Data overload, disconnected context, and stalled machine learning results are common frustrations for data teams. Even with vast datasets and advanced models, insights remain elusive when information is scattered and relationships are unclear. What if you could structure your data in a way that gives it meaning, connects the dots, and powers smarter, faster learning? By building knowledge graphs that integrate with large language models, you can transform disconnected information into actionable, context-rich intelligence that drives real results.
- Iterative top-down modeling: Aligns every graph decision with clear business questions.
- Ontology and taxonomy starters: Jump-start graph design from your existing structured data.
- Python code walk-throughs: Let you replicate techniques on day one, no guesswork.
- GNN and BERT integration: Upgrade graphs with deep learning for smarter reasoning and predictions.
- Real healthcare and policing cases: Prove scalability on messy, high-stakes datasets.
Knowledge Graphs and LLMs in Action by GraphAware scientists Dr. Alessandro Negro and colleagues delivers a code-rich softcover reference that unites cutting-edge research with field-tested engineering practice.
Starting with business questions, you model ontologies, import varied sources, then iteratively expand your graph. Later chapters layer GNNs, transformers, and reasoning algorithms, showing complete pipelines on full-scale datasets.
You will leave with repeatable workflows, reusable code, and the confidence to connect fragmented data into intelligent, context-aware applications. Stop guessing; start delivering measurable machine learning impact.
Table of Contents:
PART I: FOUNDATIONS OF HYBRID INTELLIGENT SYSTEMS
1 KNOWLEDGE GRAPHS AND LLMS: A KILLER COMBINATION
2 INTELLIGENT SYSTEMS: A HYBRID APPROACH
PART II: BUILDING KNOWLEDGE GRAPHS FROM STRUCTURED DATA SOURCES
3 CREATE YOUR FIRST KNOWLEDGE GRAPH FROM ONTOLOGIES
4 FROM SIMPLE NETWORKS TO MULTI-SOURCE INTEGRATION
PART III: BUILDING KNOWLEDGE GRAPHS FROM TEXT
5 DOMAIN-SPECIFIC KNOWLEDGE EXTRACTION FROM UNSTRUCTURED DATA
6 BUILDING KNOWLEDGE GRAPHS WITH LARGE LANGUAGE MODELS
7 NAMED ENTITY DISAMBIGUATION
8 NED WITH OPEN LLMS AND DOMAIN ONTOLOGIES
9 MACHINE LEARNING ON KNOWLEDGE GRAPHS: A PRIMER APPROACH
PART IV: MACHINE LEARNING ON KNOWLEDGE GRAPHS
10 GRAPH FEATURE ENGINEERING: MANUAL AND SEMI-AUTOMATED APPROACHES
11 GRAPH REPRESENTATION LEARNING AND GRAPH NEURAL NETWORK
12 NODE CLASSIFICATION AND LINK PREDICTION WITH GNNS
13 KNOWLEDGE GRAPH-POWERED RETRIEVAL AUGMENTED GENERATION
PART V: INFORMATION RETRIEVAL WITH KNOWLEDGE GRAPHS AND LLMS
14 ASK A KG WITH NATURAL LANGUAGE
15 BUILDING AQA AGENT WITH LANGGRAPH
APPENDIXES
APPENDIX A: INTRODUCTION TO GRAPHS
APPENDIX B: NEO4J
APPENDIX C: BUILD KNOWLEDGE GRAPHS FROM STRUCTURED SOURCES
