A controlled study showing how different chunking strategies change which questions are even representable in retrieval-augmented generation systems—independent of retrieval quality.

A lightweight utility for Node.js projects that accumulates items into fixed-size batches (number-of-items wise), preserving insertion order. It abstracts batch management, allowing users to focus on application logic. Ideal for delayed processing tasks such as bulk write/publish operations to kafka, databases, blob storage, etc.