RAG Learning

RAG Architecture

A RAG system has two components: a retriever that retrieves information from external memory sources and a generator that generates a response based on the retrieved information.

A retriever has two main functions: indexing and querying. Indexing involves processing data so that it can be quickly retrieved later. Sending a query to retrieve data relevant to it is called querying.

A high-level view of how an embedding-based, or semantic, retriever works

Multimodal RAG can augment a query with both text and images. (*The real image from Up is not used, for copyright reasons.)