← back
Practical GraphRAG: Making LLMs smarter with Knowledge Graphs — Michael, Jesus, and Stephen, Neo4j
Takeaway
For enterprise RAG, build a knowledge graph alongside vectors — combining lexical, domain, and graph algorithms produces more grounded, explainable answers.
Summary
- Neo4j team (co-authors of the O'Reilly Graph RAG book) argues vector RAG is incomplete: similarity != relevance, results lack explainability and miss enterprise context.
- GraphRAG construction: unstructured docs -> lexical graph (documents/chunks) -> entity extraction via LLM with schema -> graph algorithms (PageRank, community summarization) for enrichment.
- Cites Microsoft Research GraphRAG paper, data.world study showing 3x accuracy improvement, and LinkedIn customer-support paper reporting 28.6% reduction in median per-issue resolution time.
- Showcases pattern catalog at graphpatterns.com covering local/global search and combined lexical+domain graph queries.
graphragknowledge-graphsneo4j
Original description
RAG has become one standard architecture component for GenAI applications to address hallucinations and integrate factual knowledge. While vector search over text is common, knowledge graphs represent a proven advancement by leveraging advanced RAG patterns to access and integrate interconnected factual information, complementing the language skills of LLMs. This talk explores GraphRAG challenges, implementation patterns, and real-world agentic examples with Google's ADK, demonstrating how this approach delivers more trustworthy and explainable GenAI solutions with enhanced reasoning capabilities. About Michael Hunger Michael Hunger has been passionate about software development for more than 30 years. For the last 15 years, he has been working on the open source Neo4j graph database filling many roles, most recently heading product innovation and GenAI. As a developer Michael enjoys many aspects of software development and architecture, learning new things every day, participating in exciting and ambitious open source projects and contributing and writing software related books and articles. Michael spoke at numerous conferences and helped organize others. Michael helps kids to learn to program by running weekly girls-only coding classes at local schools. About Jesús Barrasa Dr. Jesús Barrasa is the AI Field CTO at Neo4j, where he works with organisations combining the power of GenAI with Knowledge Graphs. He co-authored "Building Knowledge Graphs" (O'Reilly 2023) and is cohost of the monthly Going Meta live webcast (https://goingmeta.live/) since 2022. Jesús holds a Ph.D. in Artificial Intelligence/Knowledge Representation and is an active thought leader in the KG and AI space. About Stephen Chin Stephen Chin is VP of Developer Relations at Neo4j, conference chair of the LF AI & Data Foundation, and author of numerous titles including the upcoming GraphRAG: The Definitive Guide for O'Reilly. He has given keynotes and main stage talks at numerous conferences around the world including AI Engineer Summit, AI DevSummit, Devoxx, DevNexus, JNation, JavaOne, Shift, Joker, swampUP, and GIDS. Stephen is an avid motorcyclist who has done evangelism tours in Europe, Japan, and Brazil, interviewing developers in their natural habitat. When he is not traveling, he enjoys teaching kids how to do AI, embedded, and robot programming together with his daughters. Recorded at the AI Engineer World's Fair in San Francisco. Stay up to date on our upcoming events and content by joining our newsletter here: https://www.ai.engineer/newsletter