Search

FIND A DOCUMENTATION PAGE — start here. Searches the project's documentation by MEANING (embeddings over a pre-built vector index), which finds the right page far more often than literal keyword matching: 'how do I reset a password' lands on a page titled 'Recovering account access', which a word search misses entirely. Use it for any natural-language question — «где написано про…», 'where do we explain X', 'which page covers Y' — and before writing anything, so you edit the page that exists instead of adding a second one about the same thing. Cheap and repeatable: the index is built once, ahead of time, so a call here is one lookup against vectors that already exist. Always answers: a project with no vector index yet is searched by full text instead, and mode ('semantic' | 'lexical') says which engine replied — no plan is required either way. Returns hits {n, title, headingPath, url, path}, best first — each with a similarity score (semantic) or a snippet (lexical); call read_doc on path for the whole page. Prefer search_docs only when you need a LITERAL string — an error message, a CLI flag, a regex, a file path. This answers WHAT, not what to do about it. If you have not already got the method from docsbook_expert, get it first: it names which readings answer this question, what to compare them against, and what would make the conclusion wrong. One call, changes nothing.