Neon is Generally Available! Serverless Postgres with branching to boost your development velocity.Read more

Changelog

The latest product updates from Neon

On-disk support for HNSW indexes with pg_embedding

Neon's pg_embedding extension, which enables graph-based vector similarity search in Postgres using the Hierarchical Navigable Small World (HNSW) algorithm (HNSW), now persists HNSW indexes to disk. In the previous pg_embedding version (0.1.0 and earlier), indexes resided in memory.

Additionally, pg_embedding now supports cosine and Manhattan distance metrics.

  • Cosine distance

    CREATE INDEX ON documents USING hnsw(embedding ann_cos_ops) WITH (dims=3, m=3, efconstruction=5, efsearch=5);
    SELECT id FROM documents ORDER BY embedding <=> array[3,3,3] LIMIT 1;
  • Manhattan distance

    CREATE INDEX ON documents USING hnsw(embedding ann_manhattan_ops) WITH (dims=3, m=3, efconstruction=5, efsearch=5);
    SELECT id FROM documents ORDER BY embedding <~> array[3,3,3] LIMIT 1;

If you have an existing pg_embedding installation and want to upgrade to the new version, see Upgrade to pg_embedding with on-disk indexes for instructions.

Also, be sure to check out the new Neon AI page on our website, and our docs, which include links to new AI example applications built with Neon Serverless Postgres.

Back to all changelog posts