embedding-generation

Generates vector embeddings from model metadata for semantic search and indexing with Voy HNSW.

Updated Aug 23, 2026

Search Tags:#indexing #vector #embedding #semantic-search #transformers #Voy

One-click install

npx skills add https://github.com/bradennapier/ai-model-registry --skill embedding-generation

Or copy as Structured Prompt for Agent▼

Please help me install this Agent Skill.
Skill: embedding-generation
Source: https://github.com/bradennapier/ai-model-registry/tree/main/.claude/skills/embedding-generation
Command: npx skills add https://github.com/bradennapier/ai-model-registry --skill embedding-generation

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires @huggingface/transformers, p-limit, voy-search, xxhash-wasm.

What problem does it solve?

Generates vector embeddings from model metadata to enable fast, semantic search and indexing with Voy HNSW.

Core Features & Use Cases

Embedding generation: Convert model name, description, and modalities into fixed-length vectors.
Batch processing: Efficiently process large model collections with memory-aware batching.
Index building: Create Voy index to power client-side search.

Quick Start

Run the embedding pipeline to produce index.voy from your models list and optionally cache embeddings for reuse.