Golem XIV uses Neo4j as its core graph engine to dynamically extract, connect, and reason over data — showing how code can become a cognitive tool for metacognitive AI.

Discussion on graph databases in big data contexts and when/why to use Neo4j.

Relational SQL databases remain the winner when it comes to optimal and structured data storage and management. However, as data storage needs become more complex, especially with the rise of AI, NoSQL databases are making waves. NoSQL (Not-Only-SQL) is a powerful alternative, excelling at handling large volumes of unstructured, non-relational data and offering flexible data structures for ever-evolving schemas. In this session, we will explore the basics and core concepts of different types of NoSQL databases, such as document stores, key-value stores, and graph databases. We’ll discuss the ideal use cases and best practices for each store, their unique strengths, and how they compare to traditional relational databases in various scenarios. We will also cover practical examples, such as using graph databases for more efficient retrieval in AI applications, or leveraging document stores for storing and querying raw logs. By the end of the session, attendees will be equipped with the knowledge required to implement NoSQL data storage in Azure, as well as being able to make informed decisions about when and where to implement NoSQL databases. While NoSQL is not always the answer, choosing the right data store will always ensure scalability and performance for your data solutions.

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.

Using Neo4j and Spring AI to build intelligent music applications.

Exploration of AI agents and GraphRAG in platform engineering.

Discussion on applying Neo4j Graph Data Technology to predict and mitigate supply chain risks.

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.

Jian Huang speaks on GraphQL+Graph databases usage and how we leverage Kafka, Elastic Search, Hackolade together.

In this session, we’ll show how to turn SurrealDB into a long-term memory layer for your LLM apps, combining graph and vector data to power richer context, better decisions. We’ll walk through practical patterns and show how SurrealDB collapses graph, vector, and relational data into a single memory substrate for next-gen AI.

How do you detect suspicious activity across seemingly unrelated transactions?\n\nJoin us at the next SurrealDB London Meetup for a deep dive into how graph and vector capabilities can help financial institutions spot transaction fraud rings, surface anomalous behaviours, and enhance fraud detection efforts.\n\nIn this session, you’ll learn:\n\n How to model financial transactions and entities using SurrealDB’s graph features\n How a multi-model structure enhances pattern detection and fraud analysis\n* Why these capabilities matter in real-world FinServ systems\n\nWhether you’re working in fraud detection, anti-money laundering, risk analysis or data architecture, this meetup is built to equip you with ideas and tools for building smarter, more connected systems.\n\nDrinks and networking after the talk — we hope to see you there!