Gen AI: Understanding and Using RAG - Making LLMs smarter by pairing your data with Gen AI

Large language models (LLMs) are great and provide a lot of utility out of the box - as long as you accept that the data they have is only as recent as their training. And, as long as you understand that that they don't have context of any data they weren't trained on - which may be the local context you really care about. In this session, we'll see how to augment their training and knowledge to include other content that they weren't trained on, such as your files. And we'll see how to seamlessly combine that with the LLM's existing knowledge and query/prompt interfaces.

Retrieval Augmented Generation (RAG) is the prominent approach/technology for adding additional data to the set that can be referenced when you are working with LLMs. This approach allows you to add more up-to-date or more contextually relevant “local” information sources, such as documents. These are then converted and stored in a way that makes them “queryable” in the same way as the LLM.

Join expert Brent Laster to learn how to integrate your data with off-the-shelf LLMs to get a unified approach for querying your local content as well as the LLM's training.