本文介绍如何构建一套文本聚类流水线，将大语言模型嵌入与基于密度的聚类算法 HDBSCAN 相结合，在无标注文本数据中自动发现主题。 当前的生成式 AI热潮，表面上似乎主要集中在聊天界面与提示词工程，但大语言模型（LLM）的实际应用范围远不止于此。

Backtests often look far better on paper than they do in live markets. The usual reason is not that the idea was completely wrong. It is that the strategy was tuned too closely to the past, then ...

Circular RNAs (circRNAs) are known to act as important regulators of the microRNA (miRNA) activity. Yet, computational resources to identify miRNA:circRNA interactions are mostly limited to already ...

我刚刚在我的一个较大的Rust项目中跨越了20K LOC，我想暂停一下并分享一些我所使用的伟大的Rust库。 我刚刚在我的一个较大的Rust项目中跨越了20K LOC，我想暂停一下并分享一些我所使用的伟大的Rust库。 我还计划在未来的文章中讨论一些话题，比如在Rust与Go之间 ...

Iterchain is a library intended to make manipulating iterators in Python easier and more ergonomic. The design is heavily inspired by the Rust iterator design, and a lot of the functionality comes ...

Python 诞生于 1989 年的圣诞期间，由 Guido van Rossum 开发而成，目前 Guido 仍然是 Python 的主要开发者，主导着 Python 的发展方向 ...