This Week in Neo4j: NODES, GraphRAG, Agents, Knowledge Graph and more

Senior Developer Marketing Manager

April 12, 2025

3 min read

Welcome to This Week in Neo4j, your fix for news from the world of graph databases!

I am very excited that the call for papers for NODES 2025 is now open! NODES is such a fantastic event with interesting sessions all day! If you have a graphy story to tell, please do submit!
In addition, this week we combine GraphRAG with fine-tuned Graph Neural Networks, structure legal contracts as a knowledge graph with agents and look at a temporally aware knowledge graph memory layer built on Neo4j.

Join our Neo4j User Research panel! Sign up to share your experiences with a researcher and influence the future of Neo4j products.
What’s in it for you? A chance to connect directly with product development teams, get paid compensation, hear about what we are working on, and more!

Happy Graphing,

Alexander Erdl

COMING UP!

Livestream: Discover AuraDB: S02E02 on April 14 & Neo4j Live: Advancing GraphRAG: Text, Images and Audio for Multimodal Intelligence on April 16
Conferences: Find us at JAX, Mainz on May 5-9 & Data Innovation Summit, Stockholm on May 7-8
Meetup: Meet us in Atlanta, US on April 15 & Atlanta, US on April 16
All Neo4j Events: Webinars and More
GraphSummit Series: Transform Your Enterprise with Graph and GenAI – Next Stop: Singapore on May 20

FEATURED COMMUNITY MEMBER: Leonie Engemann

Leonie is studying geoinformatics and doing her PhD at the Chair of Production & Supply Chain Management. She is a big data nerd and feels it’s a shame that most spatial graphs are limited to just a few coordinates or addresses.

Connect with her on LinkedIn.

In her session at NODES 2024 “Enhancing Supply Chain Resilience and Transparency Through Spatial Knowledge Graphs”, Leonie integrated geospatial data and environmental risk assessments to enhance transparency and resilience in supply chains. She highlights improved strategic decision-making and the ability to model complex relationships.

GRAPHRAG: Boosting Q&A Accuracy with GraphRAG Using PyG and Graph Databases

Brian Shi, Alfred Clemedtson, Zach Blumenfeld and Rishi Puri’s tutorial demonstrates how integrating GraphRAG with fine-tuned Graph Neural Networks (GNNs) and Large Language Models (LLMs) can double the accuracy of domain-specific question answering compared to standard baselines. This approach is particularly effective for complex queries requiring multi-hop reasoning and access to proprietary data.

NODES: Announcing NODES 2025: Submit Your Talk

NODES 2024 welcomed more than 12,000 graph enthusiasts who watched over 140 live sessions by 170 speakers from 30 countries. Will you be part of it in 2025? The Call for Papers is open now through June 15, 2025. Submit an abstract of your educational presentation demonstrating Neo4j-related technologies, focusing on building solutions through code, data modelling, Cypher, best practices or integrations.

AGENTS: Agentic GraphRAG for Commercial Contracts

Tomaz Bratanic shows how structuring legal contracts as a knowledge graph enables an Agentic GraphRAG system to deliver precise, context-aware answers and streamline contract analysis.

KNOWLEDGE GRAPH: Graphiti: Knowledge Graph Memory for a Post-RAG Agentic World

Daniel Chalef introduces Zep AI’s Graphiti framework, which provides a real-time, temporally aware knowledge graph memory layer built on Neo4j, designed to enhance autonomous AI agents by enabling dynamic, context-rich interactions and efficient data retrieval.

CONTINUOUS LEARNING

GraphAcademy: Importing Data Fundamentals: Learn how to turn raw data into a fully functional Neo4j graph – fast, flexible and optimised for powerful queries
Get to Know Graph: Level up your graph skills with webinars packed with practical insights to help you build powerful apps
Learn on Your Schedule: Go deeper into graph technology on Neo4j’s On-Demand webinar library
New Webinar: Explainable AI With Knowledge Graphs and RAG – AMER, EMEA, Asia Pacific