QVAC Logo

Addons

Reference for the QVAC components that provide AI capabilities.

Overview

Each addon is a JavaScript Bare module that adds support for one or more AI tasks to QVAC ecosystem.

If you use the SDK, you don’t need to use addons directly. The SDK is the canonical way to build with QVAC: it unifies all addon capabilities under a single interface, enables QVAC to run on JS runtimes beyond Bare, and provides out-of-the-box P2P connectivity.

Compatibility matrix

All addons support the following platforms:

PlatformMin VersionArchitectureGPU API/BackendNotes
macOS14.0+arm64MetalArch x64 supports CPU inference only; Intel iGPU acceleration not supported
iOS17.0+arm64MetalRequires Expo
LinuxUbuntu 22+arm64, x64VulkanVulkan runtime required
Android12+arm64Vulkan, OpenCL (Adreno 700+)Requires Expo
Windows10+x64VulkanVulkan-capable GPU + vendor drivers required

Catalog

The following table lists all available addons for QVAC ecosystem:

PackageAI TasksDescriptionInference engineStability
@qvac/llm-llamacppCompletion, multimodalLLM inference for text generation and chat with support to images, and other media within a single conversation context.llama.cppstable
@qvac/embed-llamacppText embeddings, RAGVector embedding generation for semantic search, clustering, and retrieval that seamlessly suppports retrieval-augmented generation workflow.llama.cppstable
@qvac/translation-nmtcppTranslationText-to-text neural machine translation (NMT).Marian and Bergamotstable
@qvac/transcription-whispercppTranscriptionAutomatic speech recognition (ASR) for speech-to-text.whisper.cppstable
@qvac/tts-onnxText-to-speechSpeech synthesis for text-to-speech (TTS).ONNX Runtimestable
@qvac/ocr-onnxOCROptical character recognition (OCR) for extracting text from images.ONNX runtimestable

On this page