Blog

The advent of large language models disrupted many fields. Software development was one of the most impacted. This makes a lot of sense. The overlap between AI and software development is large. AI folks understand software development pretty well, and they also wanted to solve their own problems. As a result, we can now choose from a plethora of AI-based tools promising productivity improvements in software development. We have: In-line code completion tools (GitHub Copilot or Augment Code) Chatbots answering our “How to …” questions (ChatGPT, Le Chat, or Claude)…

Testing is crucial for producing reliable software. As an industry, we know a lot about testing, or at least about testing conventional software. The recent democratization of AI and LLMs enabled developers and software companies to easily integrate text or image generation features into their products. LLMs possess unique properties that make testing LLM-powered software quite challenging. Why is this the case, and how can we test such software properly? Testing LLM-powered software is challenging for at least three reasons: LLMs usually produce unstructured and non-deterministic output. A small change…

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.

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…

A well-designed API is both an important business driver and a must if you want to split your software product into smaller modules. Whether you decide to deploy your app as a set of microservices or separate the client-side rendered frontend from the backend, you need to think about how the individual components will interact with each other. Externally, a high-quality API can be a huge selling point. This is especially true in the B2B world; letting customers access your service programmatically can help them improve their products or create…

At profiq, we are always interested in learning something new, and trying novel technologies. One of these technologies is Elixir—a functional programming language whose main strengths lie in fault tolerance and scalability through concurrency. This makes it a good candidate for backend development, especially when it comes to high-traffic web applications. We, for example, utilize Elixir’s properties in cooperation with Divvy to handle a large number of financial transactions. But, this, of course, is not its only use. As it turns out, Elixir can do a lot more. One of…

In an earlier article, we introduced you to Presto, an open-source, distributed SQL query engine. It lets you use SQL to query data from many types of storage solutions. This includes data sources that don’t support SQL natively; for example, a JSON file stored on AWS S3. What’s even more interesting, is that Presto lets you perform joins across multiple databases based on different technologies. In our view, Presto is a great tool for organizations that store their data in multiple data sources, and want to analyze this data without…