Skip to content
BENIBIX Learn

Dense Vector

Also known as Dense Embedding, Dense Retrieval

A list of numbers with a value in each slot. It holds meaning, not exact words.

Think of it like

It is like a full egg box. Every cup has an egg in it.

Example

A search for "cheap flights" finds a page titled "low-cost airfare". The words differ, but their dense vectors sit close together.

Why it matters

Dense vectors find matches by meaning. That is what makes semantic search work.

Definition

A dense vector is a list of numbers where almost every number has a value. Embedding models make dense vectors. The numbers are not words. Each one scores a hidden feature of the meaning. So two texts with the same meaning get close vectors, even with no words in common. Searching with them is called dense retrieval.
The top row is dense: a number in every box.

Common mistake

Expecting them to match exact codes or names. A part number like X-200 is better found by keyword search.

Key takeaways

  1. 1
    Every slot filled. Hundreds of numbers, all used.
  2. 2
    Meaning, not words. Synonyms land close together.
  3. 3
    Weak on exact terms. Rare names and codes slip.

Compare