vector-hyperbolic

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Vector Hyperbolic

Embed hierarchical data in the Poincare ball model using

ruvector

使用

ruvector

将层级数据嵌入Poincare球模型。

When to use

何时使用

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.

当你的数据具有固有层级结构时使用此技能——比如依赖树、模块结构、分类体系、组织结构图、本体论。双曲空间能够用远少于欧几里得嵌入的维度捕捉层级距离。

Steps

步骤

Ensure ruvector is available:

bash

npm ls ruvector 2>/dev/null || npm install ruvector

Embed in Poincare ball:
bash
```
npx ruvector embed --model poincare "hierarchical concept"
```
Coordinates near origin = generic/root; near boundary = specific/leaf.

Search in hyperbolic space:

bash

npx ruvector search --model poincare "query" --limit 10

Geodesic distance:
```
d(u, v) = arcosh(1 + 2 * ||u-v||^2 / ((1-||u||^2)(1-||v||^2)))
```
Distance grows logarithmically with tree depth, preserving hierarchy.

Store results:

mcp__claude-flow__memory_store({ key: "hyperbolic-CONCEPT", value: "COORDINATES_AND_NEIGHBORS", namespace: "hyperbolic-embeddings" })

确保ruvector可用:

bash

npm ls ruvector 2>/dev/null || npm install ruvector

嵌入到Poincare球中:
bash
```
npx ruvector embed --model poincare "hierarchical concept"
```
靠近原点的坐标 = 通用/根节点概念；靠近边界的坐标 = 特定/叶子节点概念。

在双曲空间中搜索:

bash

npx ruvector search --model poincare "query" --limit 10

测地距离:
```
d(u, v) = arcosh(1 + 2 * ||u-v||^2 / ((1-||u||^2)(1-||v||^2)))
```
距离随树深度呈对数增长，保留层级结构。

存储结果:

mcp__claude-flow__memory_store({ key: "hyperbolic-CONCEPT", value: "COORDINATES_AND_NEIGHBORS", namespace: "hyperbolic-embeddings" })

Poincare ball properties

Poincare球属性

Property	Meaning
Norm close to 0	Generic, root-level concept
Norm close to 1	Specific, leaf-level concept
Small geodesic distance	Closely related in hierarchy
Large geodesic distance	Distant or different subtrees

属性	含义
范数接近0	通用、根层级概念
范数接近1	特定、叶子层级概念
测地距离小	在层级结构中关系密切
测地距离大	属于遥远或不同的子树

Use cases

使用场景

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

依赖分析: 嵌入模块导入关系以找到耦合紧密的子树
代码架构: 映射类层级结构以发现结构模式
知识组织: 嵌入概念以揭示分类关系
代码库导航: 找到与查询相关的最具体/最通用模块