Vecs: Vector Store Client backed by PostgreSQL/pgvector

Vector search is a key component in building AI chatbots and semantic document search.

Vecs is a python client storing and searching vectors backed by Postgres and pgvector. It gives a familiar collection-like interface to upserting and searching.

The stack it uses is fully open source and is compatible with any Postgres vendor with the pgvector extension like Supabase or RDS + is self hostable

ai chatbots building chatbots client collection open source postgres postgresql python search searching semantic stack vector vectors vector search vendor