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: Exa (YC S21) – embeddings search agent with >20x recall than Google

28 点作者 willbryk3 个月前
Hey HN! I&#x27;m Will, founder of Exa (YC21 - <a href="https:&#x2F;&#x2F;exa.ai">https:&#x2F;&#x2F;exa.ai</a>). Today we&#x27;re opening up Websets, a search engine that finds massive lists of correct results given complex queries.<p>For example, you can search for:<p>- “software engineers in the Bay Area, with experience in startups and big tech, who know Rust and have published technical content”: <a href="https:&#x2F;&#x2F;websets.exa.ai&#x2F;cm7ax5bl8003276q689v0dde5">https:&#x2F;&#x2F;websets.exa.ai&#x2F;cm7ax5bl8003276q689v0dde5</a><p>- “US based healthcare companies, with over 100 employees and a technical founder&quot;: <a href="https:&#x2F;&#x2F;websets.exa.ai&#x2F;cm6lc0dlk004ilecmzej76qx2">https:&#x2F;&#x2F;websets.exa.ai&#x2F;cm6lc0dlk004ilecmzej76qx2</a><p>- &quot;research paper about ways to avoid the O(n^2) attention problem in transformers, where one of the first author&#x27;s first name starts with &quot;A&quot;,&quot;B&quot;, &quot;S&quot;, or&quot;T&quot;, and it was written between 2018 and 2022”: <a href="https:&#x2F;&#x2F;websets.exa.ai&#x2F;cm7dpml8c001ylnymum4sp11h">https:&#x2F;&#x2F;websets.exa.ai&#x2F;cm7dpml8c001ylnymum4sp11h</a><p>We built Websets because the web is humanity’s grand collection of all knowledge, and yet it’s totally unorganized. So much valuable content is too hard to find.<p>Traditional search engines, like Google, were built to handle simple keyword queries over the web, not arbitrarily complex SQL. While agentic tools like Deep Research help a bit, they rely on traditional search under the hood and so are similarly bottlenecked.<p>Websets works well because under the hood it uses our in-house embedding-based search engine, trained specifically to handle complex natural language queries. Crucially, Websets uses LLMs to agentically verify each result to ensure correctness. Websets is therefore a test-time compute search engine – it might take minutes or even hours to run. We believe this is a worthwhile sacrifice for high value searches.<p>It’s hard to eval these things, but we did our best and measured that Websets found 20x more results than Google on a set of complex queries and 10x more than Deep Research. These numbers could be arbitrarily higher with more compute per query. Blog post here: <a href="https:&#x2F;&#x2F;exa.ai&#x2F;blog&#x2F;websets-evals">https:&#x2F;&#x2F;exa.ai&#x2F;blog&#x2F;websets-evals</a><p>While Websets isn’t perfect search yet, it’s a significant first step, and we’re excited to share the first version of the product with you all. We have a free limited tier, and we set up a special HN code for Pro plans. Use PERFECTSEARCH for a two-week free trial of Pro.<p>Can try it here: websets.exa.ai<p>Initial launch video here: <a href="https:&#x2F;&#x2F;x.com&#x2F;ExaAILabs&#x2F;status&#x2F;1864013080944062567" rel="nofollow">https:&#x2F;&#x2F;x.com&#x2F;ExaAILabs&#x2F;status&#x2F;1864013080944062567</a><p>Would love to hear thoughts, feedback, and suggestions! I know HN thinks about search sometimes :)

3 条评论

paulista_tcb3 个月前
This is cool. Is it more meant for perfect recall or perfect precision of results?
评论 #43175930 未加载
rushingcreek3 个月前
Very cool, congrats on the launch!
tianlins3 个月前
amazing. f1 score = 1