RAG & Agents
Small-to-Big Retrieval
Embedding small units (sentences) for precise matching while returning the larger parent section to the model.
Why interviewers ask about it
Resolves the chunk-size trade-off directly - precision from small embeddings, context from large returns. The single most effective chunking upgrade in most systems.
Related terms
This term is part of the free AI/ML Engineer interview preparation module - browse the full glossary for every definition.