Blog

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…

If you want to improve your product by developing new AI features built on top of large language models (LLMs), you have many options to choose from. GPT models from Open AI are often considered the go-to solution for most use cases. But the competition in this space is heating up. Other proprietary solutions such as Gemini from Google or Claude from Anthropic are catching up in terms of quality, features, and pricing. There are also many high-quality open-weight models such as Llama-3.1 from Meta or the Mistral family from…

Are you developing an application and looking to integrate large language model (LLM) features? With multiple options like GPT, Gemini, Claude, and open-source models from Hugging Face, choosing the right solution can be overwhelming. Each model offers unique strengths, from GPT's versatile text generation to Claude's detailed descriptions, and an open-source model's flexibility. Integrating LLM features can significantly enhance your application by providing capabilities such as natural language understanding, text generation, and intelligent automation. To make an informed decision, it’s essential to evaluate your application's specific needs, compare model performances,…

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.

For a long time, we have dreamt about systems able to answer questions related to a set of text documents — a next-gen search engine. As developers, we spend a significant portion of our time reading through documentation, trying to solve a specific problem. We are not alone. People in many other fields face similar problems. Addressing this issue could save an immense amount of time. The problem of answering a question from a set of text documents has been studied for quite some time. However, only the recent improvements…

More and more companies are integrating machine learning (ML) and artificial intelligence (AI) into their products. Last year was unusually fruitful. We experienced the release of Github Copilot, DALL-E 2, Stable Diffusion, ChatGPT and many other interesting AI services. Getting your company onboard with ML and AI can be challenging. The number of experts in this field is still far below market demand. The path to become an AI professional is rigorous and long. You need to master aspects of software engineering, database and big data management, statistics, and many…