This Week in Neo4j: AI, LangChain, Knowledge Graphs, RAG and more

Welcome to This Week in Neo4j, your weekly fix for news from the world of graph databases!
Happy New Year! I hope your first week of 2024 was a good one! In graphs, we started like we finished, and our topics are Artificial Intelligence, LangChain, Knowledge Graphs and RAG!

Join our Neo4j 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


Alex Babeanu is CTO at 3edges and a former Identity management specialist. He has been building software for big companies such as PeopleSoft or Oracle and evangelising the use of graphs for Identity since 2014.
Connect with him on LinkedIn.

In his session at NODES “How to Use Graphs for Real-Time Authorization Decisions” Alex describes how modern dynamic authorisation systems use graphs to make real-time decisions. He walks you through various authorisation concepts, actual use cases, which model and methodology fit which requirements best, and how to fit these in your development projects.

Alex Babeanu

ARTIFICIAL INTELLIGENCE: Using Knowledge Graphs and LLMs for Implementing End to End Solutions

In his newsletter, Ajit Jaokar collects his thoughts on Knowledge Graphs and LLMs and how they work together. He starts with an introduction on ontologies, knowledge graphs and LLMs, then dives into use cases for combining LLMs and KG and why it matters.
LANGCHAIN: Unleash CHATGPT Magic: Turbocharge Your Graph Database for Intelligent Conversations with LangChain and Neo4j
One of the pivotal elements in harnessing the full potential of generative AI models is integrating chat interfaces with internal data. In this article, Ayoola Fakoya delves into the crucial role of building chat interfaces that use internal data.
KNOWLEDGE GRAPHS: A Simpler Way to Query Neo4j Knowledge Graphs
In this article, Wenqi Glantz is experimenting with the brand new Llama Pack for Neo4j. She explains seven query strategies and how to package and apply them.
RAG: Constructing an Efficient Knowledge Graph RAG Pipeline with LlamaIndex

Retrieval Augmented Generation (RAG) is a solution to bridge this gap, allowing LLMs to access external knowledge sources. This article by Ankush Singal delves into RAG, examines its elements, and constructs a usable RAG workflow that harnesses the potential of LlamaIndex.


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