AI engineering glossary · RAG vector search
What is Agentic RAG?
Agentic RAG: A RAG design where a language model acts as an agent that decides whether to search, which source or tool to use, how to phrase queries and whether to search again. It handles harder questions than a fixed retrieve-then-generate pipeline, with more latency and cost.
Agentic RAG: an example
An agent chooses to query the HR wiki first, finds it lacking, and then queries the payroll database.
Related terms
- Iterative retrieval
- Multi-hop retrieval
- Query decomposition
More RAG vector search terms
- Alpha weighting
- ANN recall
- Answer correctness
- Answer relevance
- Approximate nearest neighbour search
- Asymmetric search
- Attribution
- Binary quantisation
Where you learn it
Agentic RAG is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.