Semicolony ELI5 · comic

Vector databases.

A database built to answer "what is most similar to this?" by finding the nearest points in space, fast.

  1. Millions of dots to store.
    millions of points
    1

    You already turned everything into points on a map. Now there are millions of them.

  2. What’s nearest to here?
    nearest to here?
    2

    The question is always the same: which stored points sit closest to this new one?

  3. Compare all of them? No.
    check all?!
    3

    Checking every dot one by one is hopeless once the map holds millions.

  4. Skip straight to the block.
    jump to the block
    4

    So it builds an index that jumps near the right neighbourhood instead of scanning all.

  5. Close enough, way faster.
    accuracy speed close enough, way faster
    5

    It trades a sliver of accuracy for a huge speed-up — "good enough, almost instantly."

  6. Here’s your top neighbours.
    doc · 0.98 doc · 0.91 LLM with context the engine behind RAG
    6

    Back come the nearest matches with their original items — the engine behind RAG.

A database built to answer "what is nearest to this point?" across millions, fast.
Semicolony semicolony.dev/eli5/vector-database/comic
← All ELI5 explainers