This Week in Neo4j: GraphRAG, Knowledge Graphs, Open Source AI, GraphQL and more


Welcome to This Week in Neo4j, your weekly fix for news from the world of graph databases!
Have you already taken the Knowledge Graph for RAG Course on Deeplearning? Perfect timing for next week’s Knowledge Graph Conference – these two go very well together! Additionally, this edition has a recap from an Open Source AI Meetup and instructions on adding RAG to your GraphQL API.

NODES 2024 Call for Papers is now open! Please submit your graph stories. We love to hear from you.

I added a few more links for Graph Database Beginners, including a recent GraphAcademy Live, where we started with the Neo4j & LLM Fundamentals course.

I hope you enjoy this issue,
Alexander Erdl

 
COMING UP NEXT WEEK!

GETTING STARTED WITH GRAPHS

Johannes is a data architect and consultant specialising in Azure and LLM applications. He enjoys engaging with the developer community and sharing his learning through his YouTube channel.
Connect with him on LinkedIn.

In a recent livestream “Entity Resolution and Deduplication with Neo4j and GenAI“, we addressed the common challenge of duplicated entities resulting from variations in extracted names and identifiers.

Michal Štefaňák
 
DEEPLEARNING: Knowledge Graphs for RAG
This course by Andreas Kollegger will teach you how to use knowledge graphs within retrieval augmented generation (RAG) applications.
 
KNOWLEDGE GRAPHS: Entity Resolved Knowledge Graphs
Paco Nathan will teach a masterclass at the Knowledge Graph Conference. You’ll construct a knowledge graph in Neo4j, then use Jupyter, Pandas, Seaborn, PyVis and the Neo4j Graph Data Science library to compare the before/after impact of resolving duplicate records.
Besides this, you can find my colleague Jesús Barrasa delivering a keynote Exploring AI’s Future: The Convergence of Knowledge Graphs and LLMs on Thursday.
 
OPEN SOURCE AI: Ollama and Friends’ Local and Open Source AI Developer Meetup at KubeCon Paris
Alisdair Broshar summarises a joint meetup during Kubecon in Paris last month that brought together the AI Community. The event gathered a remarkable collection of builders. It included lightning talks from Timothée Lacroix (co-founder of MistralAI), Solomon Hykes (co-founder of Docker and Dagger), Paige Bailey (Lead Product Manager for DeepMind and Generative AI at Google) and others.
 
GRAPHQL: Adding Retrieval-Augmented Generation (RAG) to Your GraphQL API
Adam Cowley was curious to find out what benefits Generative AI (GenAI) can bring to front-end and full-stack developers and how GenAI would fit in the context of a GraphQL API. So he looks at the generate resolver, which accepts a prompt and will pass the values retrieved through the query and pass it into the prompt. This is a flexible approach to Retrieval Augmented Generation (RAG).


TWEET OF THE WEEK: DirectoryRanger

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