skills.rest
ruvnet
ruvnetCOMMUNITY
Explore all skills by this author →
Website𝕏@ruvGitHub

vector-hyperbolic

Embeds hierarchical data and projects vectors into the Poincare ball using ruvector.

70.1k|8.4k|Updated Jun 2, 2025
Search Tags:#dependency analysis#vector embeddings#RuVector#hierarchical data#poincare ball#hyperbolic embeddings#geodesic distance
One-click install
npx skills add https://github.com/ruvnet/claude-flow --skill vector-hyperbolic
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: vector-hyperbolic
Source: https://github.com/ruvnet/claude-flow/tree/main/plugins/ruflo-ruvector/skills/vector-hyperbolic
Command: npx skills add https://github.com/ruvnet/claude-flow --skill vector-hyperbolic

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires ruvector.

What problem does it solve?

Hierarchical data like dependency trees, taxonomies, and org charts lose structural relationships when embedded in standard Euclidean space. This Skill generates base embeddings with ruvector and projects them into the Poincare ball, where hyperbolic geometry preserves hierarchical distances with far fewer dimensions.

Core Features & Use Cases

  • Hyperbolic Embedding: Generate a 384-dim ONNX embedding via npx [email protected] embed text, then normalize and project it into the Poincare ball in your own code.
  • Geodesic Distance Computation: Measure hierarchical relatedness with the Poincare distance formula, where distance grows logarithmically with tree depth.
  • Persistent Storage: Store projected coordinates and neighbors in agent memory via the ruflo memory_store MCP tool under a dedicated namespace.
  • Use Case: Embed module import graphs from a codebase to find tightly coupled subtrees, or embed concepts to reveal taxonomic relationships for knowledge organization.

Quick Start

Ask the agent to embed a hierarchical concept like your project's module tree into the Poincare ball using ruvector and store the projected coordinates in memory.

Frequently Asked Questions about vector-hyperbolic

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I embed hierarchical data in hyperbolic space with ruvector?▼

Generate a base embedding with `npx [email protected] embed text "concept"`, then project the 384-dim vector into the Poincare ball in your own code by normalizing it inside the unit ball. Version 0.2.25 has no built-in --model poincare flag.

Does ruvector 0.2.25 support a Poincare ball model flag?▼

No, [email protected] does not expose a --model poincare flag on the embed text command. Hyperbolic projection must be treated as a post-processing step over a standard ONNX embedding, or explored via the experimental embed neural subcommand.

When should I use hyperbolic embeddings instead of Euclidean embeddings?▼

Use hyperbolic embeddings when your data has inherent hierarchy, such as dependency trees, taxonomies, ontologies, or org charts. Hyperbolic space captures hierarchical distances with far fewer dimensions than Euclidean embeddings.

How do I compute distance between Poincare ball embeddings?▼

Use the geodesic distance formula d(u, v) = arcosh(1 + 2 * ||u-v||^2 / ((1-||u||^2)(1-||v||^2))). Distance grows logarithmically with tree depth, so closely related nodes stay near each other.

What does the vector norm mean in the Poincare ball?▼

A norm close to 0 indicates a generic, root-level concept, while a norm close to 1 indicates a specific, leaf-level concept. This lets you rank concepts by specificity directly from their projected coordinates.

Related Skills

Explore More Software Engineering Skills→
manuelbrandner85manuelbrandner85

diagramming-code

Generate Mermaid diagrams from Trailmark code graphs.

Community
Intermediate
mrsorbatemrsorbate

AgentDB Vector Search

Implement semantic vector search and retrieval-augmented generation with AgentDB.

Community
Advanced
ShadylukinShadylukin
74

neumann-vector

Build HNSW vector indexes and run similarity queries with COSINE, EUCLIDEAN, and DOT_PRODUCT metrics.

Community
Intermediate
robotlearning123robotlearning123

torch-geometric

Develop and train graph neural networks with PyTorch.

Community
Advanced