Large Language Models (LLMs) are powerful but notoriously ungrounded as they generate fluent, plausible text that isn’t always factual, consistent, or explainable. One promising way to address these issues is by connecting LLMs with Knowledge Graphs, namely structured, explicit representations of knowledge that can provide context, constraints, and verifiable facts. The main paradigm for doing this is Graph-based Retrieval-Augmented Generation (GraphRAG), which integrates graph-based reasoning and retrieval into the generation process. In this talk, I’ll introduce the core ideas behind GraphRAG, describe common design patterns, and outline the steps and tools needed to implement such systems in practice.

Davide Poggiali will give an introduction to GraphRAG, showing how to represent your dataset in a graph system and implement a RAG system that combines semantic and relational information.

Exploration of AI agents and GraphRAG in platform engineering.

Revolutionizing Platform Engineering with AI Agents and GraphRAG

In this talk, you will learn about GraphRAG, a technique that combines graph databases with generative AI to improve the quality of LLM-generated content. We will explore the terms Retrieval-Augmented Generation (RAG) and Context Engineering, and how GraphRAG can be used in both scenarios. The topic is aimed at Generative AI practitioners who are familiar with vector-based Retrieval-Augmented Generation (RAG) and would like to understand how the approach of GraphRAG can improve the quality of LLM-generated content.

Learn how to combine graph and vector search to build smarter GenAI features using SurrealDB and LangChain, including how to analyse symptoms and suggest scheduling appointments based on semantic similarity and graph relationships.

A session showing how to build smarter AI-powered apps by combining SurrealDB's graph and vector capabilities with LangChain. We'll walk through a complete example: a chatbot that analyses symptoms and recommends appointment scheduling based on semantic similarity and structured graph relationships. Learn how to set up SurrealDB as both a graph and vector store in a single system, use LangChain to query structured knowledge alongside embeddings, chain together document ingestion, graph construction, and AI-driven Q&A, and deploy an architecture that scales from prototype to production.

In this hands-on workshop, you will learn how Knowledge Graphs and Retrieval Augmented Generation (RAG) can help GenAI projects avoid hallucination and provide access to reliable data. Topics include LLMs and hallucination, integrating knowledge graphs, GraphRAG, vector indexes and embeddings, querying graphs with natural language, and using Python and OpenAI to create GraphRAG retrievers and GenAI applications.

Entdecke, wie GraphRAG, Neo4j und KI Agenten zusammenarbeiten, um intelligentere Datenabfragen und dynamische KI-Anwendungen zu ermöglichen. Beginnend mit einer Einführung, zeigen wir dann eine spannende Live-Demo mit praxisnahen Einblicken in GraphRAG-Workflows mit Neo4j.

Measuring the performance of VectorRAG vs GraphRAG in knowledge graph contexts.

As you might have experienced, LLMs are powerful but not always trustworthy assistants. With a combination of a knowledge graph and vector search, you can provide the LLM with the correct, relevant context information it needs to answer your user's questions. GraphRAG is an advanced RAG (retrieval augmented generation) pattern in the Haystack-Neo4j integration. In this talk, we'll explain and demonstrate the building blocks of such an approach and show an example of code and live in action. Of course, nothing is perfect; it's important to walk through the challenges of building such GenAI apps and how to address them.

Bien que la GenAI offre un grand potentiel, elle est confrontée aux défis de l’hallucination et de la connaissance limitée du domaine. La génération augmentée de recherche alimentée par les graphes (GraphRAG) aide à surmonter ces défis en intégrant la recherche vectorielle aux graphes de connaissances et aux techniques de data science. Cette approche améliore le contexte, la compréhension sémantique, la personnalisation et les mises à jour en temps réel. Dans cet atelier, vous explorerez des exemples de code détaillés pour vous lancer avec la GenAI et les graphes. Vous repartirez avec des compétences pratiques que vous pourrez immédiatement appliquer à vos propres projets.