Podcast: Sam Partee on Retrieval Augmented Generation (RAG)

In this podcast, Sam shares his insights on Redis' vector database offering, different approaches to embeddings, how to enhance large language models by adding a search component for retrieval augmented generation, and the use of hybrid search in Redis.

ai data-augmentation database embeddings hybrid insights language language models large language large language models ml & data engineering podcast rag redis retrieval retrieval augmented generation sam search shares the infoq podcast vector vector database