<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Preprocessing on Yonk-Labs</title><link>https://yonk.dev/tags/preprocessing/</link><description>Recent content in Preprocessing on Yonk-Labs</description><generator>Hugo -- gohugo.io</generator><language>en</language><copyright>© 2026 Yonk-Labs</copyright><lastBuildDate>Tue, 28 Apr 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://yonk.dev/tags/preprocessing/index.xml" rel="self" type="application/rss+xml"/><item><title>lede</title><link>https://yonk.dev/projects/lede/</link><pubDate>Tue, 28 Apr 2026 00:00:00 +0000</pubDate><guid>https://yonk.dev/projects/lede/</guid><description>Sub-millisecond extractive summarization with byte-identical Python and Rust implementations. The preprocessor that sits in front of the LLM call.</description></item><item><title>Meet lede: The Thing You Reach for Before the LLM Call</title><link>https://yonk.dev/blog/meet-lede/</link><pubDate>Tue, 28 Apr 2026 00:00:00 +0000</pubDate><guid>https://yonk.dev/blog/meet-lede/</guid><description>Sub-millisecond extractive summarization with byte-identical Python and Rust implementations. The preprocessor that sits in front of the LLM call and cuts tokens 40-94 percent.</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://yonk.dev/blog/meet-lede/feature.jpg"/></item></channel></rss>