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。

Ask HN: Do LLMs replace the need for Elasticsearch?

4 点作者 shaburn将近 2 年前
If not, than what does or will...and why?

2 条评论

Irishsteve将近 2 年前
It depends on the use-case :-) but I’d say no. The use cases I’ve seen are either people doing prompt engineering to create queries in which case you’re using es the standard way and have a query understanding layer<p>Or people do some fine tuning of a model or their own and store it someplace (maybe es). In which case you could still be using es to cover filters and range parts of the queries and then rerank that result set.<p>Not covered the ops and scalability benefits you get with elastic &#x2F; solr &#x2F; open search which is also very important if you’ve non trivial usage
PaulHoule将近 2 年前
<a href="https:&#x2F;&#x2F;www.elastic.co&#x2F;what-is&#x2F;vector-search" rel="nofollow noreferrer">https:&#x2F;&#x2F;www.elastic.co&#x2F;what-is&#x2F;vector-search</a>