An interactive tour
Some data is shaped like a tree. Flat space is a poor home for it. Curved space isn't.
Start walking ↓Everything here is draggable. Try the tree.
01 · Three kinds of space
Put the three corners side by side. In flat space they fill a straight line exactly. Elsewhere they don't. Drag the corners.
02 · Trees don't fit flat
Every level has more nodes than the one before it. Flat space piles them up at the rim. Hyperbolic space keeps making room. Add levels. Hover a node. Drag the right disk.
03 · Position means something
Embed real categories and the hierarchy shows up as position: general ideas near the middle, specific ones toward the rim. Hover a node.
04 · Neighbors
Pick a node. Each space marks its ten closest points. Hyperbolic space picks family: parents, siblings, cousins. The flat picture picks whoever is drawn nearby. Click a node.
05 · In practice
Near the rim, plain Euclidean search picks poor neighbors. So fetch candidates fast, then re-rank with the true hyperbolic distance.
# the true distance d(u, v) = acosh( 1 + 2·‖u − v‖² / ((1 − ‖u‖²)(1 − ‖v‖²)) ) # no acosh in Qdrant's Formula Query, so rewrite it: acosh(x) = ln( x + √(x² − 1) )