Application
Retrieval & Memory
Vespa
1Search 2and 3inference 4at 5big 6scale
the six Ws · specification
W1
Who
Maintained by Vespa.ai (originally Yahoo).
W2
What
Serves search, recommendation, and vector retrieval at scale.
W3
Where
Self-hosted clusters or Vespa Cloud.
W4
When
When retrieval must scale with vectors and filters.
W5
Why
Handles billions of items with low-latency hybrid ranking.
W6
With
A Vespa cluster plus your data and schemas.
W7
Watch
Company-maintained; open-source (Apache-2.0), self-hostable, with a managed cloud (open-core). Self-hosting keeps data on your infrastructure.