RAG and fine-tuning solve different problems and are often combined. RAG handles knowledge that changes over time and gives citable answers. Fine-tuning handles style, format, and behavioural specialisation that is hard to fit in a prompt.
The usual decision rule: if the gap is "the model does not know X facts," use RAG. If the gap is "the model knows X but does not behave the way I need," use fine-tuning. Both have measurable quality lift; combining both is common in mature production systems.