Speaker
Description
The use of AI is getting more widespread in education. With that, two large concerns with using AI for education are raised - the safety of students’ data and the AI missing specific knowledge about the given class. Retrieval Augmented Generation provides the user with the way to feed their data to the locally run LLM model (using Ollama framework or) as a context for the generation of the OER and other course materials. Different models are available to support user hardware from a personal laptop to the ‘gaming’ PC. As the AI model of user’s choice is run fully locally, no data is transmitted and it can be used to do tasks with students’ data, such as summarization of evaluations, simple pre-grading and handwriting recognition tasks. The background, installation highlights and usage examples will be presented.