View this email in your browser

Build5Nines Newsletter

Your trusted source for Cloud, DevOps, and SRE guidance with Chris Pietschmann! Thank you for subscribing to the Build5Nines Newsletter!

Empowering SRE’s with Generative AI

In the ever-evolving landscape of technology, the role of Site Reliability Engineers (SREs) is becoming increasingly complex and critical. As organizations strive for higher reliability and performance in their systems, the integration of generative AI technologies, such as those offered by OpenAI and Microsoft Azure OpenAI Service, have the capability of revolutionizing the roles of SREs. There are even tools like Ollama that allow you to run Microsoft’s Phi-3 Mini small language model (SLM) on any machine. Also, the availability of GitHub Copilot Chat is brining a new level of AI usefulness from anywhere.

Generative AI has made significant advancements in recent years, with models like OpenAI’s GPT-4 demonstrating an exceptional ability to generate human-like text, code, and more. Using Azure OpenAI Service, integrated with enterprise systems, has the ability to provide tools that streamline complex tasks and foster a more efficient workflow.

The more you integrate the use of AI prompting into your daily workflow, you will see increases in productivity and overall creativity. The AI can offer you a Junior SRE of sorts to bounce ideas off of. I mention Junior SRE, not Senior, since you need to explain clearly to the AI prompt what you want, to help it generate the response that best fits what you’re looking for. The more you talk to the AI as if it were a person, the better the response will be. The reasons for this are because the LLMs are trained on human text, so if you talk like a human it’ll understand how to respond.

In my personal experience, I haven’t replaced the Google search with using ChatGPT or other LLMs just yet. What I do is augment my search with the use of AI too. Sometimes I start with asking the LLM my technical question about Terraform, Node.js, Python, Azure CLI, or some other SRE related task. Then I will verify the response with a Google search to make sure it’s giving accurate information, and sometimes it does give an AI hallucination; although it’s definitely in the right direction.

Overall, AI is a great tool to help increase productivity and creativity with it suggesting solution ideas that you may not have thought about. You can even ask it for an alternative solution to get more ideas. The power is in the prompting, and developing a style that works is definitely a skill you’ll develop over time as you use the tools.

I’m hoping these insights from my own AI experience helps, along with the other links in this issue of the Build5Nines Newsletter.

Thanks!
Chris Pietschmann

Run Your Own Local, Private, ChatGPT-like AI Experience with Ollama and OpenWebUI (Llama3, Phi3, Gemma, Mistral, and more LLMs!)

Over the last couple years the emergence of Large Language Models (LLMs) has revolutionized the way we interact with Artificial Intelligence (AI) systems, enabling them to generate human-like text responses with remarkable accuracy. From powering chatbots and virtual assistants to aiding in natural language processing tasks, LLMs have found widespread applications across every industry. However, as their capabilities continue to grow, so do concerns surrounding data privacy and productivity.

Now with two innovative open source tools, Ollama and OpenWebUI, users can harness the power of LLMs directly on their local machines. Ollama, short for Offline Language Model Adapter, serves as the bridge between LLMs and local environments, facilitating seamless deployment and interaction without reliance on external servers or cloud services. Complementing Ollama is OpenWebUI, a user-friendly interface that simplifies communication with local LLMs, enabling users to engage in natural language conversations effortlessly.

In this article, we’ll look at running your own local ChatGPT-like app using both Ollama and OpenWebUI, enabling the use of multiple LLMs locally; including Microsoft’s Phi-3 SLM (small language model). We’ll also explore the benefits of bringing powerful AI capabilities to your local machine, including enhanced privacy and productivity. Additionally, we’ll look at the introductory steps to get started with setting up and using Ollama and OpenWebUI on your own local machines, paving the way for a seamless and personalized AI experience tailored to your needs and preferences…

GitHub Copilot Chat – AI Coding Assistant Anywhere in the GitHub Mobile App

GitHub Copilot Chat is a chat interface that let’s you interact directly with GitHub Copilot from within the GitHub Mobile app. It empowers developers to ask and receive answers using an AI that is trained using a combination of natural language processing and machine learning that’s built specifically to help developers be more productive with answering coding related questions. GitHub Copilot Chat can answer a wide range of questions on topics like syntax, programming concepts, test cases, debugging, and other coding-related topics…

Microsoft Copilot for Azure: Your AI-Powered Cloud Companion

Microsoft Copilot for Azure, the innovative AI companion that is revolutionizing the way we interact with cloud infrastructure and services. In the ever-evolving landscape of cloud management, IT professionals in DevOps Engineer and SRE roles are constantly seeking ways to streamline their workflows and enhance productivity. Copilot for Azure will help you design, operate, optimize, and troubleshoot your cloud infrastructure and services with the power of cutting-edge LLMs (Large Language Models) combined with the Azure Resource Model…

Terraform: Modules using Git Branch as Source

HashiCorp Terraform empowers DevOps Engineers and SREs to manage cloud resources efficiently. One of its standout features is the Terraform Modules support, allowing users to organize and reuse infrastructure code effectively as reusable modules. While Terraform’s native module registry serves as a central hub for sharing modules, sometimes you may prefer hosting modules in your own Git repository for greater control and flexibility.

In this article, we’ll look at how to leverage Git repositories as sources for Terraform modules, enabling seamless integration of your infrastructure code with version control systems like GitHub and Azure DevOps Repos…

Interested in sponsorship opportunities? Please contact us for more information about sponsoring both the website and this newsletter.