vector-embed

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Vector Embed

向量嵌入

Generate and store vector embeddings using the

ruvector

npm package.

使用

ruvector

npm包生成并存储向量嵌入。

When to use

使用场景

Use this skill to embed text, code, or documents into 384-dimensional vectors for semantic search, similarity comparison, or clustering. ruvector uses ONNX all-MiniLM-L6-v2 with HNSW indexing (52,000+ inserts/sec, ~0.045ms search).

当你需要将文本、代码或文档转换为384维向量，用于语义搜索、相似度对比或聚类时，可以使用该技能。ruvector采用ONNX all-MiniLM-L6-v2模型搭配HNSW索引（插入速度52000+条/秒，搜索耗时约0.045毫秒）。

Steps

操作步骤

Ensure ruvector is available:

bash

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

Embed the input:

For text:
```
npx ruvector embed "your text here"
```
For a file:
```
npx ruvector embed --file src/module.ts
```

For batch:

npx ruvector embed --batch --glob "src/**/*.ts"

Normalization -- ruvector L2-normalizes by default (unit sphere, cosine similarity). Alternatives:
```
--norm l1
```
,
```
--norm minmax
```
,
```
--norm zscore
```
Confirm -- report vector ID, dimension (384), norm, and index stored in

Store metadata in AgentDB if needed:

mcp__claude-flow__memory_store({ key: "embed-SOURCE", value: "VECTOR_METADATA", namespace: "vector-patterns" })

确保ruvector可用：

bash

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

生成嵌入向量：

针对文本：
```
npx ruvector embed "your text here"
```
针对文件：
```
npx ruvector embed --file src/module.ts
```

针对批量处理：

npx ruvector embed --batch --glob "src/**/*.ts"

归一化处理——ruvector默认采用L2归一化（单位球面，余弦相似度）。可选方案：
```
--norm l1
```
,
```
--norm minmax
```
,
```
--norm zscore
```
确认结果——查看向量ID、维度（384）、归一化值，以及索引存储位置

如需存储元数据，可存入AgentDB：

mcp__claude-flow__memory_store({ key: "embed-SOURCE", value: "VECTOR_METADATA", namespace: "vector-patterns" })

MCP alternative

MCP替代方案

If ruvector MCP server is connected (

claude mcp add ruvector -- npx ruvector mcp start

```
hooks_rag_context
```
— semantic context retrieval
```
brain_search
```
— shared brain knowledge search

若已连接ruvector MCP服务器（

claude mcp add ruvector -- npx ruvector mcp start

）：

```
hooks_rag_context
```
—— 语义上下文检索
```
brain_search
```
—— 共享知识库搜索

Batch embedding

批量嵌入处理

bash

npx ruvector embed --batch --glob "src/**/*.ts"

Reports total vectors inserted and index growth.

bash

npx ruvector embed --batch --glob "src/**/*.ts"

报告会显示插入的向量总数以及索引增长情况。