k-d-trees
2 articlesAll articles tagged with "k-d-trees"

-8 min read
The Math Behind Millisecond Search: K-d Trees Explained
K-d trees are what make sub-100ms vector search possible in a browser extension. This post explains how they work, why they matter for semantic history search, and how TraceMind uses Voy's WASM k-d tree to search tens of thousands of embeddings almost instantly.
vector-searchk-d-treesbloom-filterssemantic-searchbrowser-history

-8 min read
Overcoming the Speed Limits of Local AI with Voy and K-d Trees
Searching thousands of 384-dimensional vectors in milliseconds inside a browser requires smarter data structures than linear scan. Here is how Voy, k-d trees, and approximate nearest-neighbor search make it possible.
vector-similarity-searchk-d-treesbloom-filterslocal-first-ainearest-neighbor-search