search

kaiwaehner / kafka-streams-machine-learning-examples

This project contains examples which demonstrate how to deploy analytic models to mission-critical, scalable production environments leveraging Apache Kafka and its Streams API. Models are built with Python, H2O, TensorFlow, Keras, DeepLearning4 and other technologies.
Apache License 2.0
840 stars 304 forks source link

Recommended approach to use ML inference #23

Open Krith-man opened 1 year ago

Krith-man commented 1 year ago

Hello this repo is very helpful, but it is 4 years old. Is this still the recommended way to use ML inference with Kafka Streams?

kaiwaehner commented 1 year ago

Yes. Absolutely.

Embedding an analytic model is the appropriate way to do reliable model scoring with low latency.

Some model servers also add native Kafka interfaces (see, e.g., https://www.kai-waehner.de/blog/2020/10/27/streaming-machine-learning-kafka-native-model-server-deployment-rpc-embedded-streams/). This is another good option for some use cases, but not as robust and fast.