Data
RAG (Retrieval-Augmented Generation)
RAG is a pattern in which an AI model retrieves relevant documents from a knowledge base at query time and uses them as additional context to generate its response. It reduces hallucinations and lets the model cite sources without retraining.
RAG (Retrieval-Augmented Generation) in practice
RAG fits questions answered from your own documents: policies, contracts, product manuals, past tickets. Answer quality depends mostly on retrieval: how documents are split, which search is used (often keyword plus semantic search) and whether access rights follow the user. Fine-tuning changes how the model behaves; RAG changes what it can read when it answers. Remolda builds RAG into internal assistants and LLM integrations.
Related terms
- Fine-Tuning · Data
- Vector Database · Data
- Embedding · Data