Retrieval Augmented Generation - using search (usually with some kind of semantic component) to find relevant context and provide it to the language model to help it respond, give it knowledge about a specific document, etc.

Oh right, I remember now. Thank you for explaining it

Retrieval Augmented Generation. Fancy way of saying, retrieve chunks from your document corpus similar to your input using a similarity (mostly cosine) of embedding vectors of the chunks and input vectors, then inject those relevant chunks into your prompt to the LLM. Useful for Document Intelligence.

Thank you for the explanation, I remember hearing about this now