v0.1.7

Vexa-ai/vexav0.1.7Jan 16, 2026by chonknick

Upgrading?

AI Summary

This release introduces support for the new Voyage 4 family of embedding models, featuring flagship, mid-sized, and lightweight options, alongside advanced capabilities like a 32k token context window and flexible dimensions.

Key Highlights

  • Added support for Voyage 4 embedding models (large, balanced, lite, nano)
  • 32,000 token context window support
  • Flexible dimensions via Matryoshka learning
  • Support for multiple quantization formats (float, int8, binary)

New Features

  • Voyage 4 embedding model integration
  • 32k token context support
  • Flexible dimensions
  • Multiple quantization formats

Full Release Notes

## What's New

- Added support for Voyage 4 embedding models:
  - `voyage-4-large` - Flagship MoE model, #1 on MTEB (78.26)
  - `voyage-4` - Mid-sized balanced model
  - `voyage-4-lite` - Lightweight model, #9 on MTEB (73.29)
  - `voyage-4-nano` - Open-weight model (Apache 2.0)

All Voyage 4 models support:
- 32,000 token context
- Flexible dimensions (2048/1024/512/256) via Matryoshka learning
- Multiple quantization formats (float, int8, binary)

Related Repositories