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
Contextual RAG
Prepend LLM-generated context to each chunk before embedding it.
Addresses the “lost in the middle” problem in retrieval. An LLM generates a
succinct piece of context for each document chunk, which is prepended to the
chunk before embedding, so a chunk carries enough surrounding meaning to be
retrieved for the right queries.
Was this page helpful?