To build RAG (Retrieval Augmented Generation) experiences, where LLMs can query documents, you need a strategy to chunk those documents. Kernel Memory supports this.

Johnny Reilly is a software engineer, blogger, and technology enthusiast known for his insights into software development, web technologies, and personal productivity. Readers can learn about coding best practices, web development frameworks, and career growth strategies. With blog posts, tutorials, and motivational content, Johnny Reilly inspires and educates readers on their journey to becoming successful developers.

John Reilly

Learn how to use Kernel Memory to chunk documents in an ASP.NET application, running it in 'Serverless' mode. Discover the benefits and limitations of this approach and understand the process of integrating Kernel Memory and Azure services.

Using Kernel Memory to Chunk Documents into Azure AI Search

1. Setting up Kernel Memory serverless ​