Glossary AI

RAG (Retrieval Augmented Generation)

Also known as: Retrieval Augmented Generation

A technique where an AI model looks up relevant information from a database before generating its answer. Combines a search index (vector database, full-text, or hybrid) with a language model. The most common pattern for grounding agents in private data.

Related terms

Embedding

A numerical representation of text (or images, audio, etc.) as a vector — a long list of numbers — capturing semantic meaning. ...

Grounding

Connecting an AI model's responses to real, verifiable information instead of letting it generate from training data alone. Don...

Vector Database

A database optimized for storing and searching embeddings. Lets agents find "the most semantically similar document" in millise...

Build with this on OTP

If this term shows up in your playbook, it belongs in your OOS.

OTP encodes coordination intelligence so teams of humans and AI agents can run on it.

Get started Browse practices All terms →

Found an issue with this definition? Tell us and we'll fix it.