Skip to main content
Version: 2.6

@operaide/documents

This library provides aktors to integrate Vector Stores, PDF Parsing, URL processing, and document management into your Reaktor.

Available Aktors​

Here's a short reference of the available aktors from the @operaide/documents library:

Document Conversion Aktors​

  • aktorConvertPDFToMarkdown: Converts a PDF document to markdown format.
  • aktorConvertMultiplePDFsToMarkdown: Converts multiple PDF documents to markdown format.
  • aktorConvertMultiplePdfToMarkdown: Converts multiple PDFs from URLs to markdown.

Document Content Aktors​

  • aktorGetDocumentData: Gets document data from document IDs.
  • aktorSplitMarkdownToPages: Splits markdown content into pages.
  • aktorGetFirstPages: Gets the first few pages from documents.
  • aktorTocsFormat: Formats table of contents data.
  • aktorGetDataFromRelevantPages: Gets data from relevant pages.
  • aktorGetContentFromPages: Gets content from specified pages.
  • aktorGetJSONFromDocuments: Converts document data to JSON.

Web Search and URL Processing Aktors​

  • aktorCreateSearchURLs: Creates search URLs from search terms and a site template.
  • aktorMarkdownFromURLs: Converts URLs to markdown content.
  • aktorGetRelevantPagesURLs: Gets relevant page URLs from a list of markdowns.
  • aktorGetMarkdownFromRelevantPages: Gets markdown content from relevant page URLs.

Markdown Processing Aktors​

  • aktorGetChaptersFromMarkdown: Extracts chapters from markdown content.
  • aktorFormatMarkdownChapters: Formats markdown chapters.
  • aktorMarkdownChapterNumbers: Adds chapter numbers to markdown content.
  • aktorMarkdownChaptersTransform: Transforms markdown chapters based on selected chapters.

For more detailed information on each aktor, explore the Library using IntelliSense in your IDE!

To view the latest version, please take a look at the Registry