AI preprocessing: Remove HTML tags from HTML files and convert them to Markdown files

name
AI preprocessing HTML tag removal
tag
AI preprocessing/Claude/Generative AI
Connector used
REST Connector
API
API version: 2023-06-01
AI preprocessing: Remove HTML tags from HTML files and convert them to Markdown files

This is a HULFT Square application that makes it easy to prepare RAG data for use in generative AI.
This application uses Claude, an LLM, to remove HTML tags from HTML files and output them as Markdown files.

Script Details

Convert HTML files to Markdown files

Delete_HTML_Tag_Claude_convert

Image illustrating the process of converting HTML files to Markdown files.

Checking the limit value for the number of tokens required for HTML file conversion

Delete_HTML_Tag_Claude_validate_limits

An illustrative diagram showing the check for the limit on the number of tokens required for HTML file conversion.

Convert HTML files and output them as Markdown files

Delete_HTML_Tag_Claude_convert_to_markdown

Image illustrating the process of outputting the converted HTML file to a Markdown file.

How to install and use it

»See the list of applications