Retrieval-augmented generation (RAG)
Concept
A pattern in which an AI model first retrieves relevant documents from a knowledge source and then writes its answer based on them. It reduces made-up answers and lets models use current, private data without retraining.
| Type | Concept |
|---|---|
| Also known as | RAG |
Related topics in brief
- AI agent · Related to · Concept
A software system that uses an AI model to pursue a goal on its own: it plans steps, calls tools or APIs, reads data and acts, often with a human approving critical steps. Agents go beyond chatbots because they take actions, not just answer questions. - Azure AI Search · Related to · Product
A search service that indexes content and supports vector and hybrid search, often used for RAG. - Knowledge source · Related to · Concept
Content an agent in Copilot Studio can ground its answers on, such as SharePoint sites, files, websites, Dataverse tables or connectors.
Related to
- AI agent · Concept
- Azure AI Search · Product
- Knowledge source · Concept
Community wiki
Short info above, community knowledge below: add practical tips, examples or corrections. New contributions are reviewed first; trusted members publish directly.
Experts and companies for this topic
Nobody has listed this topic yet. Add it to your profile.