Agentic RAG
Agentic RAG is a retrieval-augmented generation architecture in which the model decides when and what to retrieve — issuing its own queries, evaluating results, and retrieving again — rather than receiving a single fixed retrieval before generating.
It handles questions that plain RAG cannot: multi-hop reasoning, queries needing several distinct lookups, and cases where the first retrieval returns nothing useful. The cost is latency and unpredictability, since the number of retrieval rounds varies per request. Step limits and per-request budgets are not optional.
Related terms
- RAG (retrieval-augmented generation)
Retrieval-augmented generation is a technique where relevant documents are fetched from an external store and inserted into a language model’s prompt, so the model answers from that specific source material rather than from its training data alone.
- Tool use
Tool use is a language model’s ability to call defined external functions — querying a database, sending a request, performing a calculation — by emitting a structured call that an application executes and returns results for.
- Context window
A context window is the maximum amount of text, measured in tokens, that a language model can consider in a single request, covering the prompt, any retrieved documents, the conversation history and the generated response together.
Tell us what you are building
Send us the problem in a paragraph. You will get a straight answer on whether we can help, and what we would do first.
Book a call