v0.1.7

feyninc/catsuv0.1.7Jan 16, 2026by chonknick

AI Summary

Introduces support for Voyage 4 embedding models with extended context windows and flexible dimensions.

Key Highlights

Added support for Voyage 4 embedding models (large, standard, lite, nano)
Models support a 32,000 token context window
Flexible dimensions (2048/1024/512/256) via Matryoshka learning
Multiple quantization formats (float, int8, binary) supported

New Features

Voyage 4 embedding model integration

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)