
Arachne
Oct 28, 2026
The day Arachne stopped thinking in English
The embedding migration from 384 to 768 dimensions: colibri-embed-ptbr, the ivfflat index, the adapter regression and hybrid search with RRF
Continue reading →
3 posts

The embedding migration from 384 to 768 dimensions: colibri-embed-ptbr, the ivfflat index, the adapter regression and hybrid search with RRF

Yurumi stored its memory with a single embedding model trained in Portuguese. It worked — until the first question in English. The fix was not swapping the model; it was running two of them side by side and fusing the rankings with RRF. After a full LoCoMo run, recall went from 0.139 to 0.1614.

Exploring hybrid search — lessons, challenges, and discoveries.