Two different tools
Retrieval-augmented generation (RAG) looks up relevant passages from your documents at question time and asks the model to answer from them. Fine-tuning changes the model itself by training it on examples.
When RAG is the right choice
Use RAG when knowledge changes often, when answers must cite sources and when different users are allowed to see different documents. Most business assistants start here.
When fine-tuning helps
Fine-tuning helps when you need a consistent style or format, or a narrow specialized task, and when you have many high-quality examples to learn from.
Often the answer is both
Many production systems use RAG for knowledge and light fine-tuning for tone or structure. Evaluation sets built from real questions show which combination performs best on your data.