Skip to content

Booksellers & Trade Customers: Sign up for online bulk buying at trade.atlanticbooks.com for wholesale discounts

Booksellers: Create Account on our B2B Portal for wholesale discounts

Applied Knowledge Graphs for LLMs: Design, Integration and Semantic Retrieval: Knowledge modeling, KG vector pipelines, entity linking, schema design,

by Marcus Endo
Sold out
₹2,090.00
Original price ₹2,090.00
Original price ₹2,090.00
₹2,090.00
Current price ₹2,090.00

Imported Edition - Ships in 18-21 Days

Free Shipping in India on orders above Rs. 500

Request Bulk Quantity Quote
+91
Book cover type: Paperback
  • ISBN13: 9798264969980
  • Binding: Paperback
  • Subject: N/A
  • Publisher: Independently Published
  • Publisher Imprint: Independently Published
  • Publication Date:
  • Pages: 368
  • Original Price: USD 20.0
  • Language: English
  • Edition: N/A
  • Item Weight: 635 grams
  • BISAC Subject(s): Artificial Intelligence / Expert Systems

This book is a practical and example rich guide to combining knowledge graphs with large language models to achieve explainability, provenance, and updatability. It covers ontology and schema design, triple modeling, entity resolution and linking, knowledge graph embeddings, conversion pipelines from graph triples to vector stores, hybrid retrieval using symbolic and semantic approaches, and strategies for fact verification and provenance tracking in retrieval augmented generation systems.

Who this book is for: knowledge engineers, data architects, and natural language processing engineers building semantic systems. Enterprise search and knowledge management teams seeking explainable retrieval. Product teams needing provenance and factual grounding for large language model outputs.

What the reader will learn: how to design and model ontologies and entity schemas for domain knowledge. Pipelines to extract knowledge graph triples from documents and update them incrementally. Techniques for entity linking, disambiguation, and canonicalization. How to build knowledge graph embeddings and convert graph signals into vectorized retrieval. Hybrid retrieval strategies that combine knowledge graph rules with vector similarity and reranking. Methods to provide provenance and verifiable outputs inside retrieval augmented generation flows.

Trusted for over 49 years

Family Owned Company

Secure Payment

All Major Credit Cards/Debit Cards/UPI & More Accepted

New & Authentic Products

India's Largest Distributor

Need Support?

Whatsapp Us