Guide

What is semantic search?

You captured a note months ago and now you only remember what it was about — not its title, not the exact words. Semantic search is built for exactly that gap. Here is how it works, without the jargon.

Search by meaning, not words

Keyword search matches the letters you type against the letters in a note. Semantic search matches the idea. Describe "the note about staying focused" and it can surface a thought you spoke about deep work that never used your exact phrase — because it understands what you meant, not just what you typed.

How it works, briefly

Each note's text — whether you spoke it and it was transcribed on-device, or you jotted it down — is turned into a list of numbers called an embedding that captures its meaning. Notes that mean similar things end up with similar numbers. When you search, your query is turned into numbers too, and the closest matches come back. No exact wording required.

Why it changes note-taking

A handful of notes is easy to scan. A library of hundreds is not — unless you can ask for things the way you actually remember them. In Notabe, every note is embedded so semantic search finds it by meaning, which is what keeps a growing library from becoming a place where good thoughts quietly get lost.

Frequently asked

What is semantic search in simple terms?

Search that understands meaning. Instead of matching the exact words you type against the exact words in a note, it matches the idea — so "that thought about focus and deep work" can find a note even if you never used those words when you spoke or wrote it.

Keyword search looks for literal word matches. Semantic search compares meaning using numerical representations of text called embeddings, so related ideas score as close even when the wording differs — useful because you rarely recall a note verbatim.

Why does it matter for notes?

Because you rarely remember the title of a note you captured months ago — you remember what it was about. Semantic search lets you describe it in your own words and still find it, which is what makes a growing notes library usable instead of a place things disappear into.