Site and app search
Give users results that understand both the words they type and what they mean.
Vector database
Text, vector and hybrid search in one fast engine.
vecsai DB stores your documents and their embeddings side by side and answers keyword, semantic and hybrid queries in milliseconds. It is written in Go, ships as a single binary, and is configured with a schema rather than a pipeline. Our own search and recommendation products run on it.
warm jacket for wet hikes
- Alpine Shell JacketWaterproof · insulated · hiking0.94
- Trailhead Down ParkaWarm · water-resistant0.91
- Ridge 3-in-1 JacketRemovable fleece liner0.88
Filtered: in stockexample
Features
What vecsai DB does
Hybrid search, built in
Combine keyword relevance and vector similarity in a single request and tune the balance per query. No second system, no merging results in your application.
Fast full-text search
Typo tolerance, prefix matching, synonyms, field weighting and highlighting, out of the box.
Vector search
Store embeddings next to your documents and run approximate nearest-neighbour queries over them, with the same filters you use for text.
Filtering and faceting
Filter by any field — price, region, availability, rights — and return facet counts in the same response.
Real-time writes
Documents are searchable as soon as they are written. Updates and deletes apply immediately, with no reindex window.
Simple to run
A single Go binary with sensible defaults. Run it in our cloud or on your own infrastructure.
Use cases
Where teams use it
Semantic retrieval for AI
Use vecsai DB as the retrieval layer for RAG pipelines, chat assistants and agents.
Similar-item lookup
Find visually or semantically similar products, articles or videos from their embeddings.
FAQ
Questions about vecsai DB
How is vecsai DB different from other vector databases?
It is search-first. Full-text relevance, filtering and faceting are first-class features, not an add-on, so hybrid search works without a second engine.
Do I need to bring my own embeddings?
You can send your own vectors, or let vecsai generate them from your text fields when documents are written.
Can I run it on my own servers?
Yes. vecsai DB runs in our managed cloud or on infrastructure you operate.
Works with
The rest of the platform
vecsai Search
Search that understands what people mean.
Learn morevecsai Recommend
Personal recommendations for every user, in real time.
Learn morevecsai Sim
See the effect of a change before your users do.
Learn moreSee vecsai on your own catalogue
Tell us about your platform and we will show you search, recommendations and simulation running on your data.