Convert HTML to Markdown

Returns Markdown text from a HTML document (page).

Example
This Flow downloads the HTML of a specified page, converts the HTML to Markdown, splits the cleaned content into smaller chunks, generates embeddings for each chunk, converts the embeddings into a SQL Server–compatible format, and stores the text, vector, and document reference in a SQL Server table. This table can then be used for vector search or to feed chat models with the extracted information.

Properties

Name	Required	Description
Title	No	The title of the action.
File data	Yes	Specifies the source of the HTML text, which can either be a string, a Stream or a Byte Array.
Conversion engine	Yes	Select the engine to use in conversion, see below for details.
Result variable name	Yes	The name of the variable in which the result will be stored.
Description	No	Additional notes or comments about the action or configuration.

Conversion engines

• Docling provides the most complete extraction and is best for complex HTML pages, including nested structures, rich formatting, tables, and image-related content. It is the slowest option and can require significant resources for large pages. This is currently the only engine that supports image conversion.
• Kreuzberg is a balanced option for larger or high-volume HTML conversions. It is typically faster and more resource-efficient than Docling, but may produce less accurate results on complex or deeply nested layouts.
• MarkItDown is optimized for text-focused HTML content. It is a good choice when speed and clean text output are the top priority, and it uses a custom fine-tuned model.

Returns

This action returns a string/text in Markdown format.

HTTP: Videos / Getting started

Generate a PDF file with tabular data

This video shows how to generate a PDF file with tabular data using the Adobe PDF Services API, and download the generated file from an InVision Workbook.
It uses the HTTP trigger and Return File HTTP Response actions to handle the request and return the file.