weaviate
A vector database that owns more of the pipeline, embedding models included.
What it is
Weaviate is a vector database that stores objects together with their vectors rather than treating the embedding as an add-on column. Each record carries its properties and its vector, and you can query by vector, by property, or by both at once.
Its distinguishing feature is the module system. Embedding and generation models plug in as modules, so Weaviate can vectorize your text on the way in and call a language model on the way out, removing a separate embedding service from your stack. Hybrid search blends keyword and vector scoring in one query.
It is aimed at teams building search or RAG over a body of content who want the database to own more of the pipeline. The trade-off is more configuration to learn than a plain vector store requires.
Why we recommend it
The database can do the embedding for you
With a vectorizer module enabled you send text and Weaviate calls the embedding model itself. That removes a moving part from the ingestion path and keeps the two sides in sync.
Hybrid search in one query
Keyword search and vector search fail in different ways; blending both scores covers exact terms and fuzzy meaning together. Doing that properly normally means running two systems — here it is built in.
A real query language, not just a lookup
GraphQL and REST cover filters, aggregations and generative queries without you writing custom endpoints around the database.
Open source with a commercial backer
Weaviate B.V. sells a managed cloud built on the same open source core, which funds continued development and means the project is unlikely to be abandoned.
How it scores
These are our editorial ratings, not benchmark results. We score on how the project behaves in practice — how long it takes to get running, how good the documentation is, how responsive the maintainers are, and how well it holds up over time. The licence and star count above are read from GitHub and are a snapshot.
Pros and cons
Strengths
- Objects and vectors stored together, with structured filters and full-text search alongside similarity
- Built-in module system for vectorizers and generative models
- Hybrid search combining BM25 keyword scoring with vector similarity
- Horizontal scaling and replication supported in the open source distribution
- Clear documentation and a managed cloud for teams that want zero operations
Trade-offs
- More concepts to learn than a plain vector store — schema, classes, modules, tenants
- The module system ties parts of your pipeline to Weaviate configuration, which is harder to swap out later
- Runs several container images once modules are enabled, so it is not a single-binary install
- Resource use is on the heavier side for small deployments
How to get it
Direct download
Clicking a button downloads the file straight from the project's release — you stay on this page.
Source and documentation
At a glance
| Category | Vector DB |
|---|---|
| Licence | See repo |
| Written in | Go |
| GitHub stars | 16,798 |
| Repository | weaviate/weaviate |
Licence and star count were read from the GitHub API when this page was generated and are a snapshot. Check the repository for the current figure and the authoritative licence text.
Other Vector DB tools
We are not affiliated with weaviate or its maintainers. We list it because it is genuinely useful and genuinely free. If you plan to build a commercial product on top of it, read the licence on the repository first.