Developing applications knowledge graphs par carlson abe (5 résultats)

PAP. Etat : New. New Book. Shipped from UK. Established seller since 2000.

PAP. Etat : New. New Book. Shipped from UK. Established seller since 2000.

Taschenbuch. Etat : Neu. Neuware - No more prompts. Begin grounding. Large Language Models have changed the way we interact with machines, but they have a fatal flaw for enterprise applications: they rely on statistical probability, not deterministic truth. They hallucinate facts, struggle with multi-hop reasoning, and don't have the structured logic necessary for mission-critical systems. Standard vector-based Retrieval-Augmented Generation (RAG) attempts to remedy this, but viewing data as a flat ocean of semantic similarity is not enough. To build AI that actually knows, AI that is verifiable, explainable, and trustworthy, you must move from flat data to interconnected data. You want knowledge graph. This is your architectural blueprint for the next 10 years of artificial intelligence. This book will teach you how to build neuro-symbolic artificial intelligence systems that bridge the gap between deep learning and semantic web technologies, bringing the linguistic fluency of LLMs together with the rigorous, deterministic logic of Knowledge Graphs. Whether you're trying to remove hallucinations from your company's internal chatbot or designing autonomous AI agents that can handle complex enterprise data, this book provides the theoretical foundation and the production-ready code you need to succeed.- What You'll LearnGraph Data Foundations: Understand domain-driven design for scalable ontologies, and transform messy data into structured graph databases. Automated Knowledge Extraction Use LLMs, Named Entity Recognition (NER) and relationship extraction to automatically build Knowledge Graphs from unstructured text, PDFs and documents. GraphRAG: Go beyond traditional vector search. Design hybrid retrieval pipelines enabling true multi-hop reasoning using semantic embeddings and topological graph traversal. Machine Learning on Graphs: Leverage Graph Neural Networks (GNNs), node classification, and link prediction to discover hidden insights and structural patterns your LLM cannot infer itself. Create Autonomous AI Agents: Build end-to-end agents that leverage your Knowledge Graph as a map of the environment to drive memory, multi-step planning and autonomous decision-making. Production Deployment: Scale, secure, and govern knowledge-aware artificial intelligence systems in an enterprise setting.- Who This Book Is ForThis book is written for software engineers, data scientists, AI researchers, and technical architects ready to take their work beyond simple API wrappers. If you know Python, and understand databases and LLMs at a basic level, you have all you need to start building intelligent, graph-powered systems. The future of AI is not strictly neural. It's neuro-symbolic. Learn to build systems that don't just talk, but understand.…

Etat : New. Print on Demand.

Paperback. Etat : new. Paperback. No more prompts. Begin grounding. Large Language Models have changed the way we interact with machines, but they have a fatal flaw for enterprise applications: they rely on statistical probability, not deterministic truth. They hallucinate facts, struggle with multi-hop reasoning, and don't have the structured logic necessary for mission-critical systems. Standard vector-based Retrieval-Augmented Generation (RAG) attempts to remedy this, but viewing data as a flat ocean of semantic similarity is not enough. To build AI that actually knows, AI that is verifiable, explainable, and trustworthy, you must move from flat data to interconnected data. You want knowledge graph. This is your architectural blueprint for the next 10 years of artificial intelligence. This book will teach you how to build neuro-symbolic artificial intelligence systems that bridge the gap between deep learning and semantic web technologies, bringing the linguistic fluency of LLMs together with the rigorous, deterministic logic of Knowledge Graphs. Whether you're trying to remove hallucinations from your company's internal chatbot or designing autonomous AI agents that can handle complex enterprise data, this book provides the theoretical foundation and the production-ready code you need to succeed.What You'll LearnGraph Data Foundations: Understand domain-driven design for scalable ontologies, and transform messy data into structured graph databases. Automated Knowledge Extraction Use LLMs, Named Entity Recognition (NER) and relationship extraction to automatically build Knowledge Graphs from unstructured text, PDFs and documents. GraphRAG: Go beyond traditional vector search. Design hybrid retrieval pipelines enabling true multi-hop reasoning using semantic embeddings and topological graph traversal. Machine Learning on Graphs: Leverage Graph Neural Networks (GNNs), node classification, and link prediction to discover hidden insights and structural patterns your LLM cannot infer itself. Create Autonomous AI Agents: Build end-to-end agents that leverage your Knowledge Graph as a map of the environment to drive memory, multi-step planning and autonomous decision-making. Production Deployment: Scale, secure, and govern knowledge-aware artificial intelligence systems in an enterprise setting.Who This Book Is ForThis book is written for software engineers, data scientists, AI researchers, and technical architects ready to take their work beyond simple API wrappers. If you know Python, and understand databases and LLMs at a basic level, you have all you need to start building intelligent, graph-powered systems. The future of AI is not strictly neural. It's neuro-symbolic. Learn to build systems that don't just talk, but understand. This item is printed on demand. Shipping may be from our UK warehouse or from our Australian or US warehouses, depending on stock availability.…