本项目旨在分享大模型相关技术原理以及实战经验。

notes for software engineers getting up to speed on new AI developments. Serves as datastore for https://latent.space writing, and product brainstorming, but has cleaned up canonical references und…

基于行块分布函数的通用网页正文抽取算法的Python版本实现，添加了英文支持/ Web page content extraction algorithm, support both Chinese and English