Skip to content
Open SourceIntermediate

pgvector

What it does

Postgres extension that adds vector similarity search to an existing database. pgvector supports exact and approximate nearest-neighbour search over single-precision, half-precision, binary and sparse vectors, so embeddings live beside the rows they describe and keep ACID guarantees, joins and point-in-time recovery.

Limits

This page states what the tool does from its public description. It does not independently verify quotas, pricing, regional availability, copyright status, or the provider’s terms. Those limits are unknown here until you check the official site.

Overview

'pgvector' is a 'Open Source' resource curated by AI Resource Hub, filed under the Open-Source Tools category and suited to Intermediate-level learners. It is provided by pgvector contributors and was last updated on 2026-11-05. Click 'Visit Resource' on the right to open the original page.

Tags

Vector databasePostgresOpen source

Key Features

  • ▹Exact and approximate nearest-neighbour search in SQL
  • ▹Multiple distance metrics including cosine, L2 and inner product
  • ▹Single-precision, half-precision, binary and sparse vector types
  • ▹HNSW and IVFFlat indexes for approximate search
  • ▹ACID compliance, point-in-time recovery and JOINs from Postgres

FAQ

For most retrieval workloads up to low tens of millions of vectors it is. Beyond that, index build times, memory for HNSW graphs and vacuum pressure become the practical limits, which is the point where a dedicated vector database earns its operational cost.

Start without an index to confirm recall on your own data, then add HNSW for latency and tune its build and search parameters. IVFFlat is an alternative when build time matters more than peak recall.