Load from Docusaurus Documentation.
It leverages the SitemapLoader to loop through the generated pages of a
Docusaurus Documentation website and extracts the content by looking for specific
HTML tags. By default, the parser searches for the main content of the Docusaurus
page, which is normally the
Lazy load TiDB data into document objects.
Additional args to extend the underlying SitemapLoader, for example: filter_urls, blocksize, meta_function, is_local, continue_on_failure
