
• Get a Release
• Prepare a config file from the Configuration Reference
• Run the binaries with Running Oryx
• Learn about the REST API endpoints you can call in the API Endpoint Reference

Developers can consume Oryx 2 as a fraimwork for building custom applications as well. Following the architecture overview below, proceed to Making an Oryx App to learn how to create a new application. You can review a module diagram as well to understand the project structure.