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。

Embeddings based RSS recommendation system

2 点作者 m0wer4 个月前

1 comment

m0wer4 个月前
About a year ago I created rssfilter to help me out catching up with my RSS feeds.<p>I was getting too many new posts per day from HN and other sites and started not enjoying it as much. I wanted to have 50% of the posts but missing out as little as possible about the topics I&#x27;m most interested in.<p>After a year using it, I&#x27;m pretty satisfied about the results and other users are too.<p>How rssfilter works is by being a proxy to your existing RSS subscriptions. It replaces the article links to a redirect that stores what articles you open. This information is what&#x27;s used for the recommendations.<p>The embeddings of your read articles title and description are clustered. And from then on, you will only get 50% of the articles from all feeds, mostly what&#x27;s closest to your areas of interest but also some percentage of unfiltered posts to allow for discovery.<p>It can be self hosted and there is also a live version that I host. No registry, the user ID is just a random UUID.<p>You can also use the API (FastAPI btw) directly: <a href="https:&#x2F;&#x2F;rssfilter.sgn.space&#x2F;api&#x2F;docs" rel="nofollow">https:&#x2F;&#x2F;rssfilter.sgn.space&#x2F;api&#x2F;docs</a><p>Let me know if you like it!