
pgvecto.rs
PostgreSQL vector search can use pgvecto.rs, an extension described as scalable and low latency.

About pgvecto.rs
pgvecto.rs is a PostgreSQL extension that provides vector similarity search functions. It adds a vector(n) data type, distance operators for squared Euclidean, negative dot product and cosine distance, filtering for vector search with relational queries, and binary, FP16 and INT8 vector types. It is written in Rust using pgrx and can be run from a Docker image and enabled with CREATE EXTENSION vectors.
Dimensions are limited to 1 to 65535, and an index cannot be created when stored values do not match the column dimension. Write-ahead logging covers data while index support is still in progress. The repository notes a newer implementation, VectorChord, and encourages migration to it.
Key features
- Vector similarity search functions inside PostgreSQL via extension
- vector(n) data type for n-dimensional vectors up to 65535 dimensions
- Distance operators for squared Euclidean, dot product, cosine distance
- Filtering with relational queries via VBASE method
- Additional binary, FP16, and INT8 vector data types
- Docker image for setup with PostgreSQL 17 example
- Supports vectors up to 65535 dimensions
- Includes binary, FP16, and INT8 vector data types
- Supports filtering for vector search combined with relational queries
- Write-ahead logging for indexes is still in progress
- Indexes cannot be created when values do not match the column dimension
- Maintainers encourage users to migrate to VectorChord
pgvecto.rs at a glance
- Category
- Development › APIs & Databases
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Open source
- Yes · Source code
- Language
- English
- Last checked
- Oct 6, 2026 · Online when checked
- Listed
- Oct 5, 2026
Guides for APIs & Databases

pgvecto.rs alternatives
Tools and sites you could use instead, ranked by how closely they match.
ParadeDB adds full text search, vector retrieval, and aggregations to PostgreSQL.
An open-source vector database, Weaviate stores objects and vectors and supports vector search.
Distributed vector search is provided by Vald, an engine designed to scale across deployments.
Vector search and storage are the focus of VectorDB, a Python vector database project.
AI search and serving structured data are provided by Vespa, an open-source software platform.
A SQL database with Git-style version control, Dolt supports branching, merging, pushing, and pulling data.
Popular in APIs & Databases
Well-known listings from the same topic.
pgvecto.rs FAQ
How do I enable pgvecto.rs in PostgreSQL?
How do I start a test instance with Docker?
Which distance operators are available?
Tell us and an editor will check it.
Claim the listing and suggest updates yourself. An editor checks every claim first.












