This Week in Neo4j: LLM, Vectors, Recommendations, Knowledge Graphs and more


Welcome to This Week in Neo4j, your weekly fix for news from the world of graph databases!
Are you back in full swing or still reminiscing about that mulled wine? Did you make any New Year’s resolutions? This edition might inspire you by featuring a new course on building recommendations with Spring Boot. Additionally, we have LLMs, Vectors and Knowledge Graphs.

And if you are new to this whole graph thing, welcome! Starting with this edition, I am collecting a few interesting links below to kickstart your journey.

Join our Neo4j 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!

I hope you enjoy this issue,
Alexander Erdl

 
COMING UP NEXT WEEK!
GETTING STARTED WITH GRAPHS

Friedrich Lindenberg is the Founder of OpenSanctions, a database of persons of interest data – sanctioned companies and people, politicians, and wanted criminals – used for compliance and know-your-customer checks.
Connect with him on LinkedIn.

In his session at NODES “Follow the Money: A Graph Ontology for Anti-Corruption Investigations” Friedrich introduces a toolchain of Python-based graph processing utilities used by investigative journalists and due diligence professionals to track illicit funds, identify persons of interest, and connect the dots in vast datasets of financial, corporate, and criminal network information.


Friedrich Lindenberg

 
LLM: How to build knowledge graphs with large language models (LLMs)

In this guide, Julian Horsey gives an overview of important things to consider when building Knowledge Graphs. Combining graph databases and advanced language models transforms how we handle and analyse data. The guide includes further reading material and videos to watch.
 
VECTORS: Why Vector Search Didn’t Work for Your RAG Solution?
External knowledge is the key to resolving the problems of LLMs, such as hallucinations and outdated knowledge. And even with RAG, they sometimes don’t respond as expected. By analysing real-world examples, this article by Fanghua (Joshua) Yu demonstrates several categories where these limitations manifest, leading to inaccuracies in LLM-generated content.
   
RECOMMENDATIONS: Music Recommendation Backend with Spring Boot and Neo4j
This new course by Marshall Takudzwa Chabanga teaches you how to build a Music Recommendation Backend with Spring Boot, Neo4j, Spring Cloud, and Collaborative Filtering.
KNOWLEDGE GRAPH: The Challenges of Virtual Knowledge Graphs

Jeff Tallman muses on the history of data virtualisation. He discusses the challenges associated with virtual knowledge graphs, focusing on their implementation and the difficulties in achieving successful real-world applications.

TWEET OF THE WEEK: Tomaz Bratanic


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