Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
pg_embedding: Scale AI to millions
Learn how pg_embedding’s HNSW index in Postgres scales AI applications to millions of rows, offering a 20× performance boost over pgvector and serverless integration comparisons.
Scaling databases is hard. This remains true even for vector databases.
Nearly 50% of professional developers use Postgres, and many of them are building LLMs apps. The issue is that it is hard to scale with pgvector because of limitations around IVF index.
As a response, we built and open sourced pg_embedding, which implements HNSW index in Postgres and performs 20x better than pgvector, to help developers scale their AI apps to millions of rows.
In this talk, we will see how pg_embedding and its serverless driver perform against some well-known vector databases.
PostgreSQL extension implements HNSW algorithm for efficient vector similarity search.