This Week in Neo4j: GenAI Stack, Chatbot, Active Directory, Podcast and more

Welcome to This Week in Neo4j, your weekly fix for news from the world of graph databases!
Wow, what a week! At DockerCon last week, Neo4j announced the formation of a GenAI Stack together with LangChain, Ollama and Docker. For a more hands-on approach, please read our blog below. There is currently a hackathon going on with 20k$ in prices. Also this week: creating a patent chatbot, better active directory management with graphs and a brand new episode of GraphStuff.FM just came out.

NODES 2023 is approaching and we finally have a keynote! We are excited to announce that Hannah Fry, Professor in the Mathematics of Cities at the Centre for Advanced Spatial Analysis at UCL, will be delivering this year’s NODES 2023 Opening Keynote on October 26: “The Joy of Data”. I cannot wait to hear this one!

I hope you enjoy this issue,
Alexander Erdl


Guido Thys studied General, Psycho- and Neurolinguistics and the Philosophy of Language. As a Lecturer in Strategy, Marketing and Database Management, he (co-)authored 20 books & dozens of articles on these subjects, wrote the (dBase-II) code for his first database in 1985 and has been at the forefront of database use ever since.
Connect with him on LinkedIn.

Join Guido at NODES 2023 where he introduces the “superconnector” – a knowledge graph designed to consolidate disparate data sources, enhancing accessibility for researchers. The project leverages graph databases and visualisation tools to address research complexities. He was also part of a NODES Speaker Roundtable and gave a little teaser of what to expect in his talk.

Guido Thys

GenAI STACK: GenAI Stack Walkthrough: Behind the Scenes With Neo4j, LangChain, and Ollama in Docker
In this blog, Michael Hunger, Tomaz Bratanic and Oskar Hane show you how to implement a support agent that relies on information from Stack Overflow by following best practices and using the GenAI Stack. They invite you to follow along to explore the approaches of using retrieval augmented generation (RAG) to improve accuracy, relevance, and provenance compared to relying on the internal knowledge of an LLM.
CHATBOT: Building an LLM Chatbot to Query a Neo4j Patents Database
Christopher Roberts was inspired to this blog by presentations with demos of a retrieval-augmented generation (RAG) system that queried a knowledge graph using natural language at GraphSummit Minneapolis. With his background in patent data, the logical thing to do was to build an RAG system on top of Neo4j database containing patent data.
ACTIVE DIRECTORY: How to Build Visual Organizational Charts Using Neo4j and LDAP Data from Active Directory

This blog provides a way to visualise your organisation and gather knowledge about the dynamics of it. It gives you all the steps necessary to do the same and comes with a GitLab repository.

PODCAST: NODES 2023 Preview with Melly Beechwood

This month, our Neo4j Developer Podcast is joined by the brilliant Melly Beechwood, a seasoned Machine Learning Engineer with a profound passion for data exploration and a unique mission in the realm of knowledge graphs. Get inspired as we delve into her fascinating work and her upcoming talk at NODES 2023.


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