Back to Gap Map Infrastructure / Storage & Retrieval

Vespa

open source / Overall score: 3.2

Vespa is a serving platform that stores, indexes and retrieves vectors, tensors, text and structured data in one system, and evaluates ranking models over the results at query time. Retrieval combines approximate nearest neighbour search with lexical matching and filtering, and inference runs inside the serving path rather than beside it. The repository builds and runs the whole system.

Openness

5 high confidence

5.0

license: Apache-2.0(OSI)
source: public
core features withheld: no

Apache-2.0 license body confirmed. The repository is public and unarchived and builds the whole product, and the README describes no paid tier, enterprise edition or license-gated build beside it, so source is public and the core ungated.

https://raw.githubusercontent.com/vespa-engine/vespa/master/LICENSE recorded 2026-09-30
LICENSE file is the Apache-2.0 text: "Apache License" and "Version 2.0, January 2004" and "TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION".
https://raw.githubusercontent.com/vespa-engine/vespa/master/README.md recorded 2026-09-30
README states "This repository contains all the code required to build and run all of Vespa yourself," and "All the content in this repository is licensed under the Apache 2.0 license." It links a cloud service as an optional deployment ("Deploy your Vespa applications to the cloud service") beside "run your own Vespa instance"; searched the body for enterprise, paid tier and license key: none.

Adoption

2 low confidence

2.0

Vespa is deployed as a cluster from container images and RPM packages, and `pyvespa` on PyPI is a client for a running system rather than the product itself, so its downloads would measure the wrong thing. With no deployment count published, GitHub stars are the only adoption signal available, and a star does not confirm production use.

https://api.github.com/repos/vespa-engine/vespa recorded 2026-08-18
Repo metadata - stargazers_count = 7,054 - for vespa-engine/vespa.

Capability

5 medium confidence

5.0

Vespa combines vector, tensor, lexical and structured retrieval in one engine, evaluating multi-phase ranking and ML inference during serving over an elastic cluster with replication and live redistribution.

https://docs.vespa.ai/en/content/elasticity.html recorded 2026-09-30
Elasticity page states "Documents in content clusters are automatically redistributed on changes to maintain an even distribution" and "New replicas of documents are created automatically on other nodes to maintain".
https://docs.vespa.ai/en/ranking/phased-ranking.html recorded 2026-09-30
Phased ranking page states "Vespa allows expressing multiphased retrieval and ranking of documents."
https://raw.githubusercontent.com/vespa-engine/vespa/master/README.md recorded 2026-09-30
README describes the product as "Search, make inferences in and organize vectors, tensors, text and structured data, at serving time and any scale." and says Vespa is "a platform that performs these operations for you with high availability and performance."

Verified 2026-09-27