Matryoshka embeddings

Matryoshka embeddings are embeddings trained so that their first dimensions carry the most information, allowing vectors to be truncated to shorter lengths to save storage and compute with limited loss in quality.

Matryoshka embeddings sits in the Retrieval & memory part of the Agentik {OS} glossary, which defines the words used to build and run AI agent systems.

Also called Matryoshka representation learning.