Add a local directory as a documentation source.

The directory should contain HTML files that will be indexed for search.

Args: path: Absolute filesystem path to the docs directory slug: Unique identifier for this local source

Fetch documentation from a web URL (or re-download existing source).

If url is not provided, re-downloads an existing web source by slug.

By default, only fetches URLs in the same directory or below the initial URL. For example, fetching https://example.com/docs/api/index.html will only fetch files under https://example.com/docs/api/ and not https://example.com/docs/other/.

Only HTML files (.html, .htm, or no extension) are fetched and followed. Non-HTML files (CSS, JS, images, fonts, etc.) are automatically skipped.

Args: slug: Unique identifier for this web source url: Base URL to fetch from (optional for re-download) name: Display name (defaults to slug) max_depth: Recursion depth for crawling (default: 2) pattern: Regex pattern for URLs to fetch (default: .*.html?$) url_prefix: Optional URL prefix to restrict crawling (default: directory of initial URL)

Get detailed information about a specific documentation.

Args: slug: Documentation slug (e.g. 'javascript', 'async')

Download one or more documentation bundles from devdocs.io.

Args: slugs: Single slug string or list of documentation slugs (e.g. 'javascript' or ['javascript', 'python', 'react']) version: Optional version specifier for single slug (ignored for multiple slugs, uses latest)

Get full document content by document ID from search results.

Use this to retrieve the complete content of a document after finding it via search_docs. The doc_id can be found in search results (typically shown in the path or title).

Args: doc_id: Document ID from search results (e.g. "python~3.13/library/functions#print")

List all available documentation sources with optional filtering.

Args: source_type: Filter by 'devdocs', 'local', or None for all include_large: Include docs larger than 50 MB (default: False = exclude large) downloaded_only: only include downloaded docs (default: True = only show downloaded docs) query: Optional fuzzy text filter on doc metadata (slug, name, type, release, alias) Case-insensitive substring match. Does NOT search document content.

Rebuild the embedding index from downloaded documentation.

By default, only indexes newly downloaded documentation that hasn't been indexed yet. Use clean=True to rebuild everything from scratch.

Args: clean: If True, rebuild entire index from scratch. If False (default), only index missing documents. slugs: Optional list of specific doc slugs to re-index (e.g., ['vulkan', 'python']). If provided, only these docs will be processed. Ignores already-indexed status and re-indexes them.

Remove documentation by slug, regardless of source type.

Works for downloaded devdocs.io bundles, local sources, and web sources.

Args: slug: Documentation slug to remove (e.g. 'async')

Search documentation using semantic similarity.

Args: query: Natural language search query (e.g. "how to make HTTP requests") top_k: Number of results to return (default: 10) min_score: Minimum vector-similarity score 0.0-1.0 (default: 0.3). Applies to the semantic/vector search leg only — keyword/BM25 matches (e.g. exact title matches for bare-word queries) can still surface in results even with low semantic similarity. slugs: Optional list of doc slugs to filter by (e.g. ['javascript', 'python']) source_type: Optional source type filter ('devdocs' or 'local')