DeepVox Book a discovery sprint
Knowledge & retrievalVoice agentsAI automationFine-tuned small modelsConnectorsAccess controlDeploymentPlatform overviewBy teamBy industryCase studiesEuropeUnited StatesIndiaSecurityComparePricingBlogGuide: sovereign AIGlossaryFAQAboutTeamHow we workCareersPressContact Book a discovery sprint

Glossary

What is Retrieval-augmented generation (RAG)?

RAG retrieves relevant passages from your documents and has a model answer from them, with citations.

Definition

Retrieval-augmented generation (RAG) is a technique where an AI system first retrieves relevant passages from a knowledge base and then has a language model answer using those passages, usually citing them.

How it works

  1. Documents are split into passages and indexed, often as embeddings in a vector database.
  2. A question is matched to the most relevant passages, then reranked.
  3. A model writes the answer from those passages and cites them.

Answers stay current without retraining, sources can be shown, and permissions can be enforced at retrieval time.

See knowledge & retrieval.

Start with two weeks of evidence, not a sales call.

A fixed-price discovery sprint, credited against whatever comes next. Or write to sales@deepvox.ai.

Book a discovery sprint