This Week in Neo4j: Neo4j 5, GenAI, RAG, Vector Index and more


Welcome to This Week in Neo4j, your weekly fix for news from the world of graph databases!
Are you ready for the holidays? This week, we have AdventOfCode twice: One solving the puzzles using Neo4j and one with 24 Neo4j 5 tips and tricks. Additionally, we have more articles and videos on RAG, GenAI and Vector Indexes.

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

 
COMING UP NEXT WEEK!

Chris Smith is a Senior Software Engineer at Thomson Reuters Special Services. He has spent his professional career building robust solutions and tackling challenging problems for customers in the government and commercial spaces. Chris believes the power of graphs combined with well-designed applications are great tools to accomplish many different problem sets.
Connect with him on LinkedIn.

In his session at NODES “Unveiling Innovation Pathways End to End Graph Analytics for Emerging Tech” Chris demonstrates an end-to-end graph analytics pipeline identifying emerging communities of new technologies. Finding hidden linkages between quantum computing and artificial intelligence research communities illuminates interesting innovation pathways.


Chris Smith

 
NEO4J: AdventOfNeo4j – 24 Neo4j 5 tips in December 2023

For all of December 2023, Christophe Willemsen shares one Neo4j 5 tip daily for 24 days. In this summary, you can find his tips and tricks ranging from Working with Indexes, Cypher Clauses, Change Data Capture, Composite Databases or Vector Indexes.
 
RAG: Multimodal RAG pipeline with LlamaIndex and Neo4j
The field of AI and large language models is evolving rapidly. Today, most of us can’t imagine working without offloading at least some minor tasks to LLMs. Tomaz Bratanic looks at the latest development around GPT-4-Vision, enabling image comprehension. He shows you how to retrieve and combine information from text and images to generate an accurate response with multimodal LLMs.
   
GENAI: RAG with a Neo4j Knowledge Graph: How it Works and How to Set It Up
In this video, Philipp Brunenberg explains how RAG (retrieval augmented generation) with a Neo4j Knowledge Graph works and how we can set it up on your laptop. He also briefly introduces how we can customise the code from the Gen-AI Stack.
VECTOR INDEX: Vector Indexing plus Knowledge Graphs with Neo4j

Vector indexing is thought of as a typical implementation for Generative AI. While this is true at a very rudimentary level, Jeff Tallman discusses using vector indexes in Neo4j to complement graph analytics (non-AI) when data quality is poor, resulting in loose text search-based retrievals.

TWEET OF THE WEEK: Pierre Halftermeyer


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