Neo4j Graph Tech Weekly (E:13)
This Week in Neo4j: OpenAI, Deploying on GCP, Neodash, Graph Algorithms, Python, and More
In this blog, Eranga Dulshan uses OpenAI semantic search and py2neo package on a graph database of PDF files. He saves the OpenAI generated embedding vectors in Neo4j nodes and calculates the cosine similarity at the database level with graph data science.
VISUALIZATION:?Exploring Neodash for 197M Chemical Full-Text Graph
Tom Nijhof-Verhees , biomedical engineer, explores a chemical graph database with NeoDash. With an input field and a result field, the addition of a full query yields a fuzzy full-text search.
NODES SESSION:?Graph Algorithms and Visualization for Clinical Care Support of Pneumonia
Ana Areias and Mengjia Kang take a deep dive into patient journeys through the Medical Information Mart for Intensive Care (MIMIC)-IV de-identified Electronic Medical Records (EMR) data from 2008 – 2019, for patients diagnosed with pneumonia.
PYTHON:?NODES 2022 for Pythonistas
With over 40 hours of recorded NODES 2022 videos, it’s nice to have a guide. Jason Koo , Developer Advocate at Neo4j, sifts through it all from the viewpoint of a Python developer.
GOOGLE CLOUD:?Automating Deployment of Neo4j Java Extensions
Gaston Guitart , Neo4j Consulting Engineer, addresses potential challenges to manual deployment of Neo4j extensions, including SSH configuration. He proposes a framework for automating deployment on self-managed Google Cloud environments in two git repositories.
INTRODUCTION:?Knowledge Graphs
Tiroshan Madushanka introduces knowledge graphs and explores how a knowledge graph about movies represents the actors, directors, producers, and studios involved in each film. He explains the advantages of graph databases to represent complex relationships and connections and the common applications of graph technology.