Stop Chunking Like It's 2022 — Yuval Belfer, AI21 Labs
Source
AI Engineer
Author
AI Engineer
Date
Terms in this piece · Glossary
chunking — Splitting documents into passages small enough to embed and retrieve individually — the step that quietly determines whether retrieval works at all.
RAG — Retrieval-augmented generation — fetching relevant documents first and pasting them into the model's context so it answers from your data instead of memory.
Why it matters
It's a reproducible technique for closing a measurable recall gap in RAGRetrieval-augmented generation — fetching relevant documents first and pasting them into the model's context so it answers from your data instead of memory.Full definition → pipelines caused by choosing chunk size before you know the query.
