Chunking is still one of the least-discussed but most decisive parts of RAG.
In this episode, we break down why no single chunk size works for all questions, how different queries benefit from different window sizes, and why fixed-window indexing quietly limits retrieval performance. We walk through a multi-window chunking approach, show how rank fusion ties it together, and explain why better agents can’t fix retrieval when the data is indexed the wrong way.
Speakers
Niv Granot
Tech Group Lead @ AI21
Yuval Belfer
Sr. Developer Advocate @ AI21
