Agentic RAG

As explained in Essential GraphRAG

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

Agentic RAG uses multiple retrieval agents to find data for a user question. A retriever router selects the best retriever or retrievers, then an answer critic checks whether the retrieved context answers the question. section 5.0 section 5.1

Build the system from three foundational parts:

• Retriever router: maps user questions to suitable retrievers. section 5.1
• Retriever agents: search available sources using generic or specialized strategies. section 5.4
• Answer critic: evaluates whether retrieved answers correctly address the original question. section 5.1

Figure 5.1 The data flow for an application using agentic RAG

Trace the data flow from the user question through routing and retrieval to answer assessment. section 5.0

How Essential GraphRAG covers it

How deep it goes

Defines routing, retrieval, and answer criticism, while stopping short of advanced multi-step task planning.

Examples

Uses generic vector retrieval, specialized text2cypher, and parameterized database queries as alternative retriever agents.

What it assumes

Assumes familiarity with retrieval methods and structured versus unstructured data, while introducing agentic components from basic cases.

What you can do after

Build retrieval workflows that select suitable sources and assess answer quality before returning results.

How it connects

Connects RAG with vector similarity search, graph databases, text2cypher, and LLM tool use.

liveBookmanning.com

Read Essential GraphRAG 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
  Building Reliable AI SystemsA retrieval-augmented generation approach in which an AI agent controls the retrieval process, including deciding when multiple retrievals are needed.

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 Essential GraphRAG. The section links point to the parts of the book it draws on.