Introducing: The RAG Demo Chronicles (Blog Series)
In my last blog entry I mentioned how I’ve been spending a lot of time learning AI related topics lately. Recently the newest research topic is RAG (Retrieval Augmented Generation). The more I learn about RAG, the more I am convinced it is how my clients will be able to take advantage of GenAI in the short term.
For those of you who are not familiar with the topic, you may have heard a presentation or blog focusing on “How to Chat with Your Documents” or something along those lines - these are usually about RAG. The idea is an application that is like ChatGPT but only looks at your data and documents.
As I learn more, I am playing with a lot of demo code - and I want to capture the different characteristics and features of these demos for reference.
In this blog series I focus on highlighting the features of samples/demos that show how to implement RAG. Currently (as of Feb 4, 2024), I have a list of 10+ demos/samples to cover in this series.
Some of the demos are very simple and will help you get an idea of how RAG works without a lot of pieces involved and others are built to show enterpise worthy architectures (with lots of moving parts). I’ll begin the series with the simplier ones and focus on the minimal pieces needed to implement RAG.
Blogs in this series (to be updated as they get published):
- Simple RAG using SQL Server and OpenAI (C#)
- Simple RAG using SQL Server and OpenAI and Function Calling (C#)
- Azure Search OpenAI Demo (C#)
- Azure Search OpenAI Javascript (Typescript)
- Azure Search OpenAI Demo (Python)
- Azure Vector Search AI Assistant (C#)
- Chat Copilot (C#)
If you have a comment, please message me @haleyjason on twitter/X.