This Week in Neo4j: SBOM, Data Modeling, LLM, LangChain and more


Welcome to This Week in Neo4j, your weekly fix for news from the world of graph databases!
This episode features an interesting GitHub Repository on how to work with Bill of Material for Software, we look at Graph Data Modeling and (of course) more Vector Search and how LLMs can kickstart projects beyond NLP.

Did you get your ticket for NODES 2023 already? Also, don’t forget about our workshops for some hands-on fun with graphs: NeoDash, Data Modeling, GenAI & Geospatial Data.

I hope you enjoy this issue,
Alexander Erdl

 
COMING UP NEXT WEEK!

Alfredo is a Cyberintelligence & Security Operations Manager based in the United States. He is a passionate enthusiast and master’s graduate in Cyber Intelligence. He is currently pursuing a master’s in Big Data with a primary focus on Red Team Ethical Hacking, Vulnerability Assessment, Risk Management and Threat Hunting, Threat Intelligence and Cybersecurity Research.
Connect with him on LinkedIn.

Join him at NODES 2023 where he will explore the intricacies of the dark web and showcase how Neo4j can be the ultimate tool for navigating its depths. The mission is to develop a cutting-edge toolset that leverages Neo4j’s visualisation capabilities to collect and analyse data from the dark web.


Alfredo Abarca

 
SOFTWARE BILL OF MATERIAL: Neo4Cyclone
Neo4Cyclone is a project that uses CycloneDX SBOMs (Software Bill of Material) in a Neo4j database for visualisation. The application is a parser that gets the relevant data from the CycloneDX report and ingests it in a Neo4j database.
 
DATA MODELING: Data Modeling in Graph Databases: Building Intuitive and Scalable Structures
Tahir Waseer posted another article in his series on transitioning from relational to graph databases. In this blog, he talks about Graph Data Modelling and building structures: It’s not just about creating a structure; it’s about creating one that is intuitive and scales with your needs.
   
LLMs: Leverage LLMs for Graph Data Science Pipelines: 4 Steps to Avoid Pitfalls of ChatGPT

In this article, Sean Robinson explores five crucial steps to harness the capabilities of large language models (LLMs) for enhancing graph data science pipelines. While LLMs are often associated with natural language processing tasks, their potential extends far beyond just text analysis.

LANGCHAIN: Efficient semantic search over unstructured text in Neo4j

After the hype around ChatGPT followed the rise of Retrieval Augmented Generation (RAG) applications, where you feed relevant information to the model at query time to construct better and more accurate answers. In this blog post, Tomaz Bratanic shows us how to set up a vector index in Neo4j and integrate it into the LangChain ecosystem.

TWEET OF THE WEEK: GraphTFT (watch it in action)


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