HNSW

An HNSW index creates a multilayer graph. It has better query performance than IVFFlat (in terms of speed-recall tradeoff), but has slower build times and uses more memory. Also, an index can be created without any data in the table since there isn’t a training step like IVFFlat.

Add an index for each distance function you want to use.

L2 distance

CREATE INDEX ON items USING hnsw (embedding vector_l2_ops);

Note: Use halfvec_l2_ops for halfvec and sparsevec_l2_ops for sparsevec (and similar with the other distance functions)

Inner product

CREATE INDEX ON items USING hnsw (embedding vector_ip_ops);

Cosine distance

CREATE INDEX ON items USING hnsw (embedding vector_cosine_ops);

L1 distance

CREATE INDEX ON items USING hnsw (embedding vector_l1_ops);

Hamming distance

CREATE INDEX ON items USING hnsw (embedding bit_hamming_ops);

Jaccard distance

CREATE INDEX ON items USING hnsw (embedding bit_jaccard_ops);

Supported types are:

• vector - up to 2,000 dimensions
• halfvec - up to 4,000 dimensions
• bit - up to 64,000 dimensions
• sparsevec - up to 1,000 non-zero elements

Index Options

Specify HNSW parameters

• m - the max number of connections per layer (16 by default)
• ef_construction - the size of the dynamic candidate list for constructing the graph (64 by default)

CREATE INDEX ON items USING hnsw (embedding vector_l2_ops) WITH (m = 16, ef_construction = 64);

A higher value of ef_construction provides better recall at the cost of index build time / insert speed.

Query Options

Specify the size of the dynamic candidate list for search (40 by default)

SET hnsw.ef_search = 100;

A higher value provides better recall at the cost of speed.

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

BEGIN;
SET LOCAL hnsw.ef_search = 100;
SELECT ...
COMMIT;

Index Build Time

Indexes build significantly faster when the graph fits into maintenance_work_mem

SET maintenance_work_mem = '8GB';

A notice is shown when the graph no longer fits

NOTICE:  hnsw graph no longer fits into maintenance_work_mem after 100000 tuples
DETAIL:  Building will take significantly more time.
HINT:  Increase maintenance_work_mem to speed up builds.

Note: Do not set maintenance_work_mem so high that it exhausts the memory on the server

Like other index types, it’s faster to create an index after loading your initial data

You can also speed up index creation by increasing the number of parallel workers (2 by default)

SET max_parallel_maintenance_workers = 7; -- plus leader

For a large number of workers, you may need to increase max_parallel_workers (8 by default)

The index options also have a significant impact on build time (use the defaults unless seeing low recall)

Indexing Progress

Check indexing progress

SELECT phase, round(100.0 * blocks_done / nullif(blocks_total, 0), 1) AS "%" FROM pg_stat_progress_create_index;

The phases for HNSW are:

1. initializing
2. loading tuples