Redis and Spark are coming a bit closer together. Redis Labs today announced a new project, Redis-ML, to bring Spark-based machine learning capabilities to the Redis database. The combination will provide a faster place to store a trained Spark machine learning model.
Redis-ML is hosted on GitHub and will be demonstrated at the Big Data London conference tomorrow. Using Redis-ML, trained machine learning models can be stored and utilized faster than with traditional Spark ML solutions.
(Related: Machine learning’s place in Big Data)
Dvir Volk, senior architect at Redis Labs, said, “The Redis-ML module with Apache Spark, delivers lightning-fast classifications with larger data sizes, in real time and under heavy load, while allowing many applications developed in different languages to simultaneously utilize the same models. The Redis-ML module is a great demonstration of the power of Redis Modules API in supporting the cutting-edge needs of next-generation applications.”
Another benefit of Redis-ML is untying a model from its original language. Through Redis, these models can be accessed with other languages, like .NET and Scala. Additionally, storing Spark ML models in Redis-ML enables them to be scaled out in memory rather than on disk.
