Hey folks, Mike Oglesby here from NetApp and I'm going to show you how NetApp and Nvidia have partnered to help you unlock your data for secure private generative AI. This solution is powered by Nvidia Nemo Retriever, an enterprise ready retrieval augmented generation framework and by NetApp with the ability to ingest from your existing NetApp data sources and NetApp's enterprise data protection and governance built in. And the best part, this entire stack can run both on premises and in any of the major clouds. First, I'm going to perform a chat query with retrieval augmented generation or rag turned off. So, I'm going to ask the chatbot to tell me about AIPOD from NetApp. And you'll see the answer is pretty far off base. Now, I'm going to add some information on AIPOD to my rag knowledge base. So I go over to the knowledgebased tab here and I click on add file and I'm going to add a file that contains some information on AIP pod. Okay, that file has been added. Now we're going to perform a chat query with rag turned on. So we go back to our chatbot UI. We check the use knowledgebased checkbox. We'll click on show context and then we'll ask the same question and click submit. Uh and you'll see this time the chatbot gives us a very good answer and it cites the source from our knowledge base and this solution can scale far beyond a one file knowledge base. With Nemo retriever we can programmatically ingest private data from across onprim and multiple clouds. Uh and here you see a script that's ingesting the entire contents of a NetApp volume. And now we're going to perform a chat query with rag turned on using the knowledge base that was created by that ingest script. Uh and you'll see we get a very good answer here to our query. And on the right it's citing sources from our knowledge base. And that's it. With Nemo Retriever and NetApp, you can apply generative AI to your private enterprise data today.