Graph-RAG Engineering: Integrating Knowledge Graphs with LLMs for Context-Aware AI: Design Patterns, Graph Modeling, SPARQL & Neo4j Workflows, and ... Systems, LangFlow, RAG, and Knowledge-Graph) - Tapa blanda

Sinopsis

Graph-RAG Engineering shows how to combine structured knowledge from Knowledge Graphs with Large Language Models to build context-aware, explainable, and high-precision AI applications. The book covers graph modeling (RDF, property graphs), building and maintaining knowledge graphs with Neo4j/RDFLib, querying with SPARQL and Cypher, and creating Graph-RAG pipelines that fuse graph retrieval with dense vector search. Learn multi-hop reasoning, graph neural networks (GNN) for link prediction and entity disambiguation, temporal and streaming graph updates, and strategies for keeping graphs consistent and fresh. Practical projects include personalized recommendation systems, scientific discovery assistants, legal & regulatory search, and enterprise knowledge hubs. The book also addresses schema design, entity linking, provenance, versioning, and production considerations (ETL, connectors, monitoring).
Key topics: knowledge graph design, Neo4j/Cypher, RDF/SPARQL, entity linking & canonicalization, Graph-RAG fusion, vector + graph hybrid retrieval, GNNs, temporal graphs, production ETL & governance.

"Sinopsis" puede pertenecer a otra edición de este libro.