Model Lifecycle
RAG (Retrieval-Augmented Generation)
Giving a model outside documents to read at answer time, instead of relying only on what it memorized during training.
An LLM's training data has a cutoff date and can't include a company's private files. RAG fixes this by searching a document store for relevant passages when a question comes in, then feeding those passages into the model's context window alongside the question, so the answer is grounded in real, current source material.
RAG is one of the most common patterns in production AI products because it reduces hallucination and makes answers traceable to a specific source, without the cost of retraining the model itself.