Vector Hyperbolic

Embed hierarchical data in the Poincare ball model using ruvector.

When to use

Use this skill when your data has inherent hierarchy — dependency trees, module structures, taxonomies, org charts, ontologies. Hyperbolic space captures hierarchical distances with far fewer dimensions than Euclidean embeddings.

Steps

1. Ensure ruvector@0.3.3 is available:

   npm ls ruvector 2>/dev/null | grep '0.3.3' || npm install ruvector@0.3.3
   

2. Know what a text embedding can and cannot give you. ONNX sentence embeddings (all-MiniLM-L6-v2) are unit-norm. Rescaling or exp-mapping a unit vector puts every point at the same radius (the MCP embeddings_hyperbolic convert gives tanh(0.5) = 0.4621 for all of them), so the radius carries no depth and parent/child distances come out nearly the same as cross-branch distances. Projecting a text embedding does not create hierarchy.
3. Put the hierarchy in yourself. Choose each node's radius from its depth in the tree (root near 0, leaves near 1, for example r = tanh(depth * k)), and take its direction from the text embedding, or use embeddings trained on the tree's edges. Measure on your own tree: parent-child distance should be clearly smaller than cross-branch distance.

   npx -y ruvector@0.3.3 embed text "hierarchical concept" -o concept.vec.json   # direction only
   

4. Geodesic distance for points strictly inside the unit ball: d(u, v) = arcosh(1 + 2 * ||u-v||^2 / ((1-||u||^2)(1-||v||^2))). The MCP embeddings_hyperbolic distance computes it (curvature -1) and returns success: false for a point on or outside the ball rather than a null distance.
5. Store results: mcp__plugin_ruflo-core_ruflo__memory_store({ key: "hyperbolic-CONCEPT", value: "COORDINATES_AND_NEIGHBORS", namespace: "hyperbolic-embeddings" })

Caveats

• ruvector@0.3.3 has no --model poincare flag; attention hyperbolic is the Poincare-ball attention op, not a text-embedding projector.
• "Norm encodes depth" only holds when you set the radius from depth yourself (step 3). It does not come from the embedding.
• If you need a hyperbolic search index, store the placed coordinates in AgentDB and compute geodesic distance in your own retrieval code.

Poincare ball properties (for points you placed by depth)

Property	Meaning
Norm close to 0	Root-level concept (only if you assigned radius by depth)
Norm close to 1	Leaf-level concept (same condition)
Small geodesic distance	Close in the hierarchy you encoded
Large geodesic distance	Distant subtrees in the hierarchy you encoded

Use cases

• Dependency analysis: embed module imports to find tightly coupled subtrees
• Code architecture: map class hierarchies to discover structural patterns
• Knowledge organization: embed concepts to reveal taxonomic relationships
• Codebase navigation: find most specific/general modules relative to a query