This example is a runnable notebook in the
vectordb-recipes repository rather than a page here.
Open in Colab
Run it end to end in the browser.
View on GitHub
Read the source.
RAG
Late chunking
Retrieve whole documents first, chunk them afterwards.
Inverts the usual order: documents are retrieved first and chunked just before
synthesis. Chunking late preserves context that pre-chunking discards, since a
chunk is cut with knowledge of the query it is answering.
Was this page helpful?