Book a call

Daniel & Friends / Glossary / RAG (retrieval-augmented generation)

AI and automation

RAG (retrieval-augmented generation)

RAG is a method in which a model first retrieves relevant documents, for example company knowledge, and answers from them. It reduces made-up answers and makes it possible to answer over your own data.

Daniel Votruba ·


In practice

RAG pays off where answers rest on your own documents that change often, such as an internal knowledge base or a price list.

Related terms

  • Large language model (LLM): A large language model is a model trained on a huge amount of text that predicts the next words and can write, summarise and answer.
  • Hallucination: A hallucination is a case where a model states plausible-sounding but false information.
  • Fine-tuning: Fine-tuning is further training of an already trained model on your own examples so that it specialises in a style or a task.
  • Context window: The context window is the amount of text a model can process at once, including the instruction and the answer.

More terms in the group AI and automation

Reasoning model · Prompt injection · RPA (robotic process automation) · Prompt engineering · Semantic search · Prompt · Shadow AI · Predictive analytics · Small language model (SLM) · Open-weight model · Speech-to-text · No-code and low-code · System prompt · NLP (natural language processing) · Temperature · Neural network · Text-to-image · Multimodal model · Text-to-speech (TTS) · Multi-agent system · Text-to-video · Model evaluation (evals) · Token · Model bias (AI bias)

Full glossary (590 terms)

Terms in practice

Need help putting them to work?

Terms are one thing, putting them to work is another. We go through which of them pay off for you and say so plainly. You get a first opinion for free and we reply within 24 hours.

Book a call

Enjoyed the article? Share it with friends.