Retrieval Augmented Generation (RAG)

Retrieval Augmented Generation (RAG) in the AI environment…. What is this again?

Yesterday, Microsoft and NVIDIA held an interesting event in Munich on “Industrial Metaverse”, of course packed with the latest graphics, crazy computing and computing power, parallelization, and lots of generative AI that can be used to simulate, train, and build digital twins for manufacturing, automotive, etc.

In Ekaterina Sirazitdinova ‘s presentation, a very nice and catchy graphic on the subject of RAG was shown (see also below, (c) NVIDIA) and I would like to briefly lose a few thoughts on this term….

We all know the problem that GenAI systems sometimes hallucinate that people suddenly have three legs and that texts are somehow generated in a strange way. This is always quite easy to recognize in pictures, but often not in texts or “data”. In particular, if artificial data has to be generated and annotated to train models (see below), such errors can naturally propagate into the later models and lead to very unattractive effects. The wonderful old rule applies here: shit-in > shit-out. This problem is now being tackled by means of RAG.

This involves comparing data generated with GenAI (= artificial data) with real information (= real data). E.g. it is checked that people actually only have two legs instead of three. Generated data that does not conform to the model is discarded. This enrichment (= augmentation) of generated data with verified information naturally requires that the latter can also be found quickly and efficiently. Classic methods from information retrieval are used here, such as Graph databases (see also So you try to combine the best of two worlds.

Of course, this approach stands and falls with the fact that a review is possible at all. But since we have been working in information retrieval for decades on algorithms, concepts, databases, feature graphs and ontologies that provide such information in a (more or less) structured form, this is quite promising and could also enable approaches to the verifiability of AI.

An important point here is the need to have realistic, comprehensive, correct and annotated data sets for the training of AI. So that an AI can, for example recognizes defective screws, 10,000s of images of defective screws must be available for training. However, since we often cannot break 10,000 screws, such images are generated in all conceivable variants using GenAI and then given to the image recognition system for training. The better these are, the better the “real broken screws” will be recognized later.

In my view, RAG will play a central role in the AI environment in the future!