Show HN: An open-source tool that semantically profiles your data using LLMs

{
  "by": "zh2408",
  "descendants": 2,
  "id": 40248744,
  "kids": [
    40249297
  ],
  "score": 10,
  "text": "The problem we solve is profiling tables: this is the initial step where you need to understand the table and identify any anomalies.<p>During the process, many small decisions require semantic understanding. For example, missing values are normal for &#x27;deathdate&#x27; (still alive) but abnormal for &#x27;name.&#x27; For outliers, 100 for ages is fine, but some are -1, which is impossible! We use LLMs to semantically understand your tables and detect anomalies.<p>You can try it by uploading a CSV, and we will email back the profile: <a href=\"https:&#x2F;&#x2F;cocoon-data-transformation.github.io&#x2F;page&#x2F;\" rel=\"nofollow\">https:&#x2F;&#x2F;cocoon-data-transformation.github.io&#x2F;page&#x2F;</a><p>Let me know your feedback. Thanks!",
  "time": 1714749854,
  "title": "Show HN: An open-source tool that semantically profiles your data using LLMs",
  "type": "story",
  "url": "https://github.com/Cocoon-Data-Transformation/cocoon"
}

{
  "author": "Cocoon-Data-Transformation",
  "date": null,
  "description": "Data management with LLMs. Contribute to Cocoon-Data-Transformation/cocoon development by creating an account on GitHub.",
  "image": "https://opengraph.githubassets.com/c83284a0510a5846874b7ccdc5a4a7e07868a5c5f6501cba49162640e7e9de85/Cocoon-Data-Transformation/cocoon",
  "logo": null,
  "publisher": "GitHub",
  "title": "GitHub - Cocoon-Data-Transformation/cocoon: Data management with LLMs",
  "url": "https://github.com/Cocoon-Data-Transformation/cocoon"
}

{
  "url": "https://github.com/Cocoon-Data-Transformation/cocoon",
  "title": "GitHub - Cocoon-Data-Transformation/cocoon: Data management with LLMs",
  "description": "Skip to content            Navigation Menu                                              Sign in                Appearance settings                  AI CODE CREATIONGitHub CopilotWrite better...",
  "links": [
    "https://github.com/Cocoon-Data-Transformation/cocoon"
  ],
  "image": "https://opengraph.githubassets.com/c83284a0510a5846874b7ccdc5a4a7e07868a5c5f6501cba49162640e7e9de85/Cocoon-Data-Transformation/cocoon",
  "content": "<div>\n    <div>\n      <p><a target=\"_blank\" href=\"https://github.com/Cocoon-Data-Transformation/cocoon#start-of-content\">Skip to content</a>\n      <span>\n    <span></span>\n</span></p>\n  <h2>Navigation Menu</h2>\n  <div>\n    <div>\n      <a target=\"_blank\" href=\"https://github.com/\">\n      </a>\n      <div>\n          <p><a target=\"_blank\" href=\"https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2FCocoon-Data-Transformation%2Fcocoon\">\n            Sign in\n          </a></p><div>\n      Appearance settings\n  </div>\n      </div>\n    </div>\n    <div>\n  <div><ul><li><div><ul><li><div><p><span>AI CODE CREATION</span></p><ul><li><a target=\"_blank\" href=\"https://github.com/features/copilot\"><div><p><span>GitHub Copilot</span><span>Write better code with AI</span></p></div></a></li><li><a target=\"_blank\" href=\"https://github.com/features/spark\"><div><p><span>GitHub Spark</span><span>Build and deploy intelligent apps</span></p></div></a></li><li><a target=\"_blank\" href=\"https://github.com/features/models\"><div><p><span>GitHub Models</span><span>Manage and compare prompts</span></p></div></a></li><li><a target=\"_blank\" href=\"https://github.com/mcp\"><div><p><span>MCP Registry<sup>New</sup></span><span>Discover and integrate external tools</span></p></div></a></li></ul></div></li><li></li><li></li><li></li></ul><p><a target=\"_blank\" href=\"https://github.com/features\"><span>View all features</span></a></p></div></li><li></li><li></li><li></li><li></li><li><a target=\"_blank\" href=\"https://github.com/pricing\"><span>Pricing</span></a></li></ul></div>\n        <div>\n  <div>\n    <div>\n    <p>\n      </p><h2 id=\"feedback-dialog-title\">\n        Provide feedback\n      </h2>\n    <p></p>\n  </div>\n    <div>\n    <p>\n      </p><h2 id=\"custom-scopes-dialog-title\">\n        Saved searches\n      </h2>\n        <h2 id=\"custom-scopes-dialog-description\">Use saved searches to filter your results more quickly</h2>\n    <p></p>\n  </div>\n  </div>\n              <p><a target=\"_blank\" href=\"https://github.com/signup?ref_cta=Sign+up&amp;ref_loc=header+logged+out&amp;ref_page=%2F%3Cuser-name%3E%2F%3Crepo-name%3E&amp;source=header-repo&amp;source_repo=Cocoon-Data-Transformation%2Fcocoon\">\n                Sign up\n              </a></p><div>\n      Appearance settings\n  </div>\n          </div>\n      </div>\n  </div>\n    </div>\n  <div>\n  <div>\n      <div>\n            <ul>\n  <li>\n            <a target=\"_blank\" href=\"https://github.com/login?return_to=%2FCocoon-Data-Transformation%2Fcocoon\">    Notifications\n</a>    You must be signed in to change notification settings\n  </li>\n  <li>\n          <a target=\"_blank\" href=\"https://github.com/login?return_to=%2FCocoon-Data-Transformation%2Fcocoon\">    Fork\n    <span>18</span>\n</a>\n  </li>\n  <li>\n        <p>\n        <a target=\"_blank\" href=\"https://github.com/login?return_to=%2FCocoon-Data-Transformation%2Fcocoon\">    <span>\n          Star\n</span>          <span>173</span>\n</a></p>\n  </li>\n</ul>\n        </div>\n  </div>\n  </div>\n  <div>\n    <p>\n    You can’t perform that action at this time.\n  </p></div>\n  <details>\n    <summary></summary>\n  </details>\n  <p>\n  </p>\n  <p>\n  </p>\n    </div>",
  "author": "",
  "favicon": "https://github.githubassets.com/favicons/favicon.svg",
  "source": "github.com",
  "published": "",
  "ttr": 15,
  "type": "object"
}