What it is
Vespa is an open source big data serving engine. Combines vector search, lexical search, ML model evaluation, and ranking in one engine. Built for serving billions of items with millisecond latency.
Why we recommend it
If you need search + recommendations + ML serving in one engine (and at scale), Vespa is the answer. It is what Yahoo uses for its search and ads serving.
When to use it
- Large-scale search (billions of items)
- Recommendation systems
- ML model serving with low latency
- When you need search + ranking + ML in one
Quickstart
Run this in your terminal. Self-hosts locally with Docker or your preferred setup.
$ docker run -d --name vespa -p 8080:8080 -p 19071:19071 vespaengine/vespaSetup
Tags
Integrates with
Common use cases
- →large-scale-search
- →recommendations
- →ml-serving
- →ranking
Pricing
Self-host: free. Vespa Cloud: from $0.05/hour. Apache-2.0 licensed.
Related projects
Apache Solr
by Apache Solr
Apache Solr is the original open source search server built on Apache Lucene. Battle-tested since 2004, full-text search, faceted search, geospatial, ML model upload, vector search (recent).
Manticore Search
by Manticore Search
Manticore Search is a fast, multi-threaded search engine. SQL-first (MySQL protocol), full-text search, vector search, faceted search, real-time indexing. The fastest ES alternative.
Meilisearch
by Meilisearch
Meilisearch is a search engine that you can drop into any app with a single Docker container. Sub-50ms search latency, typo tolerance, faceting, filtering, ranking rules, and a clean API. Free, MIT-licensed, no per-query fees.