TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Show HN: "banks" Using Jinja as the basis of LLM prompt templating

3 点作者 tuanacelik将近 2 年前
banks is a side project by my colleague Massi. We work on the open source NLP framework Haystack together (<a href="https:&#x2F;&#x2F;github.com&#x2F;deepset-ai&#x2F;haystack">https:&#x2F;&#x2F;github.com&#x2F;deepset-ai&#x2F;haystack</a>) and prompt templating is obviously a &#x27;hot&#x27; topic and it&#x27;s something to design these types of projects around. Massi had this concept in mind to use Jinja (or any other templating language for that matter) as the basis, and clearly decided to take it for a spin. I personally am in love with this style of prompt templating and think it makes the whole process insanely flexible and easy to read. Wanted to share it here to see what others think. Hope you enjoy.

暂无评论

暂无评论