In this post, we’ll discuss the role of model serving in building a real-time streaming application and reveal how to implement and deploy machine learning (ML) models with open-source frameworks Cloudflow and Seldon.

This is the last post in our cloud-native series that focuses on Machine Learning in streaming data applications.

In a survey of over 800 software professionals, we asked in which use cases real-time stream processing was most used, discovering that streaming is being embraced heavily for both traditional functionalities like ETL and monitoring, as well as new ones like ML/AI...

In this blog post we will look at different implementations of model serving as a service and show how to use one of the most popular models servers, TensorFlow Serving.

In this series on Machine Learning with Akka Streams, Kafka Streams, Apache Flink, and Apache Spark, author Boris Lublinsky shares how dynamically controlled streams can be a very powerful pattern for implementing streaming applications.

In this post, author Boris Lublinsky demonstrates with code how dynamically controlled streams can be implemented leveraging Akka Streams, and the main properties of such implementation.

In this post, author Boris Lublinsky demonstrates with code how dynamically controlled streams can be implemented leveraging Kafka Streams, and the main properties of such implementation.

In this post, author Boris Lublinsky demonstrates with code how dynamically controlled streams can be implemented leveraging Apache Flink, and the main properties of such implementation.

In this post, author Boris Lublinsky demonstrates with code how dynamically controlled streams can be implemented leveraging Apache Spark, specifically Spark Structured Streaming, and the main properties of such implementation.

In a survey of over 800 software professionals, we asked in which use cases real-time stream processing was most used—and revealed an astonishing 500% increase in Machine Learning and Artificial Intelligence use cases in the last 2 years.

Welcome to this technical series on getting long-term value from Machine Learning (ML) with Kubeflow on Lightbend Platform with Red Hat OpenShift.

In Part 1 of this series “How To Deploy And Use Kubeflow On Red Hat OpenShift”, we discussed what Kubeflow is, and how it can be useful for running Machine Learning applications in production. In this post, we discuss installation of Kubeflow.

In Part 2 of “How To Deploy And Use Kubeflow On OpenShift”, we looked at Installation and some of the additional components used by Kubeflow, such as Ambassador, Spartakus, Argo, Minio, etc. In this post, we will describe and show how to use some of them.

In Part 3 of “How To Deploy And Use Kubeflow On OpenShift”, we looked at Kubeflow support components like Argo, Ambassador, Minio, and Spartakus. In this post, we look at using JupyterHub.

In Part 4 of “How To Deploy And Use Kubeflow On OpenShift”, we looked at setting up and using JupyterHub with Kubeflow. In this post, we look closer at running Machine Learning jobs with TensorFlow.

In Part 5 of “How To Deploy And Use Kubeflow On OpenShift”, we looked at machine learning in production. In this part, we turn our attention to tuning ML parameters with Kubeflow and Katib.

In Part 6 of “How To Deploy And Use Kubeflow On OpenShift”, we examined Kubeflow ML parameters tuning. In this part, we look at serving ML models in production.

In Part 7 of “How To Deploy And Use Kubeflow On OpenShift”, we looked at model serving with Kubeflow. In this part, we now look at deploying Kubeflow pipelines.

In the last article in “How To Deploy And Use Kubeflow On OpenShift”, we looked at deployment operations using Kubeflow pipelines. In this final part of the series, we look at model management as the last component of Kubeflow that we will describe, ModelDB.

In this intermediate level presentation for Architects, Data Scientists, Developers with O’Reilly author and Lightbend Principal Architect, Boris Lublinsky, we will define an alternative approach to model serving, based on treating the model itself as data.