Guest lecture on Retrieval-augmented generation by Raivis Skadiņš

ChatGPT-style AI tools are powerful, but they can hallucinate and lack access to specific knowledge sources. Retrieval-Augmented Generation (RAG) solves this by combining large language models with information retrieved from trusted documents. In this lecture, you will learn what RAG is, how it works, how to implement it, and what practical challenges appear when deploying such systems for real clients.

The guest lectures are realized with the financial support of the Language Technology Initiative. The project “Language Technology Initiative” (No. 2.3.1.1.i.0/1/22/I/CFLA/002) is co-financed by the European Union Recovery and Resilience Facility investment and the State Budget.