Semantic searchis a new form ofmachine learningpowered search that doesn’t rely on any form of keyword matching, but transforms text into embeddingsandperforms nearest neighborssearch.

Semantic searchusesmachine learningto understand the meaning of text by converting it into numerical vectors, allowing for more accurateandcontext-awaresearch results.

It is not a complete replacement for fulltext search. In many cases fulltext searchis capable of outperformingsemantic search. Specifically, if a user knows the exact phrasein a documentthey want to match, fulltext search is faster and guaranteed to return the correct result while semantic search is only likely to return the correct result. Fulltext search and semantic search can be combined to create powerful and robust search systems.

It is not a complete replacement for full-text search. In many cases, full-text searchcan outperformsemantic search. Specifically, if a user knows the exact phrase they want to match in a document, full-text search is faster and guaranteed to return the correct result, whereas semantic search is only likely to return the correct result. Full-text search and semantic search can be combined to create powerful and robust search systems.

Semantic search is not just for machine learning engineers. Theactualsystem behind semantic search is relatively easy to implement and thanks to new Postgres extensions like pgml and pgvector, is readily available to SQL developers. Just asit is expected formodern SQL developers to be familiar with and capable of implementing fulltext search,soon SQL developerswill be expected to implement semantic search.

Semantic search is not just for machine learning engineers. The system behind semantic search is relatively easy to implement, and thanks to new Postgres extensions like pgml and pgvector,itis readily available to SQL developers. Just as modern SQL developersare expectedto be familiar with and capable of implementing full-text search,theywillsoonbe expected to implement semantic search as well.