04
Chunking
Decide what a searchable piece of knowledge looks like.
Concept 4.1
Why we chunk, and the main chunking strategies
Why documents are cut into pieces before search, and how fixed, recursive and heading-based splitting differ on the same corpus.
Concept 4.2
Structure aware chunking and tables
Splitting documents along their own headings and keeping tables whole, and why structure alone did not win on our table questions.
Concept 4.3
Chunk size, overlap and token based sizing
How big each piece of a document should be, why you measure it in tokens, and how to find the right size with a number instead of a guess.
Concept 4.4
Contextual chunking and late chunking
Two ways to give a chunk the context it lost when it was cut out, a cheap header and a model-written summary, plus late chunking, with a measured test of the cheap one.
Concept 4.5
Parent child and multi representation indexing
Search with small precise pieces, answer with the larger section they belong to, and other ways to index one passage in more than one form.
Concept 4.6
Chunk metadata, provenance and the chunking debugging playbook
What to store with every chunk so you can cite, filter and update it, and a step by step way to find out why a question was missed.
Chapter 4 recap