menu
{ "item_title" : "Advanced Knowledge Graphs for LLMs", "item_author" : [" Lin Prescott "], "item_description" : "Building a Knowledge Graph is only the beginning.Modern AI applications increasingly need to retrieve information across connected entities, reason over multiple relationships, coordinate tools and data sources, and operate reliably at production scale. Advanced Knowledge Graphs for LLMs explores the techniques and architectures required to take graph-powered LLM applications beyond basic retrieval and into sophisticated intelligent systems.This volume builds on the foundations of Knowledge Graph construction and LLM integration to explore advanced retrieval, reasoning, agentic workflows, optimization, evaluation, security, and production deployment.You will learn how to: Design advanced graph-based retrieval architecturesBuild Graph RAG systems for complex information needsImplement multi-hop retrieval and relationship-aware reasoningCombine graph search, vector search, and semantic retrievalImprove context selection and reduce irrelevant informationBuild LLM-powered agents that interact with Knowledge GraphsDesign agentic workflows for research, question answering, and decision supportOptimize graph queries, retrieval pipelines, and LLM context windowsEvaluate Knowledge Graph quality and LLM application performanceDevelop testing, benchmarking, human-in-the-loop, and A/B evaluation strategiesAddress security, access control, privacy, and data governanceDesign scalable architectures for large Knowledge Graph and LLM workloadsMonitor, maintain, and continuously improve graph-powered AI systemsTransition experimental Knowledge Graph applications into production environmentsThe book focuses on the engineering challenges that emerge when Knowledge Graphs and LLMs move from prototypes to real-world systems.Through practical architectures, implementation patterns, evaluation strategies, and production considerations, you will learn how to build AI applications that can retrieve connected knowledge, reason across relationships, use structured context, and operate reliably at scale.If Foundations of Knowledge Graphs for LLMs teaches you how to build the foundation, this volume teaches you how to extend, optimize, evaluate, and productionize it.Go beyond basic RAG. Build AI systems that can connect knowledge, retrieve context, and reason across relationships.", "item_img_path" : "https://covers3.booksamillion.com/covers/bam/9/79/819/185/9798191854434_b.jpg", "price_data" : { "retail_price" : "22.99", "online_price" : "22.99", "our_price" : "22.99", "club_price" : "22.99", "savings_pct" : "0", "savings_amt" : "0.00", "club_savings_pct" : "0", "club_savings_amt" : "0.00", "discount_pct" : "10", "store_price" : "" } }
Advanced Knowledge Graphs for LLMs|Lin Prescott

Advanced Knowledge Graphs for LLMs : Designing, Optimizing, and Scaling Production-Ready Graph-Based AI Systems

local_shippingShip to Me
In Stock.
FREE Shipping for Club Members help

Overview

Building a Knowledge Graph is only the beginning.

Modern AI applications increasingly need to retrieve information across connected entities, reason over multiple relationships, coordinate tools and data sources, and operate reliably at production scale. Advanced Knowledge Graphs for LLMs explores the techniques and architectures required to take graph-powered LLM applications beyond basic retrieval and into sophisticated intelligent systems.

This volume builds on the foundations of Knowledge Graph construction and LLM integration to explore advanced retrieval, reasoning, agentic workflows, optimization, evaluation, security, and production deployment.

You will learn how to:

  • Design advanced graph-based retrieval architectures
  • Build Graph RAG systems for complex information needs
  • Implement multi-hop retrieval and relationship-aware reasoning
  • Combine graph search, vector search, and semantic retrieval
  • Improve context selection and reduce irrelevant information
  • Build LLM-powered agents that interact with Knowledge Graphs
  • Design agentic workflows for research, question answering, and decision support
  • Optimize graph queries, retrieval pipelines, and LLM context windows
  • Evaluate Knowledge Graph quality and LLM application performance
  • Develop testing, benchmarking, human-in-the-loop, and A/B evaluation strategies
  • Address security, access control, privacy, and data governance
  • Design scalable architectures for large Knowledge Graph and LLM workloads
  • Monitor, maintain, and continuously improve graph-powered AI systems
  • Transition experimental Knowledge Graph applications into production environments

The book focuses on the engineering challenges that emerge when Knowledge Graphs and LLMs move from prototypes to real-world systems.

Through practical architectures, implementation patterns, evaluation strategies, and production considerations, you will learn how to build AI applications that can retrieve connected knowledge, reason across relationships, use structured context, and operate reliably at scale.

If Foundations of Knowledge Graphs for LLMs teaches you how to build the foundation, this volume teaches you how to extend, optimize, evaluate, and productionize it.

Go beyond basic RAG. Build AI systems that can connect knowledge, retrieve context, and reason across relationships.

This item is Non-Returnable

Details

  • ISBN-13: 9798191854434
  • ISBN-10: 9798191854434
  • Publisher: Independently Published
  • Publish Date: August 2026
  • Dimensions: 10 x 7 x 0.42 inches
  • Shipping Weight: 0.77 pounds
  • Page Count: 196

Related Categories

You May Also Like...

    1

BAM Customer Reviews