Query approach in Azure AI Search where an LLM turns a conversation into several planned subqueries; these execute together, are reranked semantically, and the best chunks are merged. Classic RAG, by contrast, issues just one query.
Read more: Microsoft Learn
In the Ultra Transcenders books
Each book explains Agentic retrieval in context, with comparison tables and the common traps.
Terms in this definition
- Azure AI Search
Managed Azure service that builds indexes over your content and answers keyword, vector, hybrid and semantically ranked queries, optionally with AI enrichment. Retrieval-augmented generation, Foundry agents and knowledge mining all use it to fetch relevant content.
- WHERE
Limits a SELECT, UPDATE or DELETE to just the rows meeting a condition. Omit it, and the statement hits every row.
- LLM
Large language model, usually a transformer network with billions of parameters that learnt to predict the next token from vast amounts of text. Compared with a small language model it is more capable across tasks, but slower and costlier.
- EXECUTE
Allows calling a function or loading a registered model in Unity Catalog, and seeing its definition.
USE CATALOGandUSE SCHEMAare needed too. - RAG
Technique for answering from private or recent information: relevant content is fetched from your own data, typically a search index, and inserted into the prompt as grounding so the model can respond with citations.
Related terms
- Foundry IQ
A managed knowledge layer for Foundry agents, made up of knowledge bases and knowledge sources and built on agentic retrieval in Azure AI Search. It provides grounding that respects permissions and includes citations.
- Knowledge source
In agentic retrieval, the object that tells a knowledge base which content to use, whether indexed or remote (SharePoint, Blob, OneLake or the web). It has nothing to do with knowledge stores.