Vespa
The open big data serving engine for vector search, lexical search, and machine learning scoring.
Why consider Vespa?
Vespa is an open-source big data engine developed by Yahoo for real-time vector search, lexical search, and ML model inference over billions of documents with sub-100ms latencies.
Learn Vespa by building
Practical setup notes, real use cases, and copy-ready examples in one focused guide.
In this guide3 sections
Overview of Vespa
Vespa scales real-time search, ranking, and machine learned model inference across massive document corpora. It performs hybrid search (combining sparse BM25 text match with dense HNSW vector search) and re-ranks results with ONNX machine learning models in real-time.
Starting Vespa with Docker
docker run -d \ --name vespa \ -p 8080:8080 -p 19071:19071 \ vespaengine/vespa:latestDeploying an Application Package
vespa deploy --wait 300 path/to/application_packageQuery with vector embeddings and text filters using the REST endpoint:
curl -X POST http://localhost:8080/search/ \ -H "Content-Type: application/json" \ -d '{"yql": "select * from sources * where userInput(@query);", "query": "autonomous AI agents"}'Vespa is licensed under the Apache License Version 2.0.
Related tools
More options with a similar category or technology profile.
AI Fullstack SaaS Boilerplate
All-in-one AI SaaS starter kit with OpenAI, Anthropic, Gemini, Stripe, and Next.js.
Vibe
Transcribe audio and generate subtitles completely offline with modern UI on desktop.
Buzz
Transcribe and translate audio offline on your personal computer using OpenAI Whisper.
InvokeAI
Leading open-source generative AI creative engine for visual artists and design studios.