Intro and demo to RAG with Azure OpenAI

Retrieval Augmented Generation (RAG) is a technique used to feed more accurate and up to date data to LLM models like ChatGPT. That is because LLM models have two important limitations. They are trained on a massive amount of data, but they not trained on all data available on the internet. In addition to that, they are not trained on customer private data. So the question is how can we feed LLM models with this lacking data so we make sure its answers are accurate and correct.
Well, this is what RAG will do.
More details in this video.
Disclaimer: This video is part of my upcoming course on Udemy. Watch the updates here: www.udemy.com/...
Follow me on Twitter for more content: / houssemdellai

[@antonhokkonen7578]

Great video, Houssem! One of the best tutorial on that topic!

[@mikael-pz4oz]

very good and fresh summary - very good starting point with detaisl implementaiton details

[@Renz_Online]

Nice! Do you have a reference for RAG that uses Azure Cosmos DB for MongoDB (vCore)?

[@RicardoJosue]

Do you have a course for that?

[@mariastein100]

Thanks a lot! Really got content in short time!
Do you have mor information on which toolset can be used to simplify the data loading process or how to load document types such as pdf in a simple way?

[@TheKorimilli]

Good job !