Concept
Dense retriever
A dense retriever is a search component that finds relevant documents by comparing learned vector embeddings rather than matching literal terms. Think of it like grep, except instead of looking for exact strings, it maps both the query and every document into a shared…
The rest of “Dense retriever” is a premium feature: every concept in the library gets a precise, practitioner-focused write-up like this one, cross-linked straight from the paper summaries that use it.
Log in to unlock→