NLJUG – Nederlandse Java User Group NLJUG – de Nederlandse Java User Group – is opgericht in 2003. De NLJUG verenigt software ontwikkelaars, architecten, ICT managers, studenten, new media developers en haar businesspartners met algemene interesse in alle aspecten van Java Technology.
DEVOXX 2024 is around the corner in 2 weeks in Antwerp. To complement this great event Neo4j and Hopsworks invite you to a great meetup in Antwerp, just a short tram ride away from DEVOXX.
During this meetup there are 3 fantastic talks:
Michael Hunger, lead product innovation and developer strategy at Neo4j, will explain the role Neo4j is playing in the GenAI journey.
We all know that LLMs hallucinate and RAG can help by providing current, relevant information to the model for generative tasks.
But can we do better than just vector retrievals? A knowledge graph can represent data (and reality) at high fidelity and can make this rich context available based on the user’s questions. But how to turn your text data into graphs data structures?
Here is where the language skills of LLM can help to extract entities and relationships from text, which you then can correlate with sources, cluster into communities and navigate while answering the questions.
In this talk we will both dive into Microsoft Research’s GraphRAG approach as well as run the indexing and search live with Neo4j and LangChain.
Rik Van Bruggen, VP EMEA for Hopsworks will illustrate how you can use graph embeddings in a broader Machine Learning system
Graphs are great – and Rik would probably be the very last person to doubt that. As a native Antwerpian and a decade-long graph enthusiast, Rik will show you how you can use the power of Neo4j together with the Hopsworks Machine Learning Operations (MLOps) platform to bring the power of the graph to life. After all, it’s great to get graph insights, but unless you fully operationalise them in a production system, it does not provide the business value it deserves.
Quinten Rosseel, freelance Machine Learning Engineer, is diving headfirst into the mashup of AI agents, generative audio/video, and healthcare know-how.
Quinten will demonstrate Mina, an LLM-powered Q&A chatbot built with Neo4j and LangChain, that’s already answering medical questions via chat and voice for UZ Brussel. He’ll also dish on his work with Wobby.ai (AI agents) and Anam.ai (generative AI personas), and how melting today’s AI tech could lead to healthcare experiences sharp enough to make your doctor sweat.
For more info see here