Hands-on Webinar on Kairntech RAG (retrieval-augmented generation)

Organized by the german DGI (Association for Information and Knowledge), Kairntech had delivered a webinar on June 26 on the use of Large Language Models for the analysis of document corpora with retrieval-augmented generation (RAG).

Webinars are a fine tool to comfortably convene an audience and deliver a presentation. But often they tend to do a lot of frontal teaching with many colorful slides and then a short discussion at the end. Last week’s Kairntech webinar had chosen a different approach: Stefan Geißler from Kairntech had invited the audience to a hands-on session where everybody could try out the effects of LLMs on their own documents on an online instance of a RAG system.

Natural language answers, not just lists of hits

RAG is one of the most popular applications of LLMs these days because it delivered the capabilities of LLMs on a user’s own content – content that the LLM has never seen in training. Kairntech had prepared user accounts to their software and guided the participants though the process of importing content and then asking natural language questions to receive natural language answers.

Figure 1: Rather than delivering a list of potential hits as in a convention search engine,a RAG system returns a direct answer to the user’s question.

More on the Kairntech implementation of RAG can be found here.

Relevant for – among others – libraries

The participants, not uncommon for an event organized by the DGI, came from a wide selection of large scientific and public libraries – a sector for which the possibilities offered by the adoption of LLMs evidently are of great relevance. Following the webinar, all users now can continue to use the system for their own experiments with their own data for an extended test period.

We’d like to thank the DGI and in particular Dr. Margarita Reibel-Felten for the smooth cooperation in the preparation and delivery of the webinar. If you are interested to give RAG a try, you don’t have to wait for the next Webinar: Drop us a line and we will ensure you get a free trial access to the system.