10 PyData Piraeus Meetup: LLMs with Knowledge Graphs and Information Retrieval

Dear All,

We are excited to announce our next meetup, happening on Friday, November 14th! We’re thrilled to welcome two outstanding data scientists, Panos Alexopoulos and Konstantinos Eftaxias, who will be sharing their insights on Large Language Models in Knowledge Graphs, Information Retrieval and Matching at Scale.
A big thank you to Panos and Konstantinos for generously agreeing to share their expertise with our community!

Program:

18:00 - 19.00: Grounding LLMs with Knowledge Graphs: What, Why, and How

• Panos Alexopoulos - Data Semantics & AI Specialist | Author | Educator

Linkedin: https://www.linkedin.com/in/panosalexopoulos/

Abstract:
Large Language Models (LLMs) are powerful but notoriously ungrounded as they generate fluent, plausible text that isn’t always factual, consistent, or explainable. One promising way to address these issues is by connecting LLMs with Knowledge Graphs, namely structured, explicit representations of knowledge that can provide context, constraints, and verifiable facts. The main paradigm for doing this is Graph-based Retrieval-Augmented Generation (GraphRAG), which integrates graph-based reasoning and retrieval into the generation process.
In this talk, I’ll introduce the core ideas behind GraphRAG, describe common design patterns, and outline the steps and tools needed to implement such systems in practice.

Bio:
Panos Alexopoulos is a Data and AI practitioner, author, and educator, with 20 years of industry experience across diverse domains. His expertise lies at the intersection of semantic data modeling, data quality, and development and evaluation of AI systems. Currently he works as Lead Semantic Data and AI solutions at Triply BV, in Amsterdam, Netherlands, where he helps large organizations design, develop and deploy data management and AI solutions.

He is also the author of Semantic Modeling for Data (O’Reilly, 2020), a well received and highly rated book in the semantic technology and knowledge graph communities. In the last few years he has designed and delivered over 20 masterclasses, tutorials, and courses on data and AI, including a highly popular course on Knowledge Graphs and Large Language Models.

19:00 - 19.45: Retrieval and Matching at Scale: from embeddings to payouts in music rights

• Konstantinos Eftaxias - Staff Data Scientist at Orfium

Linkedin: https://www.linkedin.com/in/konstantinos-eftaxias-a9389921/

Abstract:
The growth of digital platforms has led to an explosion of data. Our aim in Orfium is to effectively process this ever-increasing volume of information. We achieve this by building and deploying cloud services designed to accurately track how music is used, how music rights are managed, and ensuring rightful payments to artists and rights Holders.
In this talk we are going to explore techniques that bring our AI models to production, building and maintaining our services and overcoming cost and scale barriers. Attendees can anticipate a brief overview of our services, the tools that we are using to bring our models to production, the cloud architecture that makes all this possible and a deeper dive on how technologies like vectorDBs enabled us to reach the scale we have today without breaking the bank.

Bio:
Dr. Konstantinos Eftaxias is an experienced Data Scientist with a PhD from University of Surrey, MSc in Information Technologies in Medicine and Biology in UoA and BSc in Physics from the University of Patras. Currently, he is working in Orfium as a Staff Data Scientist focusing on productising machine learning models and building scalable services for audio and video matching/classification. In his PhD, he has specialised in machine learning methods that exploit graph properties to model brain signals. Through the KTP program in the UK, he worked as a Data Scientist in WSP and University of Surrey, designing and implementing mathematical optimisation algorithms for water networks and machine learning methods for time-series prediction. Finally, he has authored more than 10 scientific papers that have been published in conferences and journals.

19.45 - 20.30: Light Refreshments

The venue details will be shared soon, so stay tuned!
Looking forward to seeing you all!

The organizing team,