This Week in Neo4j: SSO, Chatbots, Vector Search, Knowledge Graphs and more

Welcome to This Week in Neo4j, your weekly fix for news from the world of graph databases!
Hope you didn’t miss the exciting news about Vector Search last week! Sticking with the topic, this week continues with lots of interesting articles around Chatbots, LLMs and (of course) Vectors.

We need your help! Neo4j is looking for participants for our research group. Everybody is invited – no matter your experience with Neo4j (or lack of).
If you have any feedback 🗣️ for this newsletter, I’d be very interested to hear it. Just jump over to our Community Forum or Discord Server and feel free to @tag me in your posts!

I hope you enjoy this issue,
Alexander Erdl


Gal is an Applied Research Team Lead at Accenture Israel Cyber R&D Lab. He is an experienced data scientist with a demonstrated history of converting data into actions and building cutting-edge technologies across various industries, especially in the cybersecurity space.
His recent research projects focused on the use of knowledge graphs, graph data science algorithms, and process-mining techniques to infer what is the business impact of cyber attacks on organizations. Gal enjoys watching Netflix, reading books, listening to political podcasts, and spending quality time with his family. Connect with him on LinkedIn.

Join him at NODES 2023 where he will generate countermeasures to cyberattacks with LLMs & Knowledge Graphs.

Gal Engelberg

SSO: How to Integrate Neo4j With SSO on Azure
Morgan Senechal guides us through everything we need to know to configure and access a Neo4j graph with SSO authentication and authorization for both user applications (Neo4j Browser, Bloom, Neodash, …) as well as a backend service (which can be your ETL pipeline, GDS batches, etc.).
CHATBOT: Building an Educational Chatbot for GraphAcademy with Neo4j Using LLMs and Vector Search
Imagine using the content from GraphAcademy and the Neo4j Documentation to train an educational chatbot for user support. That’s an opportunity Adam Cowley couldn’t resist and explains in this blog post how he did it.
VECTOR SEARCH: Fine-grained Access Control of Vector-based Search

Fanghua (Joshua) Wu will walk through different scenarios of fine-grained access control in the context of vector search, and provide a real world example using Neo4j AuraDB Enterprise.

KNOWLEDGE GRAPH: From Raw Text to Wikidata Taxonomy and Knowledge Graph

Sixing Huang demonstrates a semi-automatic NLP pipeline that generates an augmented knowledge graph from both English and Japanese raw texts.


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