Conclusion : Streaming model workflows
Discover how to build scalable streaming model pipelines for real-time machine learning using Kafka and PubSub. Learn the challenges of low-latency operations and approaches like precomputing aggregates, as well as trade-offs between self-managed and managed streaming platforms.
We'll cover the following...
We'll cover the following...
Streaming model pipelines are useful for systems that need to apply ML models in real-time. To build these types of pipelines, we explored two message brokers that can scale to large volumes of events and provide data sources and data sinks for these pipelines. Streaming pipelines often constrain ...