This Week in Neo4j: GPT, NASA, Generative AI, Chatbot and More

This week’s newsletter features a few articles on GPT (version intentionally omitted), reflecting its increasing use with knowledge graphs. “An Ensemble Chatbot for Healthcare,” by Neo4j Ninja Sixing Huang and Hong Wang, describes how crowdsourcing chatbots can produce more accurate results. In “Knowledge Graph-Based Chatbot With GPT-3 and Neo4j,” Neo4j Ninja Tomaz Bratanic describes a knowledge graph-based approach to chatbots, where the chatbot returns answers based on information and facts stored in the knowledge graph. Our development teams at Neo4j want to hear from you! Help us improve Neo4j by taking part in a 45-minute interview about all things Neo4j. You don’t need to be an expert – everyone is invited, wherever you are on your Neo4j learning path. If interested, please fill out this form and we will get back to you soon. We are running a lot of community events, and welcome speakers to present about technical topics related to graphs. Tell us about your presentations and we will contact you with speaking opportunities. Cheers, Yolande Poirier
Elena Kohlwey completed her studies in European Business and Mathematics, which led her into building intelligent applications that yield business benefits. She has spent the last three and a half years at RLE International, specializing in the field of graph-based applications with Neo4j. She is a Neo4j Ninja and you can connect with her on LinkedIn. In her NODES 2022 presentation, “User Change Modeling in Graph Applications,” she discusses the advantages and disadvantages of different modeling options. Watch her talk!
KNOWLEDGE GRAPH: KG-Based Chatbot With GPT-3 and Neo4j
Tomaz Bratanic explores a knowledge graph-based approach to chatbots, where the chatbot returns answers based on information and facts stored in the knowledge graph. Using a knowledge graph as a storage object for answers gives you explicit and complete control over the answers provided by the chatbot.
NATURAL LANGUAGE SEARCH: Generative AI, ChatGPT, and the Future of Graph Technology
Gemini Data added GPT-3 to their natural language search feature. End users can type what parts of a graph they’d like to see – or get answers to a specific question. The search captures the query and sends it to GPT-3 for analysis.
CHATBOT: An Ensemble Chatbot for Healthcare
Can crowd sourcing chatbots produce more accurate results? Sixing Huang demonstrates an ensemble chatbot in Google Colab.
INTERVIEW: Neo4j at NASA: Chatting With David Meza
Ashleigh Faith, Founder of IsA DataThing and Neo4j Ninja, chats with David Meza, Acting Branch Chief of NASAs People Analytics Department, to discuss machine learning ethics, how to get started in graph, and tidbits on his experience using Neo4j.
FROM NODES TO ROWS: A Guide to Querying Graph DB Neo4j in Pandas/SQL Style Using Cypher
Saloni Gupta, Data Scientist at SparkCognition, explains how Pandas and SQL-style queries in Cypher can be used to extract data from a graph database for data analysis or visualization tasks that require working with tabular data. Also, writing SQL or Pandas-style queries in Cypher leverages the benefits of the graph database for those who are more comfortable performing data analysis in SQL or Pandas.
VISUALIZATION: Graph Data Model Interactions
Vijaya Durga N’s blog is an introduction to creating a graph data model, querying, and visualizing using Neo4j Browser and Neo4j Bloom.
  Don’t forget to retweet, if you like it!
… Of Special Interest
  • Instructions for installing the Neo4j v5 on a Raspberry Pi 4 Check it out!
  • The latest graph-representation of @TeamKujira FIN order books, derived from <href=””>market data-scrape transformed with graphista computed into the Neo4j graph database with Cypher queries.