mcpField
V
vector-embed

vector-embed

github.com/ruvnetData & databases80.0k731 installsUpdated today
Repository

About vector-embed

Vector Embed uses the ruvector npm package to create 384-dimensional embeddings from text, code, and documents. The skill covers single and repeated file embedding, an adaptive LoRA option, and optional metadata storage in AgentDB.

Key features

  1. 01Create 384-dimensional embeddings
  2. 02Embed text, code, and documents
  3. 03Use adaptive LoRA embedding by domain
  4. 04Store metadata in AgentDB

Use cases

  1. 01Prepare text for semantic search
  2. 02Compare or cluster embedded content
  3. 03Embed file contents one at a time

MCP support

An MCP server can be registered with the documented command; its tools include semantic context, search, AST analysis, and routing.

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/ruvnet/ruflo --skill vector-embed

After installing, type/vector-embedin Claude Code to confirm it loaded.

Details

From the project README

Vector Embed

Generate and store vector embeddings using the ruvector npm package.

When to use

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).

Steps

  1. Ensure [email protected] is available: 
    npm ls ruvector 2>/dev/null | grep '0.2.25' || npm install [email protected]
    If embed text later reports ONNX WASM files not bundled, also run: 
    npm install ruvector-onnx-embeddings-wasm
  2. Embed the input (use the text subcommand, with text as a positional arg):
    • Single string: npx -y [email protected] embed text "your text here"
    • With output file: npx -y [email protected] embed text "your text here" -o vec.json
    • For a file: read its content via the Read tool, then pass it as the positional argument.
    • For batch: loop over files in shell — [email protected] has no built-in --batch/--glob flags.
  3. Adaptive (LoRA) variant: npx -y [email protected] embed text "..." --adaptive --domain code
  4. Confirm — report vector dimension (384), norm, and any output path written.
  5. Store metadata in AgentDB if needed: mcp__plugin_ruflo-core_ruflo__memory_store({ key: "embed-SOURCE", value: "VECTOR_METADATA", namespace: "vector-patterns" })

MCP alternative

Register the MCP server once with the pinned version:

claude mcp add ruvector -- npx -y [email protected] mcp start

Then call MCP tools directly: hooks_rag_context (semantic context), brain_search (collective brain), hooks_ast_analyze, hooks_route.

Caveats

  • The embed --batch --glob and embed --file flags do not exist in [email protected]; only embed text <text> is supported. Read files yourself and call embed text per file.
  • ONNX runtime is not bundled by default. If embedding fails, install ruvector-onnx-embeddings-wasm or run npx -y [email protected] doctor to diagnose.

Comments

Markdown supported