--- id: 01M4WNEPZJ5QHKYPC5TTCPT2GW type: page title: Search description: Full text and embeddings over every document, for people and agents. order: 16 updated: 2026-09-16 --- ## Two indexes, one answer Every document is indexed twice: its title and body for full-text search, and pieces of about 1,200 characters as embeddings for semantic search. A query runs both and merges the hits; the result says whether embeddings took part, and the palette marks such hits with a **semantic** badge. ## Where to search ::::tabs :::tab[Palette] ⌘K opens the command palette. It searches document titles as you type and asks the server for full-text and semantic hits, alongside recent documents and quick actions. ::: :::tab[CLI] ```sh notdocs search "how do we bill yearly" --limit 5 ``` ::: :::tab[Agents] The `search` tool takes `q` and `limit` and returns hits with the document id, path, title and a snippet, plus `semantic: true` when embeddings were used. ::: :::tab[Published sites] A published site has a search box in its header, over its listed pages alone, and `/api/public/search?org=&project=&q=` answers the same hits as JSON for an agent. A visitor's search is full-text only: a query from someone with no account is never embedded. ::: :::: ## Keeping it fresh Hosted, every push re-indexes the changed files through the GitHub webhook. Locally, the daemon watches the folder. `notdocs reindex`, or **Rebuild index** in settings, stamps missing ids and rebuilds search and embeddings for the whole branch, with progress rows while it runs. :::note[What leaves the service] Embeddings are computed by a model through Vercel AI Gateway, which means document text is sent to that provider. The [AI disclosure](https://notdocs.dev/legal/ai) says exactly what, and how to have embeddings disabled for a project. :::