This Week in Neo4j: Chatbot, GraphRAG, Graph Analytics, Bloodhound and more

Senior Developer Marketing Manager

May 24, 2025

3 min read

Welcome to This Week in Neo4j, your fix for news from the world of graph databases!

This edition mixes powerful ways to use Neo4j across AI, analytics and cybersecurity: we explore how to build smarter chatbots, create knowledge graphs from unstructured data, scale graph algorithms with Aura Analytics and simplify Active Directory security with BloodHound-MCP.

NODES 2025 is back on November 6 – our global, 24-hour graph dev conference spotlighting real-world apps, intelligent systems and all things Neo4j. The Call for Papers is open through June 15, so take the chance to share your code, models and graph-powered insights with the community!

Happy Graphing,

Alexander Erdl

COMING UP!

Livestream: Discover Neo4j AuraDB on May 26 & Neo4j Live: AI Engineer World’s Fair GraphRAG Track on June 5
Conferences: Find us at AWS Summit, Singapore on May 29, Snowflake Summit, San Francisco on June 2-5, AI Engineers World’s Fair, San Francisco on June 3-5, AWS Summit, Sydney on June 4-5 & GrAPL 2025, Milan on June 4
Meetup: Meet us in Malmö, SE on May 26 & Mumbai, IN on May 31
All Neo4j Events: Webinars and More
GraphSummit Series: Transform Your Enterprise with Graph and GenAI – Next Stop: Paris on June 17

FEATURED COMMUNITY MEMBER: Irina Adamchic

Irina is a Fullstack LLM developer at Accenture, specialising in end-to-end Generative AI solutions. Se’s passionate about transforming workflows through cutting-edge GenAI technologies.

Connect with her on LinkedIn.

In a livestream “Neo4j Live: Entity Architecture for Efficient RAG on Graphs”, she used fixed entities to enhance data retrieval, improve contextual understanding and boost AI performance.

CHATBOT: Codelab – Build a Movie Recommendation Chatbot using Neo4j and Vertex AI

This hands-on codelab by Romin Irani and Siddhant Agarwal guides you through building an intelligent movie recommendation chatbot by integrating Neo4j, Vertex AI and Gemini. The result is a chatbot capable of understanding natural language queries and providing personalised movie suggestions based on semantic similarity and graph-based context.

GRAPHRAG: Creating Knowledge Graphs from Unstructured Data

Have you had a look recently at our Developer Guides around GraphRAG? We just published a comprehensive guide on how to transform unstructured data into a structured knowledge graph. This knowledge graph can then be integrated with existing structured data, enhancing applications like Retrieval-Augmented Generation (RAG) with more accurate and contextually relevant information.
There is also great content around MCP.

GRAPH ANALYTICS: Aura Graph Analytics: A Technical Deep Dive

Last episode we celebrated the launch of Aura Graph Analytics which supports data from diverse sources, including relational databases and data lakes, with zero ETL, enabling scalable, parallel analytics via Python and the Graph Data Science client. This time Alison Cossette shows us how to apply over 65 graph algorithms, like community detection, centrality and link prediction.

BLOODHOUND: BloodHound-MCP

BloodHound-MCP-AI from Mor David is an open-source integration that connects BloodHound with AI through the Model Context Protocol (MCP), enabling security professionals to analyse Active Directory attack paths using natural language instead of complex Cypher queries. Security professionals can now assess Active Directory security posture more effectively and better identify vulnerabilities.

CONTINUOUS LEARNING

GraphAcademy: Learn to search unstructured data using Neo4j and vector indexes in our course “Introduction to Vector Indexes and Unstructured Data“
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: GenAI and Graphs: An Introduction to Building GenAI Apps – AMER, EMEA, Asia Pacific
Workshops: Virtual Courses on Mastering GraphRAG – EMEA on June 3, Mastering GraphRAG – APAC on June 3 & Neo4j Fundamentals – AMER on June 18

POST OF THE WEEK: Linghua Jin

Build Real-Time Product Recommendation Engine ? with LLM #OpenAI and Graph Database @neo4j.com

? repo: github.com/cocoindex-io…
? tutorial: cocoindex.io/blogs/produc…

#LLM #GraphDatabase #Neo4j #AIRecommendations #GenerativeAI #KnowledgeGraph #LLMApplications #GraphAI

[image or embed]

— Linghua Jin (@badmonster0.bsky.social) 19. Mai 2025 um 07:18

Please share it if you like it!