Retrieval-augmented generation (RAG) is a technique in which a system first retrieves relevant passages from your own documents or data, then gives them to a large language model as context, so answers are grounded in current, private facts and can cite their sources.
RAG is usually the first choice when an AI assistant must know company-specific or frequently changing information, because documents can be updated without retraining the model. Quality depends heavily on chunking, retrieval, permissions and evaluation.
Read more about Retrieval-augmented generation (RAG)
- RAG in Production: An Engineering ChecklistWhat changes when a retrieval-augmented generation prototype becomes a production system — retrieval quality, evaluation, permissions, guardrails, observability and cost.
- LLM Fine-Tuning vs RAG: Which Should You Use?RAG supplies facts at question time; fine-tuning changes how a model behaves. How to choose between them, what fine-tuning needs, and how to prove it worked.
How Marquedata helps
AI & GenAIGenerative AI, RAG and agentic systems engineered for enterprise reliability, security and control.
Related terms
Have a Data, AI or Customer Intelligence Challenge?
Let's explore what you can build with your data.
Have an idea for an intelligent product?