Basic RAG is the foundational version of Retrieval-Augmented Generation. When a query comes in, the system retrieves relevant documents from an external source and includes them in the prompt sent to the language model, which then generates a response based on that retrieved content.
Basic RAG uses a fixed retrieval step before every generation — it always retrieves something, regardless of whether retrieval is actually needed. More advanced variants like Adaptive RAG and Agentic RAG build on this foundation by making retrieval smarter, more selective, and more responsive to the complexity of each query.
