English | MP4 | AVC 1280×720 | AAC 44KHz 2ch | 13h 22m | 2.05 GB
Combine knowledge graphs with large language models to deliver powerful, reliable, and explainable AI solutions.
Knowledge graphs model relationships between the objects, events, situations, and concepts in your domain so you can readily identify important patterns in your own data and make better decisions. Paired up with large language models, they promise huge potential for working with structured and unstructured enterprise data, building recommendation systems, developing fraud detection mechanisms, delivering customer service chatbots, or more. This book provides tools and techniques for efficiently organizing data, modeling a knowledge graph, and incorporating KGs into the functioning of LLMs—and vice versa.
In Knowledge Graphs and LLMs in Action you will learn how to:
- Model knowledge graphs with an iterative top-down approach based in business needs
- Create a knowledge graph starting from ontologies, taxonomies, and structured data
- Build knowledge graphs from unstructured data sources using LLMs
- Use machine learning algorithms to complete your graphs and derive insights from it
- Reason on the knowledge graph and build KG-powered RAG systems for LLMs
In Knowledge Graphs and LLMs in Action, you’ll discover the theory of knowledge graphs then put them into practice with LLMs to build working intelligence systems. You’ll learn to create KGs from first principles, go hands-on to develop advisor applications for real-world domains like healthcare and finance, build retrieval augmented generation for LLMs, and more.
Using knowledge graphs with LLMs reduces hallucinations, enables explainable outputs, and supports better reasoning. By naturally encoding the relationships in your data, knowledge graphs help create AI systems that are more reliable and accurate, even for models that have limited domain knowledge.
Knowledge Graphs and LLMs in Action shows you how to introduce knowledge graphs constructed from structured and unstructured sources into LLM-powered applications and RAG pipelines. Real-world case studies for domain-specific applications—from healthcare to financial crime detection—illustrate how this powerful pairing works in practice. You’ll especially appreciate the expert insights on knowledge representation and reasoning strategies.
What’s Inside
- Design knowledge graphs for real-world needs
- Build KGs from structured and unstructured data
- Apply machine learning to enrich, complete, and analyze graphs
- Pair knowledge graphs with RAG systems
Table of Contents
1 Part 1. Foundations of hybrid intelligent systems
2 Chapter 1. Knowledge graphs and LLMs – A killer combination
3 Chapter 1. Large language models
4 Chapter 1. KGs and LLMs – Stronger together
5 Chapter 1. The paradigm shift in data-driven applications
6 Chapter 1. Building data-driven applications using KGs and LLMs
7 Chapter 1. Knowledge graph technologies
8 Chapter 1. How do we teach KGs and LLMs
9 Chapter 1. Summary
10 Chapter 2. Intelligent systems – A hybrid approach
11 Chapter 2. Designing an intelligent system
12 Chapter 2. Knowledge acquisition and representation
13 Chapter 2. Reasoning
14 Chapter 2. Reasoning engines
15 Chapter 2. A KG approach to IASs
16 Chapter 2. Summary
17 Part 2. Foundations of hybrid intelligent systems
18 Chapter 3. Create your first knowledge graph from ontologies
19 Chapter 3. Understanding knowledge graph technologies
20 Chapter 3. Building a knowledge graph
21 Chapter 3. Querying the data
22 Chapter 3. Reasoning over the KG
23 Chapter 3. Summary
24 Chapter 4. From simple networks to multisource integration
25 Chapter 4. Multi-omic applications of KGs
26 Chapter 4. Pharmaceutical applications of KGs
27 Chapter 4. Clinical applications of KGs
28 Chapter 4. Summary
29 Part 3. Building knowledge graphs from text
30 Chapter 5. Extracting domain-specific knowledge from unstructured data
31 Chapter 5. Key concepts of knowledge extraction
32 Chapter 5. Building KGs with large language models
33 Chapter 5. Summary
34 Chapter 6. Building knowledge graphs with large language models
35 Chapter 6. Intellectual network analysis – The value of graphs
36 Chapter 6. Next steps in the Rockefeller Archive Center project
37 Chapter 6. The value of knowledge graphs in the LLM era
38 Chapter 6. Summary
39 Chapter 7. Named entity disambiguation
40 Chapter 7. Understanding named entity disambiguation
41 Chapter 7. Domain-based NED and LLMs
42 Chapter 7. Business and domain understanding
43 Chapter 7. Understanding the data
44 Chapter 7. Building a SoHO knowledge graph
45 Chapter 7. KG-based use cases
46 Chapter 7. Summary
47 Chapter 8. NED with open LLMs and domain ontologies
48 Chapter 8. Ingesting the domain ontology
49 Chapter 8. Setting up the model with Ollama and Llama 3.1 8B
50 Chapter 8. End-to-end NED process
51 Chapter 8. Conclusions
52 Chapter 8. Summary
53 Part 4. Machine learning on knowledge graphs
54 Chapter 9. Machine learning on knowledge graphs – A primer approach
55 Chapter 9. Machine learning on graphs – What
56 Chapter 9. Machine learning on graphs – How
57 Chapter 9. Summary
58 Chapter 10. Graph feature engineering – Manual and semiautomated approaches
59 Chapter 10. Manual relationship features
60 Chapter 10. Semiautomated feature extraction
61 Chapter 10. Summary
62 Chapter 11. Graph representation learning and graph neural networks
63 Chapter 11. The encoder decoder model
64 Chapter 11. Shallow embeddings – A first approach to graph representation
65 Chapter 11. Embeddings in knowledge graphs
66 Chapter 11. Message passing and graph neural networks
67 Chapter 11. Generalized aggregation and update methods
68 Chapter 11. The synergy of GNNs and LLMs
69 Chapter 11. Summary
70 Chapter 12. Node classification and link prediction with GNNs
71 Chapter 12. Link prediction for movie recommendations
72 Chapter 12. Summary
73 Part 5. Information retrieval with knowledge graphs and LLMs
74 Chapter 13. Knowledge graph powered retrieval-augmented generation
75 Chapter 13. Chatting with the LLM
76 Chapter 13. Challenges in the production environment
77 Chapter 13. Chatting with the AI about private data
78 Chapter 13. Summary
79 Chapter 14. Asking a KG questions with natural language
80 Chapter 14. RAG for KG querying – Capabilities and challenges
81 Chapter 14. Schema-based approach for querying KGs
82 Chapter 14. Think like an expert – Using metadata for enhanced querying
83 Chapter 14. Intent detection – Understanding user expectations
84 Chapter 14. From schema to LLM-ready context
85 Chapter 14. It s time to think – Understanding LLM reasoning
86 Chapter 14. Response summarization – From results to insights
87 Chapter 14. Summary
88 Chapter 15. Building a QA agent with LangGraph
89 Chapter 15. Streamlit application
90 Chapter 15. Expert-emulating investigation
91 Chapter 15. Future directions and enhancements
92 Chapter 15. Summary
93 Appendix A. Introduction to graphs
94 Appendix A. Graphs as models of networks
95 Appendix A. Representing graphs
96 Appendix B. Neo4j
97 Appendix B. Installing Neo4j
98 Appendix B. Cypher
99 Appendix B. Installing plugins
100 Appendix B. Cleaning
101 Appendix C. Building knowledge graphs from structured sources
102 Appendix C. Building the miRNA knowledge graph
103 Appendix C. Exploring and analyzing the miRNA KG
Resolve the captcha to access the links!
