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

vector-embed

Generate 384-dimensional text embeddings with ruvector and store them in an HNSW index.

70.1k|8.4k|Updated Jun 2, 2025
Search Tags:#embeddings#vector database#npx#HNSW#ONNX#RuVector#Semantic Search
One-click install
npx skills add https://github.com/ruvnet/claude-flow --skill vector-embed
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: vector-embed
Source: https://github.com/ruvnet/claude-flow/tree/main/plugins/ruflo-ruvector/skills/vector-embed
Command: npx skills add https://github.com/ruvnet/claude-flow --skill vector-embed

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires [email protected], ruvector-onnx-embeddings-wasm.

What problem does it solve?

Converting text, code, or documents into numeric vectors for semantic search and similarity comparison requires setting up an embedding model and index, which is tedious to wire up manually.

Core Features & Use Cases

  • Text Embedding: Generate 384-dimensional vectors from any string using ONNX all-MiniLM-L6-v2 via the ruvector CLI.
  • Adaptive Embeddings: Produce domain-tuned vectors with the LoRA-based --adaptive flag, for example for code.
  • Metadata Storage: Persist embedding metadata in AgentDB memory for later semantic retrieval.
  • Use Case: Embed a set of documentation files one by one, store their vectors in the HNSW index, and later run semantic search to find the most relevant document for a user query.

Quick Start

Ask the agent to embed the text of a specific file or string using ruvector and report the resulting vector dimension and norm.

Frequently Asked Questions about vector-embed

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

FAQPage Schema
How do I generate text embeddings with ruvector?▼

Run npx -y [email protected] embed text "your text here" to produce a 384-dimensional vector using the ONNX all-MiniLM-L6-v2 model. Add -o vec.json to write the output to a file.

How do I embed multiple files with ruvector?▼

[email protected] has no --batch or --glob flags, so loop over files in the shell. Read each file's content yourself and call embed text once per file.

Does ruvector support batch embedding or file input flags?▼

No. In [email protected] only the embed text subcommand with a positional text argument is supported; the --batch, --glob, and --file flags do not exist.

Why does ruvector embedding fail with ONNX WASM errors?▼

The ONNX runtime is not bundled by default, so embedding can report missing ONNX WASM files. Install ruvector-onnx-embeddings-wasm or run npx -y [email protected] doctor to diagnose the setup.

What is the ruvector adaptive embedding mode?▼

Adaptive mode applies a LoRA-tuned variant of the embedding model for a specific domain. Invoke it with npx -y [email protected] embed text "..." --adaptive --domain code for code-oriented embeddings.

Related Skills

Explore More Software Engineering Skills→
winsorllcwinsorllc

qr-decoder

Decode QR codes from image files and URLs into text, JSON, or raw data.

Community
Intermediate
agenticsorgagenticsorg
25

AgentDB Vector Search

Implement semantic vector search with AgentDB for document retrieval and similarity matching.

Official
Advanced
hiddink-aihiddink-ai
1

semble-integration

Integrate the Semble MCP server for embedding-based semantic code search.

Official
Intermediate
DhumitechDhumitech

embedding-strategies

Compare and select embedding models for retrieval pipelines.

Community
Advanced