Skip to content

RAG & Search

Dense retrieval

Retrieval that uses learned vector representations to find semantically similar content.

Example

A meaning-based search represents both questions and documents with dense vectors.

Why people use it

Knowing how “Dense retrieval” works helps teams design search-backed answers that are accurate and traceable.

What you'll hear

“How are we handling Dense retrieval so the assistant gets the right information?”

Related terms