Today's leading AI solutions are trained on vast amounts of generally available data. A powerful way to enhance these AI systems is by incorporating localized, specific knowledge into this broader dataset. One method for achieving this is through Retrieval Augmented Generation (RAG).

In this session, we'll walk through how RAG can be implemented with ChatGPT or any other Large Language Model (LLM). By using RAG, you can enable scenarios like chatting with your email inbox, local computer files, intranet articles, or any other local knowledge base.

We'll demystify this topic by breaking down the concept into simple terms, as well as looing at both code and prompts that enable AI access to local knowledge stored in a database.