This Week: GraphRAG, Knowledge Graph, Python, Ease of Use

Welcome to This Week in Neo4j, your weekly fix for news from the world of graph databases!
In this episode, our CTO, Philip Rathle, is interviewed to discuss GraphRAG and GQL. Additionally, we create Knowledge Graphs from Texts and Images, learn how to turn a Relational Database into a Graph Database and look at a tool to make working with Neo4j a bit easier.

Join our Neo4j User Research panel! Sign up to share your experiences with a researcher and influence the future of Neo4j products.
What’s in it for you? A chance to connect directly with product development teams, get paid compensation, hear about what we are working on, and more!

I hope you enjoy this issue,
Alexander Erdl

COMING UP NEXT WEEK!

Conferences: Find us at WeAreDevelopers, Berlin on July 18-19
Meetup: Meet us in Berlin, DE on July 18 & Bangaluru, IN on July 20
All Neo4j Events: Webinars and More
GraphSummit Series: Get Connected With Graphs

FEATURED COMMUNITY MEMBER: Katja Glaß

Katja is deeply passionate about fostering idea-sharing, particularly in technology. Her enthusiasm for innovation is rivalled only by her dedication to Open Source.
Connect with her on LinkedIn.

During a recent Life Science Workshop, Katja introduced the revolutionary Open Study Builder, an open-source tool designed to enhance the clinical trial process. It can replace traditional, manual processes with a centralised metadata repository, ensuring consistency and efficiency across clinical trial activities.

INTERVIEW: Neo4j’s Philip Rathle on the Rise of GraphRAG and GQL

Ben Lorica interviews Philip Rathle, Neo4j’s CTO, to discuss the rising popularity of graph-enhanced retrieval augmented generation (GraphRAG). He shares real-world examples of companies using Graph RAG in production for applications like enterprise search, supply chain risk analysis, and criminal investigations. They also talk about the potential impact of the new GQL graph query language standard.

KNOWLEDGE GRAPH: End To End Multimodal Knowledge Graph Creation from Texts and Images & Querying in Natural Language using LangChain and Neo4j

This blog post by Shubham Shardul explores a method that leverages OpenAI’s Large Language Models (LLMs) and Google’s Generative Model, Gemini, to automatically generate knowledge graphs from textual and visual data. He also discusses interacting with the constructed knowledge graph using natural language queries.

PYTHON: Turning Your Relational Database into a Graph Database

In this tutorial, Katia Gil Guzman guides you through transforming your relational database into a dynamic graph database in Python. Using the Amazon Products Dataset as an example, extract entities from the products’ titles to enrich the dataset and turn it into a graph. This can be achieved using OpenAI’s GPT model and then loading the data into Neo4j.

ANANSI: Enterprise Wrapper for Neo4j/

Anansi is built on top of the Neo4j Graph DB. It is specially designed for enterprises looking to streamline their Neo4j experience. Common tasks like node creation, relationship management, or data import become easy, allowing users to use the power of Neo4j without worrying about its syntax and other nuances.