Build Efficient Vector Search on CPUs with Neural Magic and Weaviate


We are excited to share a recent conversation between Neural Magic and Weaviate. We've been collaborating with Weaviate in an effort to help companies scale machine learning efforts to enterprise-grade production, as many business use cases require robust ML pipelines through information retrieval, semantic search, image similarity search, recommendations, classification, and more.

Weaviate is a Vector Search Engine that gives you all the structured filtering and fault-tolerance of a cloud-native database. Together with Weaviate, Neural Magic is making it more economical and easier to build these deployments by enabling sparse inference acceleration on CPUs.

We hope you enjoy this podcast with Connor Shorten and Michael Goin on how Neural Magic helps Weaviate run faster and cheaper.