55 packages
@qvac/cli
Command-line interface for the QVAC ecosystem
@qvac/decoder-audio
This decoder library leverages FFmpeg for efficient audio decoding. It simplifies processing of input audio, particularly as a preprocessing step for other addons.
@qvac/diagnostics
Diagnostic report generation library for QVAC
@qvac/dl-base
Base dataloader class for QVAC
@qvac/dl-filesystem
`@qvac/dl-filesystem` is a data loading library designed to load model weights and other resources from a local filesystem. It provides a simple and efficient way to retrieve files required for AI model inference, training, and other operations directly f
@qvac/dl-hyperdrive
`@qvac/dl-hyperdrive` is a data loading library designed to load model weights and other resources from a [Hyperdrive](https://github.com/holepunchto/hyperdrive) instance. It leverages the `Hyperdrive` distributed file system for efficient peer-to-peer fi
@qvac/embed-llamacpp
bert addon for qvac
@qvac/error
Base error handling library for QVAC
@qvac/infer-base
Base class for inference clients
@qvac/langdetect-text
`@qvac/langdetect-text` is a language detection library for qvac. It provides an interface for detecting the language of a given text, returning either the single most likely language or the top K probable languages.
@qvac/langdetect-text-cld2
Language detection using CLD2 with same API as @qvac/langdetect-text
@qvac/llm-llamacpp
llama addon for qvac
@qvac/logging
`qvac-lib-logging` wraps any logger you supply and normalizes the interface.
@qvac/ocr-onnx
OCR addon for qvac
@qvac/onnx
Bare addon for ONNX Runtime session management
@qvac/rag
A JavaScript library for Retrieval-Augmented Generation (RAG) within the QVAC ecosystem. Build powerful, context-aware AI applications with seamless document ingestion, vector search, and LLM integration.
@qvac/registry-client
QVAC Registry client library for read-only queries via Hyperswarm
@qvac/registry-schema
HyperDB schema and database wrapper for QVAC Registry
@qvac/response
Response class for QVAC
@qvac/sdk
**QVAC SDK** is the canonical entry point to develop AI applications with QVAC.
@qvac/transcription-parakeet
High-performance speech-to-text inference addon using NVIDIA Parakeet models for Bare runtime
@qvac/transcription-whispercpp
transcription addon for qvac
@qvac/translation-nmtcpp
translation addon for qvac
@qvac/tts-onnx
Text to Speech (TTS) addon for qvac
@tetherto/create-wdk-module
Create WDK modules with a single command