In this post, we reproduce the state-of-the-art baseline for retrieval-based question-answering systems within a single, scalable production ready application on Vespa.ai.
We’ve been working a lot lately on evaluating Transformer models in Vespa. Here we show how and share a bit on how we view the benefits of inference in Vespa....
In this blog post we explore how the Vespa team selected HNSW (Hierarchical Navigable Small World Graphs) as the baseline approximate nearest neighbor algorithm for extension and integration in Vespa....
The April 2020 update includes Top-K hits, smarter data migration and CloudWatch integration. Contributing to Vespa is now easier with the release of a CentOS 7 dev environment.