This Week in Neo4j: Graph Data Science 2.3 Release, GraphGPT, New Courses, Recommendation Engine, Selling KGs to Execs, and More!


Graph Data Science 2.3 was just released! Check out the new features like the Minimum Directed Steiner Tree, super useful for understanding the shortest or least expensive routes when travelling from multiple locations to a specific destination. Or HashGNN, where, instead of doing neural transformations like most GNNs, transformations are done by locality-sensitive min-hashing.

We are also introducing negative relationships, which provide negative relationship examples for more options to train link prediction models and get them into production quickly. Learn more about it here.

Cheers,
Yolande Poirier

P.S.: If you’re a developer building modern applications with GraphQL, don’t forget to take this short, two-minute survey. We want to hear from you!
 

Mark is an Apache Pinot Advocate and Developer Relations Engineer at StarTree. He previously worked as Developer Relations Engineer at Neo4j. Apart from writing blog posts and creating videos, Mark is dedicated to the developer experience, simplifying the process of getting started by making tweaks to product and documentation. Mark writes about his experiences working with all things data at markhneedham.com. Connect with him on Twitter.

In his NODES 2022 presentation, he exposes a graph model before doing a quick walk-through of it based on his predictions of tennis tournaments in 2022. Watch his talk “Graph Modeling The Shadow Graph”!


 
AI: Use ChatGPT to Query Your Neo4j Database
In this blog, Tomaz Bratanic trains the famous AI bot to generate Cypher queries. He feeds it a graph schema, and prompts it to self-correct its own errors. 
 
OPENSOURCE: Extrapolating Knowledge Graphs From Unstructured Text Using GPT-3
GraphGPT, an open source project by Varun Shenoy, converts unstructured natural language into a knowledge graph. Use your OpenAI API key to try the web version or install on your machine from the GitHub repo.
 
HANDS-ON: Recommendation System Using Neo4j

In part one describing a recommendation system, Susmit explored collaborative and content-based filtering and designed the data model. In this second article, he explains writing cypher queries for loading the data, tracking new orders and implementing the recommendations.

FREE TRAINING: Neo4j GraphAcademy News for Q4 2022

Don’t miss the quarterly GraphAcademy News by Elaine Rosenberg. There are new features, new courses, bug fixes, and other items you will want to take advantage of.


NODES SESSION: Doctor.ai A Graph-Based Medical Chatbot

Sixing explains how a cloud-native medical chatbot called Doctor.ai, backed by a Neo4j graph was developed. You can employ either AWS Lex, GPT-3, or Alan AI as the natural language understanding engine.




KNOWLEDGE GRAPH ADOPTION: Sales Pitch for Getting Executive Support

Bojan Ciric shows how to present a convincing graph solution to executives. He explains how the knowledge graph is the solution to maintaining an enterprise view of data, a key problem of data decentralization.

UBUNTU CONFIGURATION: How to Install the Neo4j Graph Database on Ubuntu Server 22.04

In this post, Jack Wallen walks us through the installation of the Neo4j graph database on Ubuntu Server 22.04. Then, we enable remote connections by editing neo4j.conf and the system hosts file.

APP: Creating the Magic Remote Control

Chris Heisz chronicles the birth of an internal SRE portal at Neo4j that tracks AuraDB databases. He describes the workflows and also the construction of the portal’s CLI.

TWEET OF THE WEEK: @rastadidi

Don’t forget to retweet, if you like it!
 
COMING UP NEXT