What is RAG?

Retrieving relevant material before answering.

Retrieval-Augmented Generation fetches passages relevant to the question and supplies them to the model before it answers. It is the standard way to ground a model in specific, changeable material without retraining it.

This is an industry glossary. A term defined here is not a statement that Drop AI provides it — see the pricing page for what is included.

Knowledge base

Your own material the agent answers from.

Grounding

Tying answers to source material.

Hallucination

A confident answer that is not true.

Voice AI

More in this category

Voice agent Conversational AI ASR STT TTS LLM System prompt Function calling Tool use Knowledge base Grounding Hallucination

Transform every customer conversation.

Start free, or talk to us about what a custom rollout looks like for your team.

Try for Free Contact Sales