← @bgSponge

do-me/SemanticFinder: SemanticFinder - frontend-only live semantic search with transformers.js

Summary

SemanticFinder is a browser-only semantic search and chat-with-your-documents app built on transformers.js, with Wasm and WebGPU backends.

  1. Embeddings never leave the browser.

    transformers.js runs feature-extraction models locally; Wasm covers the model set, WebGPU is the fast path.

    Calculates the embeddings and cosine similarity client-side without server-side inferencing

    Data privacy-friendly - your input text data is not sent to a server, it stays in your browser!

  2. Segment size trades recall for speed.

    Longer chunks finish faster; only changing segment length forces a full re-embed because embeddings are cached per segment.

  3. Pre-indexed catalogues beat cold starts.

    Shared JSON.gz indices for large books let subsequent queries finish in about two seconds after the model loads.

    Following queries take only ~2 seconds!

  4. Hybrid search and a threshold gate results.

    Semantic plus full-text ranking, with a similarity cutoff deciding how many highlights appear.

  5. For libraries, use a real vector DB.

    Moby Dick-scale one-shot indexing works in-browser; sustained multi-book libraries need an external vector store.

Read the original ↗Save to your Sponge

Summarized with Sponge. Quotes are the author’s own words.

More from @bg

All readings →