Agentic RAG

As explained in Building Reliable AI Systems

A retrieval-augmented generation approach in which an AI agent controls the retrieval process, including deciding when multiple retrievals are needed.

Agentic RAG gives an AI agent control over retrieval: it can decide when a question needs multiple searches, then synthesize the results. It can also combine stored documents with actions or services that provide current information. section 3.7.8 section 6.3

Two kinds of information need

To compare electronics and clothing return policies alongside customer reviews, the agent queries the relevant policy and review sources, then combines the findings. For trip planning, it can pair document retrieval with a weather service to address current conditions that stored knowledge cannot provide. section 3.7.8 section 6.3

A practical travel assistant can combine a vector store with tools such as a weather API. One implementation uses a ReAct-based TypeScript chat interface that displays selected tools and reasoning steps; a Python equivalent provides the same agent behavior. section 6.3.1

Figure 6.6 An Agentic RAG system consisting of a weather tool (API) and vector store (RAG)

Illustrates an agentic RAG setup combining a weather API tool with a vector store. section 6.3.1

How Building Reliable AI Systems covers it

How deep it goes

Explains multi-source retrieval decisions and practical tool integration through a travel-assistant implementation.

Examples

Uses policy-and-review comparisons and travel planning with a weather service to illustrate retrieval needs.

What you can do after

Build a travel assistant that combines document retrieval with real-time services using LangChain.

How it connects

Connects retrieval-augmented generation with AI agents, ReAct, vector stores, and external APIs.

liveBookmanning.com

Read Building Reliable AI Systems on liveBook Get the book at manning.com

Also explained in

• 

  liveBookmanning.com
  AI Agents in Action, Second Edition
• 

  liveBookmanning.com
  Domain-Specific Small Language ModelsA retrieval-augmented generation setup that uses an AI agent to plan, select, and combine retrieval actions across one or more sources before generation.
• 

  liveBookmanning.com
  Essential GraphRAGAgentic RAG is a retrieval-augmented generation pattern in which agents and routing mechanisms select and coordinate retrieval actions to answer a question.

Compare how 4 books explain agentic RAG →

Related concepts

• AI agentuses · An AI agent is a computational system that uses artificial intelligence to interpret information, select actions, and pursue goals through interaction with an environment.
• information retrievaluses · Information retrieval is the process of locating and selecting relevant information from an available collection in response to a query or information need.
• retrieval-augmented generationkind of · Retrieval-augmented generation is a technique that retrieves relevant information from external sources and supplies it as context to a generative model when producing an output.
• routinguses · Routing is the selection of a path, destination, or processing component to direct an item, request, or flow toward an intended endpoint.
• LangChainuses · LangChain is an open-source software framework for building applications that compose language models with prompts, data sources, tools, and other components.
• similarity searchuses · Similarity search is a retrieval technique that finds or ranks items by comparing their representations with a query according to a similarity or distance measure.

This explainer was generated by Manning's knowledge graph from the text of Building Reliable AI Systems. The section links point to the parts of the book it draws on.