Jason Haley

Ramblings from an Independent Consultant

Demo Review: Simple RAG using SQL Server, OpenAI and Function Calling

Demo Review: Simple RAG using Blazor, SQL Server, Azure OpenAI and Function Calling If you are like me, a full stack C# developer who is attempting to get up to speed on how GenAI technologies are going to show up in our business applictions - then after you get the first demo up and running, this demo (also by Michael Washington) is a great next step. RAG (Retrieval Augmented Generation) applications typically have the following steps: Gather input from the user (Retrieval) Use the user’s input to do a query over data or documents (ofen using vector embeddings) and gather N number of the best results from that search then pass to an LLM as context to use in crafting a response for the user (Generation) Return the natual language result from the LLM describing its search result …

Demo Review: Simple RAG using SQL Server and OpenAI

Demo Review: Simple RAG using Blazor, SQL Server and Azure OpenAI Are you a full stack C# developer attempting to get up to speed on all this GenAI stuff? Are you typically a relational database developer (ie. SQL Server) wondering what all the hoopla is around vector databases and more importantly how all this stuff relates to some type of functionaly that you have a chance at really using in your day-to-day work? Oh and you probably have not had time to dig into this pattern named Retrieval Augmented Generation (RAG) due to being too busy implementing web application or service code. If so, then fear not! This demo is a fantastic place for you to start. It uses your skillset to get a RAG application up and running without introducing too many things outside of what you already know …