Blog

In this video demo, profiq engineer Viktor Nawrath explores the intricacies and the realities of AI Computer Use, offering viewers a better understanding of what is possible when applying language models to control their computers and the benefits of doing so. Learn how AI can interact with computers as a human would, highlighting the strengths, challenges, and future developments of this technology. Highlights from the demo: AI-Powered Computer Control: Overview of using language models to automate tasks and control a computer. Evolution from HTML to Visual-Based Automation: Transition from text-based…

In this technical video demo, Pavel Balcárek, a software engineer at profiq walks through some foundational concepts for working with Go (Golang) to create HTTP servers, handle JSON, and even render simple web pages. If you're looking to deepen your understanding of Go's capabilities and standard library, this session offers plenty of practical value.  Here's a highlight of what you'll learn in the video: 1. Building an HTTP Server  Discover how to set up a basic HTTP server using Go's robust standard library. The demo illustrates why learning the fundamentals…

As 2024 winds down, we’re excited to share our Top 5 blogs of the year, hand-selected by our team for their relevancy, innovations, and practicality for software developers. These blogs cover a wide range of topics from how to write better code and leveraging AI, to developing custom voice models and improving elder care communication. Each post offers actionable tips, real-world case studies, and expert perspectives that are sure to inspire and empower developers, engineers, and tech enthusiasts alike.  At the top of our list is Hana Klingova’s practical and…

In recent years, the rise of synthetic voice technology has opened up new possibilities for a variety of voice-based applications. Whether it's creating personalized voice assistants, enhancing accessibility tools, or developing unique AI-driven experiences, the potential is vast. But how easy is it to create a custom voice AI model that runs locally on your computer, without relying on cloud services? Applio offers a powerful, open-source solution making training and using a custom voice model accessible to everyone—from developers to creative teams. Unlike cloud-based alternatives, Applio does not require an…

In recent years, large language models (LLMs) have revolutionized the way we interact with technology. From enhancing productivity to enabling creative applications, their potential is vast. How challenging is it to run a powerful LLM directly on your PC or laptop? LM Studio is a user-friendly app that allows you to easily manage and run LLMs on your computer. It offers a streamlined interface, making it accessible even for those new to machine learning. In this video tutorial, Miloš Švaňa walks users through how to choose, download, and run an…

AI Developer Tools With the rapid advancements in large language models (LLMs) over the past few years, we’ve seen a surge in AI-powered developer tools. Since code is essentially text, it’s an ideal use case for LLMs. While there are many tools available to assist with software development, let’s focus on the most impactful ones: code completion and code manipulation tools. The most well-known tool in this space is GitHub Copilot, which gained immense popularity as one of the first to hit the market. However, there are now several new…

New frameworks and tools are constantly emerging, each promising to make our lives easier and our applications faster. But every so often, a framework comes along that doesn’t just promise incremental improvements—it redefines the game. Qwik is one such framework: built by performance nerds, for performance nerds.  Qwik introduces novel architecture that eliminates the need for the traditional UI hydration process, a step that often bogs down web apps with unnecessary overhead. Instead of rehydrating the entire UI on the client side, Qwik only activates the parts of the application…

In this article, we are going to talk about three tools that can, at least in theory, force any local LLM to produce structured output: LM Format Enforcer, Outlines, and Guidance. After a short description of each tool, we will evaluate their performance on a few test cases ranging from book recommendations to extracting information from HTML. And the best for the end, we will show you how forcing LLMs to produce a structured output can be used to solve a very common problem in many businesses: extracting structured records from free-form text.

Me and many of my colleagues at profiq use Notion for note-taking and work organization. Our workspaces contain a lot of knowledge about our work, plans, or the articles or books we read. At some point, a thought came to my mind: couldn’t we use all this knowledge to come up with project ideas suited to our skills and interests?

It has been over a year since OpenAI introduced ChatGPT and brought the power of AI and large language models (LLMs) to the average consumer. But we could argue that introducing APIs for seamlessly integrating large language models into apps developed by companies and independent hackers all over the world can be the true game changer in the long term. Developers are having heated discussions about how we can utilize this technology to develop truly useful apps that provide real value instead of just copying what OpenAI does. We want to contribute to this discussion by showing you how we think about developing autonomous agents at profiq. But first a bit of background.