What is RAG (retrieval-augmented generation)?

Letting a model look things up in your documents before answering. It searches, puts the relevant parts into the prompt, then answers — so answers stay up to date without retraining.

AI glossary

LLM (large language model)Token Context window Prompt Fine-tuning Embedding Parameters (7B, 70B…)Quantization Open weights Hallucination Multimodal Diffusion model AI agent Inference Benchmark