pgvector: Open-source vector similarity search for Postgres

pgvector

Open-source vector similarity search for Postgres

CREATE TABLE items (embedding vector(3));
CREATE INDEX ON items USING ivfflat (embedding vector_l2_ops);
SELECT * FROM items ORDER BY embedding <-> '[1,2,3]' LIMIT 5;

Supports L2 distance, inner product, and cosine distance

Installation

Compile and install the extension (supports Postgres 11+)

git clone --branch v0.4.0 https://github.com/pgvector/pgvector.git
cd pgvector
make
make install # may need sudo

Then load it in databases where you want to use it

You can also install it with Docker, Homebrew, PGXN, or conda-forge

Getting Started

Create a vector column with 3 dimensions

CREATE TABLE items (embedding vector(3));

Insert values

INSERT INTO items VALUES ('[1,2,3]'), ('[4,5,6]');

Get the nearest neighbor by L2 distance

SELECT * FROM items ORDER BY embedding <-> '[3,1,2]' LIMIT 1;

Also supports inner product (<#>) and cosine distance (<=>)

Note: <#> returns the negative inner product since Postgres only supports ASC order index scans on operators

Indexing

Speed up queries with an approximate index. Add an index for each distance function you want to use.

L2 distance

CREATE INDEX ON items USING ivfflat (embedding vector_l2_ops);

Inner product

CREATE INDEX ON items USING ivfflat (embedding vector_ip_ops);

Cosine distance

CREATE INDEX ON items USING ivfflat (embedding vector_cosine_ops);

Indexes should be created after the table has some data for optimal clustering. Also, unlike typical indexes which only affect performance, you may see different results for queries after adding an approximate index. Vectors with up to 2,000 dimensions can be indexed.

Index Options

Specify the number of inverted lists (100 by default)

CREATE INDEX ON items USING ivfflat (embedding vector_l2_ops) WITH (lists = 100);

A good place to start is 4 * sqrt(rows)

Query Options

Specify the number of probes (1 by default)

A higher value improves recall at the cost of speed.

Use SET LOCAL inside a transaction to set it for a single query

BEGIN;
SET LOCAL ivfflat.probes = 1;
SELECT ...
COMMIT;

Indexing Progress

Check indexing progress with Postgres 12+

SELECT phase, tuples_done, tuples_total FROM pg_stat_progress_create_index;

The phases are:

1. initializing
2. performing k-means
3. sorting tuples
4. loading tuples

Note: tuples_done and tuples_total are only populated during the loading tuples phase

Partial Indexes

Consider partial indexes for queries with a WHERE clause

SELECT * FROM items WHERE category_id = 123 ORDER BY embedding <-> '[3,1,2]' LIMIT 5;

can be indexed with:

CREATE INDEX ON items USING ivfflat (embedding vector_l2_ops) WHERE (category_id = 123);

To index many different values of category_id, consider partitioning on category_id.

CREATE TABLE items (embedding vector(3), category_id int) PARTITION BY LIST(category_id);

Performance

To speed up queries without an index, increase max_parallel_workers_per_gather.

SET max_parallel_workers_per_gather = 4;

To speed up queries with an index, increase the number of inverted lists (at the expense of recall).

CREATE INDEX ON items USING ivfflat (embedding vector_l2_ops) WITH (lists = 1000);

Reference

Vector Type

Each vector takes 4 * dimensions + 8 bytes of storage. Each element is a single precision floating-point number (like the real type in Postgres), and all elements must be finite (no NaN, Infinity or -Infinity). Vectors can have up to 16,000 dimensions.

Vector Operators

Operator	Description
+	element-wise addition
-	element-wise subtraction
<->	Euclidean distance
<#>	negative inner product
<=>	cosine distance

Vector Functions

Function	Description
cosine_distance(vector, vector) → double precision	cosine distance
inner_product(vector, vector) → double precision	inner product
l2_distance(vector, vector) → double precision	Euclidean distance
vector_dims(vector) → integer	number of dimensions
vector_norm(vector) → double precision	Euclidean norm

Aggregate Functions

Function	Description
avg(vector) → vector	arithmetic mean

Libraries

Frequently Asked Questions

How many vectors can be stored in a single table?

A non-partitioned table has a limit of 32 TB by default in Postgres. A partitioned table can have thousands of partitions of that size.

Is replication supported?

Yes, pgvector uses the write-ahead log (WAL), which allows for replication and point-in-time recovery.

What if I want to index vectors with more than 2,000 dimensions?

Two things you can try are:

1. use dimensionality reduction
2. compile Postgres with a larger block size (./configure --with-blocksize=32) and edit the limit in src/ivfflat.h

Additional Installation Methods

Docker

Get the Docker image with:

docker pull ankane/pgvector

This adds pgvector to the Postgres image (run it the same way).

You can also build the image manually:

git clone --branch v0.4.0 https://github.com/pgvector/pgvector.git
cd pgvector
docker build -t pgvector .

Homebrew

With Homebrew Postgres, you can use:

brew install pgvector/brew/pgvector

PGXN

Install from the PostgreSQL Extension Network with:

conda-forge

Install from conda-forge with:

conda install -c conda-forge pgvector

This method is community-maintained by @mmcauliffe

Hosted Postgres

pgvector is available on these providers.

To request a new extension on other providers:

• Amazon RDS - follow the instructions on this page
• Google Cloud SQL - vote or comment on this page
• DigitalOcean Managed Databases - vote or comment on this page
• Azure Database - vote or comment on this page

Upgrading

Install the latest version and run:

ALTER EXTENSION vector UPDATE;

Upgrade Notes

0.4.0

If upgrading with Postgres < 13, remove this line from sql/vector--0.3.2--0.4.0.sql:

ALTER TYPE vector SET (STORAGE = extended);

Then run make install and ALTER EXTENSION vector UPDATE;.

0.3.1

If upgrading from 0.2.7 or 0.3.0, recreate all ivfflat indexes after upgrading to ensure all data is indexed.

-- Postgres 12+
REINDEX INDEX CONCURRENTLY index_name;

-- Postgres < 12
CREATE INDEX CONCURRENTLY temp_name ON table USING ivfflat (column opclass);
DROP INDEX CONCURRENTLY index_name;
ALTER INDEX temp_name RENAME TO index_name;

Thanks

Thanks to:

History

View the changelog

Contributing

Everyone is encouraged to help improve this project. Here are a few ways you can help:

To get started with development:

git clone https://github.com/pgvector/pgvector.git
cd pgvector
make
make install

To run all tests:

make installcheck        # regression tests
make prove_installcheck  # TAP tests

To run single tests:

make installcheck REGRESS=functions                    # regression test
make prove_installcheck PROVE_TESTS=test/t/001_wal.pl  # TAP test

To enable benchmarking:

make clean && PG_CFLAGS=-DIVFFLAT_BENCH make && make install

Resources for contributors

from Hacker News https://ift.tt/wXgNP7s