Supabase Vecs: a vector client for Postgres

Summary

Vecs is a new Python library for managing embeddings in Postgres databases that use pgvector, offering a vector-store-like interface for table creation, indexing, querying, and metadata filtering. Collections are stored in a vecs schema with an id text primary key, a vector column, and JSONB metadata; queries support cosine distance, l2 distance, and maximum inner dot product, with optional filters and returned values. A short Python workflow can create a collection, upsert records, create an index after insertion, and search by vector; the collection can also be queried without an index. With Supabase, a collection can be exposed through a public-schema view and accessed from supabase-js, while proposed preprocessing transforms and an asynchronous client remain under debate.

Takeaways

1. 1

   get_or_create_collection creates a table in the vecs schema with an id text primary key, a vector column sized to the declared dimension, and a non-null JSONB metadata column.

2. 2

   Collection.upsert adds a record when its user-defined identifier is new and updates the existing record when that identifier already exists.

3. 3

   The proposed transformation pipeline and asynchronous client are mock code only and remain subjects of debate in the referenced feature requests.