Blog

Software Development & Infrastructure Insights

pgvector Without Embeddings: When a Feature Vector Beats Semantic Search

pgvector Without Embeddings: When a Feature Vector Beats Semantic Search

Almost every pgvector tutorial teaches semantic search over text and stops there. But pgvector is a nearest-neighbor engine, not an embeddings feature: for structured data where you already know what makes two things alike, a hand-built feature vector you can normalize, weight, and explain beats a black-box embedding. Here is the distinction, with a worked example from a real "find similar players" build.

Read more →