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: Quepid now works with vector search

2 点作者 eskibars超过 1 年前
Hi HN!<p>I lead product for Vectara (<a href="https:&#x2F;&#x2F;vectara.com" rel="nofollow noreferrer">https:&#x2F;&#x2F;vectara.com</a>) and we recently worked with OpenSource connections to both evaluate our new home-grown embedding model (Boomerang) as well as to help users start more quantitatively evaluating these systems on their own data&#x2F;with their own queries.<p>OSC maintains a fantastic open source tool, Quepid, and we worked with them to integrate Vectara (and to use it to quantitatively evaluate Boomerang). We&#x27;re hoping this allows more vector&#x2F;hybrid players to be more transparent about the quality of their systems and any models they use instead of everyone relying on and gaming a benchmark like BIER.<p>More details on OSC&#x27;s eval can be found at <a href="https:&#x2F;&#x2F;opensourceconnections.com&#x2F;blog&#x2F;2023&#x2F;10&#x2F;11&#x2F;learning-to-measure-ai-powered-search-with-vectara&#x2F;" rel="nofollow noreferrer">https:&#x2F;&#x2F;opensourceconnections.com&#x2F;blog&#x2F;2023&#x2F;10&#x2F;11&#x2F;learning-t...</a>

暂无评论

暂无评论