kafka-streams-machine-learning-examples icon indicating copy to clipboard operation
kafka-streams-machine-learning-examples copied to clipboard

Recommended approach to use ML inference

Open Krith-man opened this issue 2 years ago • 1 comments

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?

Krith-man avatar Nov 20 '22 21:11 Krith-man

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.

kaiwaehner avatar Nov 21 '22 06:11 kaiwaehner