This Week in Neo4j: Context Engineering, Chunking, Cypher, Aura 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 edition dives into context engineering for smarter AI agents, shows how hierarchical chunking supercharges RAG performance, explores powerful new traversal tricks in Cypher and gets you hands-on with deploying graphs in Neo4j Aura.
NODES 2025 is back on November 6 – our global, 24-hour graph dev conference spotlighting real-world apps, intelligent systems and all things Neo4j. Our keynote this year, by Andrew Ng, dives into the technical frontiers shaping the future of AI.
And while we are getting ready for NODES 2025, we have just opened the Call for Papers for NODES AI: On April 15, practitioners will gather virtually to explore AI, context engineering, and intelligent agents.
Happy Graphing,
Alexander Erdl
COMING UP!
- Livestream: NODES 2025 – Speaker Roundtable on October 28 & Going Meta: S03 E02 on November 04
- Conferences: Find us at Databricks Amsterdam on November 06
- Meetup: Meet us in Berlin, DE on October 30
- All Neo4j Events: Webinars and More
FEATURED COMMUNITY MEMBER: Andrew Ng
Andrew Ng is the Founder of DeepLearning.AI, Managing General Partner at AI Fund, Executive Chairman of LandingAI, Chairman & Co-Founder of Coursera, and Adjunct Professor at Stanford. As an AI and online education pioneer, who has taught 8M+ people.
Connect with him on LinkedIn.
Andrew is delivering the NODES 2025 Keynote. Together with Emil Eifrem, CEO of Neo4j, they share their vision for what comes next. Together, they’ll dive into the technical frontiers shaping the future of AI.
CONTEXT ENGINEERING: Build Intelligent AI Agents With Context Engineering
Michael Hunger uses a graph-backed context engineering approach with Neo4j to build intelligent AI agents. You’ll learn how to selectively manage and feed relevant information into the agent’s context window – vastly improving reasoning, decision-making, and tool integration.
CHUNKING: Feed the Raptor, Not the Pigeon – How Hierarchical Chunking + Contextual Retrieval Turns a Plain-Old RAG Into a Carnivore
Ercin Dedeoğlu explores how a system named Feed Raptor Pigeon applies hierarchical chunking to transform flat document segments into layered, tree-organised elements – enhancing the precision and context-awareness of RAG pipelines. The article highlights how chunking strategies can significantly improve LLM performance on complex knowledge tasks by structuring retrieval in multiple abstraction levels.
CYPHER: Solve Hard Graph Problems With Cypher 25
In this article, Pierre Halftermeyer showcases how Cypher 25 introduces significant new features – most notably the REPEATABLE ELEMENTS match mode and the allReduce function, which let developers elegantly and efficiently solve previously challenging graph-traversal problems (Example: an Advent of Code puzzle that ran in ~144s is reduced to ~1.2s).
AURA: Aura Fundamentals
Our latest interactive course in the Neo4j GraphAcademy guides you through deploying and managing your graph database in the cloud using Neo4j Aura. From selecting the right tier and working with the console to importing data, querying graphs, and setting operational best practices, it includes all steps necessary to start with graph on Aura.
CONTINUOUS LEARNING
- GraphAcademy: Learn to build on “Neo4j Aura” with our newest course.
- 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
- Workshops: Road to NODES
- New Webinar: Build Intelligent Agents Grounded in Enterprise Data in Minutes – AMER, EMEA, Asia Pacific
POST OF THE WEEK: Artemiy Vereshinskiy
Please share it if you like it!
Share Article
Explore
Related Articles
