Students material for the open knowledge full day hands-on workshop on GenAI and RAG.
Thanks to powerful frameworks and libraries, the first generative AI applications at the Hello World level can be implemented with just a few lines of code. However, these first attempts quickly reach their limits. Why? Because reality presents challenges that cannot be easily solved with this trivial approach.
But what is needed for a generative AI application at the enterprise level? A well-thought-out generative AI architecture! In this full-day hands-on workshop, we will build a complex Generative AI application step by step to query the in-house, distributed domain knowledge via chat.
Examples of this distributed knowledge could be the entire expertise of an IT department, product information and specifications of an international retailer or the internal employee portal of a large company.
Starting with a minimalist RAG (Retrieval Augmented Generation) system, we consider various challenges and discuss suitable solutions. By the end, we will have an architecture that can withstand the challenges of reality.
You will find the corresponding presentation on SpeakerDeck: