Your RAG-powered LLM application might look pretty convincing at first glance, but how do you really know if it’s any good? And how do you justify the design choices you make? In this talk, you will learn about the RAG evaluation concept we produced at Airbus for evaluating the components of our digital shopfloor assistant, its implementation with open source tools paired with Google Vertex AI, and what we learnt in the process.

Nataliia Kees

Affiliation: Airbus GmbH

I am a Data Scientist at Airbus, where I am a part of the team Digital, building AI products which empower engineering, manufacturing, sales and other business activities of the company. I enjoy diving deep into natural language processing and am passionate about MLOps, good coding practices and deploying AI applications in the cloud. Before joining Airbus, I built data products as a consultant in various client projects, in particularly focusing on NLP and Responsible AI. Apart from that, I teach Python, and in my free time, I enjoy hiking and learning new languages.

visit the speaker at: Homepage