{
  "id": 7203292,
  "title": "No Server, No Backend, Just Blazor WebAssembly Doing Semantic Search",
  "url": "https://urgent.news/2026/09/13/no-server-no-backend-just-blazor-webassembly-doing-semantic-search",
  "topic": "tech",
  "section": "Tech",
  "published": "2026-09-13T23:54:32.000Z",
  "source": {
    "name": "Dev.to",
    "slug": "dev-to",
    "url": "https://dev.to/j_sakamoto/no-server-no-backend-just-blazor-webassembly-doing-semantic-search-bl4"
  },
  "original_language": "en",
  "account": "Semantic search can be implemented on Blazor WebAssembly standalone apps hosted on GitHub Pages, requiring no server-side code or backend. This is achieved by transforming text into vectors, which represent the meaning of the data. These vectors are computed ahead of time and stored in an index file that ships with the site. At search time, the user's input is also converted into a vector using the same model, and the distance between the input vector and the stored vectors is calculated to find semantically similar data. The MiniLM L6-v2 model is used for this purpose, which is small enough to be downloaded by the browser. The process involves converting text into vectors through mean pooling and normalization techniques.",
  "summary": "🚀 Semantic search on GitHub Pages with zero backend I recently added semantic search to the documentation site of my project, Blazing Story. The interesting part is that the site is a Blazor WebAssembly standalone app hosted on GitHub Pages. There is no server-side code, no API, and no database. Yet users can search documentation by meaning rather than exact keywords. Here's how I built it. 🔰…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}