Welcome to This Week in Neo4j, your weekly fix for news from the world of graph databases!
In this last edition of the newsletter, I want to look back at a few of our most-read blog posts across the year. We start with our overview on Graph Databases – not only worth a read for newcomers to the world of graphs! From there, we go to the dominating topics of the year: Knowledge Graphs, GenAI and Vector Search.
I wish you a Graphy New Year 2024,
COMING UP NEXT WEEK!
In this Graph Databases for Beginners blog series, we’ll take you through the basics of graph technology. We introduce you to graph databases with basic definitions and why those distinctions matter. The following segments touch on topics like Graph Data Modelling, Graph Theory, Graph Algorithms, Cypher Query Language, Native vs Non-Native Graph Databases and more.
In this article, Tomaz Bratanic discusses the limitations of Large Language Models (LLMs) and explores two approaches to enhance their performance: fine-tuning and retrieval-augmented generation. Fine-tuning involves supervised training with question-answer pairs to optimise the LLM’s performance. At the same time, retrieval-augmented generation uses external information sources to produce answers, offering advantages like source-citing and reduced hallucinations.
In this blog by Oskar Hane, Michael Hunger and Tomaz Bratanic, you will learn how to implement a support agent that relies on information from Stack Overflow by following best practices and using trusted components.
Earlier this year, we added Vector Search as a feature to Neo4j, which enables customers to use vector search to achieve richer insights from generative AI applications by understanding the meaning behind words rather than matching keywords. Sudhir Hasbe explains how you can get started with Vector Search on Neo4j.
TWEET OF THE WEEK: evin
Don’t forget to share it if you like it!