Build a Reasoning Model (From Scratch)
Sebastian Raschka
Description A deep dive into the architecture and implementation of AI models capable of logical deduction and multi-step reasoning. It explains how t...
Knowledge Graphs and LLMs in Action
Alessandro Negro, Vlastimil Kus, Giuseppe Futia, Fabio Montagna
Book Metadata
Publisher
Simon and Schuster
Duration
13 hr 5 min
ISBN
9781633439894
Genres
Computers
About This Book
Description A technical manual on integrating knowledge graphs with Large Language Models (LLMs) to create intelligent systems with structured reasoning capabilities. It details how to leverage the connected nature of data to improve the accuracy of AI-driven decisions. Key Topics: Knowledge graph modeling, building graphs from unstructured data using LLMs, KG-powered Retrieval-Augmented Generation (RAG), and using machine learning to complete graph data. About the Technology: Knowledge graphs represent relationships between objects and concepts, providing a factual anchor for LLMs. This combination is used in critical domains like healthcare, finance, and law enforcement. About the Book: The text provides an iterative approach to modeling knowledge graphs based on business needs, accompanied by code samples and real-world use cases for building "intelligent advisor" applications. About the Reader: For data scientists, engineers, and researchers interested in graph technologies and advanced RAG architectures. About the Author: Alessandro Negro, Vlastimil Kus, Giuseppe Futia, and Fabio Montagna are specialists in graph analytics and machine learning.
AI Summary
Knowledge Graphs and LLMs in Action is a practical guide that teaches data scientists and engineers how to build knowledge graphs from raw text with large language models and then use those graphs for Retrieval‑Augmented Generation and structured reasoning, backed by real code and industry case studies.
Technical Reference
Summary
Knowledge Graphs and LLMs in Action is a practical guide that teaches data scientists and engineers how to build knowledge graphs from raw text with large language models and then use those graphs for Retrieval‑Augmented Generation and structured reasoning, backed by real code and industry case studies.
Key Themes
- Graph modeling from unstructured data using LLMs
- KG‑enhanced Retrieval‑Augmented Generation
- Iterative, business‑driven KG design process
- Machine‑learning methods for graph completion
Ideal Reader
Data scientists, machine‑learning engineers, and researchers who need to add factual grounding and structured reasoning to AI applications.
Details
styletechnical but example‑driven with code snippets and diagrams
levelintermediate-to-expert
commitmentdeep‑dive reference guide
Why It Matters
By uniting LLMs with knowledge graphs, the book provides a reproducible path to trustworthy AI systems that can reason over structured facts, a capability still rare in mainstream LLM literature.
Related Reading
Graph Neural Networks – Lingfei Wu et al.Designing Data‑Intensive Applications – Martin KleppmannLangChain documentation and tutorialsRetrieval‑Augmented Generation for Knowledge‑Intensive NLP Tasks – Patrick von Platen
auto-generated