v0.1.7

thevoiceguy/siphon-aiv0.1.7Jan 16, 2026by chonknick

Upgrading?

AI Summary

This update introduces new embedding model support for Voyage 4, featuring flagship, mid-sized, and lightweight variants. The new models provide advanced capabilities such as 32,000 token context windows and flexible dimensions via Matryoshka learning. Users can also choose from multiple quantization formats including float, int8, and binary.

Key Highlights

  • Added support for Voyage 4 embedding models (large, mid-sized, lite, nano)
  • Support for 32,000 token context windows
  • Flexible dimensions (2048/1024/512/256) via Matryoshka learning
  • Multiple quantization formats (float, int8, binary)

New Features

  • Voyage 4 embedding model support
  • 32,000 token context support
  • Flexible dimensions support
  • Multiple quantization formats support

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