Show HN: Hacker Search – A semantic search engine for Hacker News

{
  "by": "jnnnthnn",
  "descendants": 73,
  "id": 40238509,
  "kids": [
    40238986,
    40239439,
    40241070,
    40239867,
    40242516,
    40241048,
    40239040,
    40239328,
    40239298,
    40270799,
    40239416,
    40241470,
    40262545,
    40240279,
    40239894,
    40238849,
    40241477,
    40242397,
    40244152,
    40238894,
    40241151,
    40242319,
    40241638,
    40244926,
    40239752,
    40252696
  ],
  "score": 233,
  "text": "Hi HN!<p>I&#x27;m Jonathan and I built Hacker Search (<a href=\"https:&#x2F;&#x2F;hackersearch.net\" rel=\"nofollow\">https:&#x2F;&#x2F;hackersearch.net</a>), a semantic search engine for Hacker News. Type a keyword or a description of what you&#x27;re interested in, and you&#x27;ll get top links from HN surfaced to you along with brief summaries.<p>Unlike HN&#x27;s otherwise very valuable search feature, Hacker Search doesn&#x27;t require you to get your keywords exactly right. That&#x27;s achieved by leveraging OpenAI&#x27;s latest embedding models alongside more traditional indexes extracted from the scraped and cleaned up contents of the links.<p>I think there are many more interesting things one could build atop the HN dataset in the age of LLMs (e.g. more explicitly searching for technical opinions, recommending stories to you based on your interests, and making the core search feature more useful). If any of those sound interesting to you, head over to <a href=\"https:&#x2F;&#x2F;hackersearch.net&#x2F;signup\" rel=\"nofollow\">https:&#x2F;&#x2F;hackersearch.net&#x2F;signup</a> to get notified when I launch them!<p>Note: at least one person has built something similar before (<a href=\"https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=36391655\">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=36391655</a>). Funnily enough, I only found out about this through my own implementation, and I based on my testing, I think Hacker Search generally performs better when doing keyword&#x2F;sentence searches (vs. whole document similarity lookup), thanks to the way the data is indexed.",
  "time": 1714669260,
  "title": "Show HN: Hacker Search – A semantic search engine for Hacker News",
  "type": "story",
  "url": "https://hackersearch.net"
}

{
  "author": null,
  "date": null,
  "description": null,
  "image": null,
  "logo": null,
  "publisher": "Cloudflare",
  "title": "Attention Required! | Cloudflare",
  "url": "https://hackersearch.net"
}

{
  "url": "https://hackersearch.net/",
  "title": "Attention Required! | Cloudflare",
  "description": "Why have I been blocked?            This website is using a security service to protect itself from online attacks. The action you just performed triggered the security solution. There are several actions...",
  "links": [
    "https://hackersearch.net/"
  ],
  "image": "",
  "content": "<div>\n            <h2>Why have I been blocked?</h2>\n            <p>This website is using a security service to protect itself from online attacks. The action you just performed triggered the security solution. There are several actions that could trigger this block including submitting a certain word or phrase, a SQL command or malformed data.</p>\n          </div><div>\n            <h2>What can I do to resolve this?</h2>\n            <p>You can email the site owner to let them know you were blocked. Please include what you were doing when this page came up and the Cloudflare Ray ID found at the bottom of this page.</p>\n          </div>",
  "author": "",
  "favicon": "",
  "source": "hackersearch.net",
  "published": "",
  "ttr": 19,
  "type": ""
}