v1.1.1

What's Changed

• Add Asynchronous Processing | v0.1.3 by @Daethyra in #5
• 0.1.3 by @Daethyra in #7
• Tweaked readme by @Daethyra in #8
• ci(workflows): Add pypi-publish.yml, remove python-publish.yml by @Daethyra in #12
• Stable 1.0.0 by @Daethyra in #13
• Publish by @Daethyra in #15

Full Changelog: 0.1.31...v1.1.1

Stable PreRelease v0.1.2 | Automate the curation of context for LLMs

Description

Automate the conversion of HTML content from JSON files into a Markdown document.

This release successfully applies programmatic and a semantic similarity threshold to remove irrelevant context from scraped HTML content stored inside of a JSON file. This package was created specifically to extend the functionality of GPT-Crawler's ability to gather quality context for retrieval augmented generation.

Passing in quality data to a large language model is imperative to generate accurate, helpful information, perspective, or code.

---

Full Changelog: https://github.com/Daethyra/conv_html_to_markdown/commits/v0.1.2