Applied AI·Embeddings and retrieval
you split the document into pieces before you store it, because embedding a whole 40-page PDF as one blob retrieves nothing useful.
Chunking
Draft summary, pending review
Splitting documents into pieces before embedding, because embeddings represent one 'thought' well and a 40-page document poorly, and because retrieved chunks must fit a context budget. Chunking quality caps retrieval quality; garbage chunks, garbage answers.