This Week in Neo4j: Knowledge Graph, Deepseek, Bloodhound, RAG and more
Senior Developer Marketing Manager
3 min read
Welcome to This Week in Neo4j, your fix for news from the world of graph databases!
This week’s episode compares Deepseek-R1 7B vs Mistral 7B for Knowledge Graph Construction. Also, the LLM Knowledge Graph Builder received a few new features in 2025, we take a look at BloodHound Viewer for Chrome and have a few best practices for your RAG-based projects!
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!
Happy Graphing,
Alexander Erdl
COMING UP NEXT!
- Livestream: Neo4j Live: Cypher Workbench on March 18 & Neo4j Live: Stunning Graph Visualizations with NVL on March 20
- Conferences: Find us at Databricks Data Intelligence Day, Melbourne on March 18, Factor Data and AI Day, Melbourne on March 27 & Kubecon Europe, London on April 1-4
- Meetup: Meet us in Montreal, CA & Bristol, UK on March 22
- All Neo4j Events: Webinars and More
- GraphSummit Series: Transform Your Enterprise with Graph and GenAI – Next Stop: Munich on April 2
FEATURED COMMUNITY MEMBER: Alicia Powers
Her work uses analytics to help people and businesses make better decisions. She is now creating tools that use LLMs to apply the power of the latest AI technology.
Connect with her on LinkedIn.
In her session at NODES 2024 “Just Add an LLM: Creating a New Food Recommendation Engine From an Old Cypher Based One”, she compares two approaches to building AI-supported recommendation engines, where one includes LLM-generated Cypher queries based on a prompt, and an LLM using Retrieval-Augmented Generation (RAG).
KNOWLEDGE GRAPH: LLM Knowledge Graph Builder — First Release of 2025
In this article, Michael Hunger introduces the new features of the LLM Knowledge Graph Builder, including community summaries, parallel retrievers and expanded model support for better knowledge graph construction from text.DEEPSEEK: Knowledge Graph Construction and Querying with Deepseek-R1 7B vs Mistral 7B on Neo4j
Kennedy Selvadurai investigates whether Deepseek’s chain-of-thoughts approach can generate meaningful graphs and reduce hallucinations in comparison to Mistral 7B.BLOODHOUND: BloodHound Viewer
Mor David has developed a Chrome extension that enhances BloodHound Community Edition with additional features, including query history navigation, improved layout controls and a Neo4j button.RAG: Graph Assets – Best practises for your RAG based project
Ashok Vishwakarma discusses strategies for managing graph assets in Retrieval-Augmented Generation (RAG) applications. The focus is on optimised schema design, efficient querying, automation, security and AI integrations to build scalable, high-performance RAG applications.CONTINUOUS LEARNING
- GraphAcademy: Learn to use the Neo4j Data Importer to import data and create a graph data model in Importing Data Fundamentals
- Get to Know Graph: Level up your graph skills with webinars packed with practical insights to help you build powerful apps
- Learn on Your Schedule: Go deeper into graph technology on Neo4j’s On-Demand webinar library
- New Webinar: Discover Hidden Patterns with Graph Databases – Fraud Detection and More – AMER, EMEA, Asia Pacific
POST OF THE WEEK: Holger Knublauch
Please share it if you like it!
Share Article
