Retriever

An architectural pattern that enhances generative model responses by retrieving relevant information from external knowledge bases.

A retrieval technique that uses dense vector embeddings to identify semantically relevant documents based on similarity in an embedding space.

A search technique that uses term frequency and keyword matching, such as BM25, to locate relevant documents within a corpus.

A retrieval process that re-scores and re-orders an initial list of candidate documents using a specialized model to improve relevance.

A retrieval technique that combines semantic vector search with keyword-based lexical search to improve the relevance, accuracy, and recall of retrieved information by leveraging the strengths of both approaches.