vector-search

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Vector Search

向量搜索

HNSW-indexed vector search with RuVector embeddings (384-dim ONNX).

基于RuVector嵌入（384维ONNX格式）的HNSW索引向量搜索。

When to use

使用场景

When you need fast semantic search across large knowledge bases. HNSW provides 150x-12,500x faster search compared to brute-force scanning.

当你需要在大型知识库中进行快速语义检索时。与暴力扫描相比，HNSW可将搜索速度提升150倍至12500倍。

Steps

操作步骤

Check status — call
```
mcp__claude-flow__embeddings_status
```
to verify the embedding engine
Initialize — call
```
mcp__claude-flow__embeddings_init
```
if not already active
Generate embeddings — call
```
mcp__claude-flow__embeddings_generate
```
for text input
Search — call
```
mcp__claude-flow__embeddings_search
```
with a query for semantic matches
Compare — call
```
mcp__claude-flow__embeddings_compare
```
to measure similarity between texts
Unified search — call
```
mcp__claude-flow__memory_search_unified
```
to search across all namespaces

检查状态 — 调用
```
mcp__claude-flow__embeddings_status
```
验证嵌入引擎状态
初始化 — 若嵌入引擎未激活，调用
```
mcp__claude-flow__embeddings_init
```
生成嵌入向量 — 针对文本输入调用
```
mcp__claude-flow__embeddings_generate
```
搜索 — 传入查询语句调用
```
mcp__claude-flow__embeddings_search
```
获取语义匹配结果
相似度对比 — 调用
```
mcp__claude-flow__embeddings_compare
```
衡量文本间的相似度
统一搜索 — 调用
```
mcp__claude-flow__memory_search_unified
```
跨所有命名空间搜索

HNSW Index

HNSW索引

For building custom HNSW indexes:

```
mcp__claude-flow__ruvllm_hnsw_create
```
— create a new index
```
mcp__claude-flow__ruvllm_hnsw_add
```
— add vectors to the index
```
mcp__claude-flow__ruvllm_hnsw_route
```
— route queries through the index

如需构建自定义HNSW索引：

```
mcp__claude-flow__ruvllm_hnsw_create
```
— 创建新索引
```
mcp__claude-flow__ruvllm_hnsw_add
```
— 向索引中添加向量
```
mcp__claude-flow__ruvllm_hnsw_route
```
— 通过索引路由查询请求

Hyperbolic embeddings

双曲嵌入

For hierarchical data (code trees, org charts), use

mcp__claude-flow__embeddings_hyperbolic

which maps to Poincare ball space.

针对层级数据（如代码树、组织结构图），可使用

mcp__claude-flow__embeddings_hyperbolic

，它会将数据映射到庞加莱球空间。

CLI alternative

CLI替代方案

bash

npx @claude-flow/cli@latest embeddings search --query "authentication patterns"
npx @claude-flow/cli@latest embeddings init
npx @claude-flow/cli@latest memory search --query "your query"

bash

npx @claude-flow/cli@latest embeddings search --query "authentication patterns"
npx @claude-flow/cli@latest embeddings init
npx @claude-flow/cli@latest memory search --query "your query"

Performance

性能表现

Method	Speed
Brute-force scan	Baseline
HNSW (n=500)	150x faster
HNSW (n=10,000)	12,500x faster

方法	速度
暴力扫描	基准速度
HNSW (n=500)	快150倍
HNSW (n=10,000)	快12,500倍