ruvector-onnx-embeddings-wasm

Generate text embeddings with ONNX Runtime in WebAssembly.

1|Updated Feb 8, 2026
One-click install
npx skills add https://github.com/ricable/cli-skills-builder --skill ruvector-onnx-embeddings-wasm
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ruvector-onnx-embeddings-wasm
Source: https://github.com/ricable/cli-skills-builder/tree/main/.claude/skills/ruvector-onnx-embeddings-wasm
Command: npx skills add https://github.com/ricable/cli-skills-builder --skill ruvector-onnx-embeddings-wasm

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill enables the generation of text embeddings directly within the browser or on edge devices, eliminating the need for server-side infrastructure for AI model inference.

Core Features & Use Cases

  • On-Device Embeddings: Generate embeddings using ONNX Runtime compiled to WebAssembly, with SIMD and multi-threading support.
  • Offline Capability: Build applications that can generate embeddings without an internet connection.
  • Use Case: Develop a semantic search feature for a web application that works entirely in the user's browser, allowing for fast, private, and offline-capable search functionality.

Quick Start

Use the ruvector-onnx-embeddings-wasm skill to generate embeddings for the text 'Hello world'.

Frequently Asked Questions about ruvector-onnx-embeddings-wasm

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

FAQPage Schema
How do I generate text embeddings in the browser without a backend server?

You can generate text embeddings directly in the browser using ONNX Runtime compiled to WebAssembly, eliminating server-side inference. This enables private, client-side semantic search applications without internet connectivity.

Can I use WebAssembly and ONNX to build offline semantic search?

Yes, WebAssembly with ONNX Runtime supports offline semantic search applications. It leverages SIMD and parallel workers to compute text embeddings directly on edge devices or within the user's browser.

Does ONNX Runtime WebAssembly support SIMD and multi-threading for inference?

ONNX Runtime in WebAssembly supports SIMD and parallel workers to accelerate inference. This allows efficient text embedding generation directly in browser and edge environments.

What is the best way to run AI models for semantic search on edge devices?

Running AI models on edge devices is best achieved by compiling ONNX Runtime to WebAssembly. This approach processes text embeddings locally, ensuring fast and private semantic search without server infrastructure.

Do I need a WASM runtime with ONNX support to generate client-side embeddings?

Yes, a WASM runtime with ONNX support is required to generate client-side text embeddings. This environment executes the model inference locally, enabling offline and private semantic search functionality.