This page lists large upcoming features in Vespa.
To make it easy to keep up to date, we're not listing smaller items, nor
work that we consider improvements to existing features. These are often tracked by
GitHub issues.
Launching soon
Production support for the ARM64 (AArch64) architecture.
Document Summary fetch optimizations +
support for dynamic summary / bolding for array<string> fields.
Paged support for sparse & mixed tensor attributes.
In progress
New sample applications for hybrid/vector search.
Tensor math optimizations for hash-like lookups.
New python learn-to-rank module for data science.
New Data Logging feature for simplified Amazon Kinesis (and the likes) export.
Priority backlog
Support for high-performance feeding in the Vespa CLI.
Online learning: Global tensors mutable at a high continuous rate.
Global multi-region feeding: Feed once, globally, with automatic resync.