vectorize

Overview

Package 0.27.1; SQL control version 0.23.0. Requires preload with pg_cron; built with pgrx 0.19.2.

Version

Build

You can build the RPM / DEB packages for pg_vectorize using pig build:

pig build pkg pg_vectorize         # build RPM / DEB packages

Install

You can install pg_vectorize directly. First, make sure the PGDG and PIGSTY repositories are added and enabled:

pig repo add pgsql -u          # Add repo and update cache

Install the extension using pig or apt/yum/dnf:

pig install pg_vectorize;          # Install for current active PG version

pig ext install -y pg_vectorize -v 18  # PG 18
pig ext install -y pg_vectorize -v 17  # PG 17
pig ext install -y pg_vectorize -v 16  # PG 16
pig ext install -y pg_vectorize -v 15  # PG 15
pig ext install -y pg_vectorize -v 14  # PG 14

dnf install -y pg_vectorize_18       # PG 18
dnf install -y pg_vectorize_17       # PG 17
dnf install -y pg_vectorize_16       # PG 16
dnf install -y pg_vectorize_15       # PG 15
dnf install -y pg_vectorize_14       # PG 14

apt install -y postgresql-18-pg-vectorize   # PG 18
apt install -y postgresql-17-pg-vectorize   # PG 17
apt install -y postgresql-16-pg-vectorize   # PG 16
apt install -y postgresql-15-pg-vectorize   # PG 15
apt install -y postgresql-14-pg-vectorize   # PG 14

Preload:

shared_preload_libraries = 'pg_cron, vectorize';

Create Extension:

CREATE EXTENSION vectorize CASCADE;  -- requires: pg_cron, pgmq, vector

Usage

Sources: repo README, extension README, v0.26.2 release

vectorize is the PostgreSQL extension from pg_vectorize. Upstream documents two modes: a standalone HTTP service and the in-database SQL extension. For the packaged extension here, the SQL workflow is the relevant one.

Enable The Extension

ALTER SYSTEM SET shared_preload_libraries = 'vectorize,pg_cron';
ALTER SYSTEM SET cron.database_name = 'postgres';

CREATE EXTENSION vectorize CASCADE;

The extension README lists pg_cron, pgmq, and pgvector as dependencies, plus vectorize.embedding_service_url for the embedding service.

Create A Search Job

The high-level SQL API starts with vectorize.table():

SELECT vectorize.table(
  job_name    => 'product_search_hf',
  relation    => 'products',
  primary_key => 'product_id',
  columns     => ARRAY['product_name', 'description'],
  transformer => 'sentence-transformers/all-MiniLM-L6-v2',
  schedule    => 'realtime'
);

The extension README says this creates and maintains an embeddings column for the source table.

Search, RAG, And Direct Model Calls

Search with:

SELECT * FROM vectorize.search(
  job_name       => 'product_search_hf',
  query          => 'accessories for mobile devices',
  return_columns => ARRAY['product_id', 'product_name'],
  num_results    => 3
);

Upstream also documents:

• vectorize.rag() for retrieval-augmented answers.
• vectorize.generate() for text generation.
• vectorize.encode() for direct embedding generation.
• vectorize.import_embeddings() for loading precomputed vectors.

Update Behavior And v0.26.2 Note

The extension README says schedule => '* * * * *' checks for updates every minute, while schedule => 'realtime' creates triggers for immediate refresh on inserts and updates.

pg_vectorize 0.26.2 updates vector-serve and security-related dependencies; there is no material SQL/API delta beyond the existing README surface.