This Week in Neo4j: NODES, Retrievers, Graph Analytics, Agents and more

Photo of Alexander Erdl

Alexander Erdl

Senior Developer Marketing Manager

4 min read

Samira Korani

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

After months of preparation, NODES 2025 unfolded in a flurry of excitement around Graphs and AI, featuring sessions from customers, community members and the Neo4j team. I am still buzzing from the day. Some videos are already available for you to watch, and we will add the rest soon.
Additionally, this edition invites you to explore DRIFT search with Neo4j and LlamaIndex, analyse patient journeys with Aura Graph Analytics, and build agentic workflows that construct knowledge graphs autonomously.

And while we have just finished NODES 2025, we are already preparing for the next one. The Call for Papers for NODES AI is open: On April 15, practitioners will gather virtually to explore AI, context engineering, and intelligent agents.

Happy Graphing,

Alexander Erdl

 

COMING UP!

Samira Korani is an AI and NLP expert, as well as the co-founder of tripoh.ie, a travel startup that utilises AI and knowledge graphs for personalised recommendations.

Connect with her on LinkedIn.

Samira delivered one of the sessions that was live-streamed from NODES2025: “Building Contextual Knowledge Graphs to Adapt, Evaluate, and Leverage LLMs”. She shared how she built contextual knowledge graphs by combining diverse datasets like Geonames, OpenStreetMap, Yelp, and Wikidata. These graphs were designed to enrich LLMs with real-world context, enabling more relevant and grounded outputs.​


Samira Korani

 

NODES: Watch Sessions


What an event! On November 6, all eyes were on graph at NODES2025. Our tracks “AI Engineering, App Dev, Data Intelligence & Knowledge Graphs” had mindblowing session all day long. We are currently getting the recordings ready and will add them to our NODES 2025 playlist on YouTube as soon as we can. We streamed a few sessions live (including the one mentioned above) – so if you missed the day, you can start watching now!

 

RETRIEVERS: Implementing DRIFT Search with Neo4j and LlamaIndex


In this article, Tomaz Bratanic demonstrates how to implement a “DRIFT” search workflow using LlamaIndex and Neo4j – starting with vector-based community summaries and then drilling down into detailed graph-based retrieval via Cypher queries. He shows how combining broad semantic embeddings with relationship-aware graph traversal elevates retrieval accuracy and context for complex document corpora.

 

GRAPH ANALYTICS: Find Similar Patient Journeys With Neo4j Aura Graph Analytics


This article by Corydon Baylor explores how to model patient treatment trajectories as graphs in Neo4j Aura Graph Analytics and then apply algorithms such as node similarity and community detection to identify patients with similar care paths and group them into actionable cohorts.

 

AGENTS: Agentic Knowledge Graph Construction


This course from Andreas Kollegger teaches you how to build intelligent, multi-agent workflows that automatically extract, link, and structure entities into knowledge graphs. You’ll learn to move beyond simple RAG setups – designing agents to parse data, propose graph schemas, and load graphs into Neo4j for more accurate, contextual retrieval.

 

 

POST OF THE WEEK: Isuru Alagiyawanna



Please share it if you like it!

Share Article

Explore

Why Startups in the Google Ecosystem Choose Neo4j


4 min read

Andrew Ng

This Week in Neo4j: Context Engineering, Chunking, Cypher, Aura and more


3 min read

A constellation of Orion represented as a graph with nodes and relationships.

Advanced RAG Techniques for High-Performance LLM Applications


17 min read

Analyze Graphs Directly in Snowflake — The Wait Is Over


14 min read

Isaac Ritharson

This Week in Neo4j: Aura Agents, Fraud, Langchain, AI Memory and more


4 min read

Production-Proofing Your Neo4j Cypher MCP Server


7 min read