This Week in Neo4j: Vectors, Cypher, Geospatial, DFIR and more

Welcome to This Week in Neo4j, your weekly fix for news from the world of graph databases!
Once again, we are looking at the combination of Vector Search, OpenAI, LangChain and Neo4j, but this issue also brings you interesting posts on Cypher Improvements since Neo4j 5, we are getting hands-on with geospatial data and exploring digital forensics with graphs.

There is only one month to go till NODES 2023! On 5th and 10th October we are also conducting the final two Road to NODES workshops: GenAI & Geospatial Data. Will you be there?

I hope you enjoy this issue,
Alexander Erdl


Tomaz loves to work with graphs and writes about various graph analytics approaches in his blog. He is very excited about the intersection of ML and Graph technologies.
Connect with him on LinkedIn.

Join him at NODES 2023 where Tomaz will demonstrate how using a knowledge graph as a storage object for answers gives you explicit and complete control over the answers provided by the chatbot and helps avoid hallucinations.

Tomaz Bratanic

VECTORS: Explore OpenAI vector embedding with Neo4j, LangChain, and Wikipedia
Rob Brennan shares this write-up of his experience during a hackathon exploring AI and Large Language Models (LLMs) possibilities, how Neo4j works with vector embedding and the creation of a demo Retrieval-Augmented Generation (RAG) project.
CYPHER: Did You Take the Neo4j 5 Cypher Bullet Train?
Pierre Halftermeyer compares, in a real use case, the performance of two queries doing the same job. Neo4j 5 introduced many improvements to Cypher, and he is looking at changes, particularly with COUNT{<subquery>} (since 5.0) and Graph Pattern Matching with Quantified Path Patterns (since 5.9)
GEOSPATIAL: Importing Overture Maps Data Into Neo4j

In this article, Will Lyon looks at the recently released public map dataset from the Overture Maps Foundation and how to import the map data into a Neo4j graph database. From here, he uses low-code tooling to create a dashboard using the Neodash graph app and GraphQL API using the Neo4j GraphQL Toolbox.

Digital Forensics and Incident Response: Graphs for DFIR Analysis. The Roadmap

At the start of this series, Mario Pérez shows that graphs can organise and represent DFIR artefacts such as network traffic or system events very well and are a powerful tool for Thread Hunting and Incident Response operations. Graph analysis enables agile access to data and the ability to pivot between different source types, reducing response times.

TWEET OF THE WEEK: Thomas Banafa

Don’t forget to share it if you like it!