As many organizations today have implemented at least one ChatGPT-enabled chatbot in production, the next question now is how can it do more? For instance, let’s consider a banking assistant chatb...

As I was writing my last post, I thought of enabling markdown *.md files with GitHub Copilot. The results surprised me that I knew I had to make a video about it. So here it is!

The biggest problem with most cloud migration assessments is that it focuses on VM-sizes and potential cost savings. Don’t get me wrong, this is a very important area of concern… and there are some...

Fifteen years ago, I embarked on my Agile journey when I received my Scrum Master certification. Back then, I was one of three developers in a budding startup, where self-management was not just a ...

One of the things that I love about GitHub is that it’s easy to find working code for areas that I want to learn. For OpenAI, it has become a great source of working GPT-enabled applications. This ...

The popularization of OpenAI’s ChatGPT has put the world in a rapid pace of innovations. One of which is the rapid advancements of SDKs such as LangChain and Semantic Kernel. To integrate OpenAI w...

In my last two posts, I shared how you could load balance multiple OpenAI instances using Azure API Management and using Azure Application Gateway. The reality of enterprise organization requiremen...

Last time, I shared best practices on addressing Azure OpenAI token limits, which included a section on using multiple Azure OpenAI instances distributed across regions, accessed through a load bal...

As with any service, Azure OpenAI has service quotas and limits, depending on which model you are using. This is a summary of the current limits of the “famous” models (as of 2023-06-23): ...

This post concludes the my series of notes as I learn how to integrate LLMs like OpenAI in enterprise applications. Intro and Architecture Development with Semantic Kernel Develop...