Machine Learning and Real-Time Analytics in Apache Kafka Applications

This article is very useful because it discuss and compare two different options for AI model deployment: model servers with remote procedure calls (RPCs), and natively embedding models into Kafka client applications. This example uses TensorFlow, but the underlying principles are also valid for other machine learning/deep learning frameworks or products, such as H2O.ai, Deeplearning4j, Google’s Cloud Machine Learning Engine, and SAS.

Is very useful also the other details on this topic, present on the video recording and slides from my Kafka Summit San Francisco 2019 presentation: Event-Driven Model Serving: Stream Processing vs. RPC with Kafka and TensorFlow.

Learn how Apache Kafka applications can drive machine learning and real-time streaming analytic models with stream processing technology.

Source: Machine Learning and Real-Time Analytics in Apache Kafka Applications