December 18, 2023
Are open source large language models the future? Let's find out with an example
Many are raving about the capabilities of GPT-4. A growing group of people is worried that OpenAI is getting to powerful. I spend time exploring open source large language models to figure out, how to set them up, and what's missing. Read on to learn more.
Read moreOctober 7, 2023
How-to gradually switch from Qwerty to Colemak in 5 steps
Everyone who knows me knows that I like custom keyboards. I’ve been using a Moonlander for quite some time now. People have wondered why and even questioned my sanity. But it’s more than a hobby. I mainly use customizable keyboards because I can reduce the amount of keyboard gymnastics I need to participate in by rebinding often-used key combinations. In this post, I’ll show you how I switched to Colemak in 5 steps.
Read moreJuly 19, 2023
Building language model applications with Azure OpenAI Service
We've been using ChatGPT quite a lot at work. As we used it more and more we found that keeping data within our own environment has become more important. In this post we'll explore how you can use Azure OpenAI as an alternative to OpenAI to keep your chat data private. Take a look!
Read moreJune 9, 2023
The Art of AI Implementation: Strategic Steps for Building Effective LLM Applications
We’ve seen a lot of demonstrations lately with large language models. Everyone is racing to get on board with ChatGPT and other large language models (LLMs). I’ve never seen so many experts pop up in such a short time. But is there a method to the madness? Are we doing the right thing by staying away from the hype or should we go all in? It’s a question I get a lot this week. Here’s my answer.
Read moreMay 29, 2023
How to enhance your C# application with a large language model using Semantic Kernel
While chat applications have received much attention, there is so much more you can achieve by integrating language models into your projects. Imagine automating budgeting, generating engaging tweets, transforming documents, or creating compelling conference abstracts. Semantic Kernel offers a lightweight SDK that simplifies the process, allowing you to build language applications effortlessly. In this post, we'll explore how you can leverage Semantic Kernel to add powerful language skills, from installation to building skills and integrating them into your C# application. Unleash the potential of large language models and take your projects to new heights.
Read moreApril 23, 2023
Fun ChatGPT prompts to improve your Python code
Let's explore fun prompts for improving your Python code using GPT-4. These prompts include writing docstrings, writing automated tests, checking your code for optimizations and bugs, and refactoring a method. While GPT-4 could be better, it's a significant improvement over doing these tasks by hand.
Read moreApril 4, 2023
Quarkus: Java revisited!
I'm not a fan of Java, but I've given it another try with Quarkus, and it's pretty cool. In this guide, I'll show you how to create a new Quarkus project, explore its extensions, and build a microservice using DDD principles. Whether you're a seasoned Java developer or just starting, this guide will introduce you to Quarkus and what it can do for you. Let's dive in!
Read moreFebruary 27, 2023
Why You Need a Sandbox Separate from Your ML Pipeline to Create Successful Experiments
Machine learning operations (MLOps) is a rapidly evolving field that is transforming the way businesses approach data science. One of the most critical aspects of MLOps is the ability to create and test experiments quickly and efficiently. While it may be tempting to use your production ML pipeline as a testing ground, it's essential to have a separate sandbox environment for several reasons.
Read moreFebruary 16, 2023
Github Copilot: What you need to know to get started with AI-assisted programming
We’re starting with a pilot to test Github Copilot at Info Support. This is awesome news for us because we can now learn how much copilot is going to help us with our code. In the past few months, I’ve been testing Github Copilot on my own projects and learned a ton about things like use cases and plugins for various IDEs.
Read moreFebruary 2, 2023
Why a Data Fabric is Not Enough: The Importance of Human Expertise in Data Governance
Are you considering implementing a Data Fabric for your organization's big data management needs? Before making a decision, it's important to understand the limitations and challenges of this approach. In this article, we dive into why a Data Fabric is not enough to ensure the quality and accuracy of your data.
Read moreJanuary 13, 2023
Did you know DVC doesn't handle large datasets? Neither did we and here's how we fixed it
We hit a nice roadblock yesterday while working on a dataset with 5 million samples. It took us 8 hours to upload the dataset and 11 hours to download and unpack it. We learned some valuable lessons there that I’ll discuss in this post so you don’t have to run into the same issues.
Read moreJanuary 7, 2023
Building a custom Kubernetes operator in C#
Setting up environments in Kubernetes can be done in quite a few ways. You can use Helm, plain manifests, Kustomize and custom-built CLI tools. But what are you going to do after you’ve configured the environment? Read this post to find out how I used C# to write a custom operator in C# to manage my MLOps environment.
Read moreJanuary 5, 2023
How to configure memory limits in WSL2
One of the downsides to building machine learning models is that you need quite a bit of power in your machine. I've just upgraded my home desktop that I use for side projects and experiments to 64GB of memory because it was clearly no longer up to the task. However, when I booted up my WSL linux distro, it couldn't get more than 32GB of memory. Time to figure out how to fix that! In this quick post I'm showing you how you can limit or increase the memory available to your WSL2 distributions. Let's go!
Read more