Have you ever jumped straight into coding, only to realize later that you built the wrong thing? - I have. Many times. In fact, I tend to do it so often that I’ve started thinking about why it happens—and how I can avoid it. One reason, I’ve found, is that I often get stuck drinking too much from the wrong mug. Wait, mugs? Yes, mugs. Let me explain. 🎩 First, a sip from Edward de Bono Let’s take a moment to appreciate the wisdom of Edward de Bono, a renowned psychologist and author who introduced the concept of “Six Thinking Hats.” His idea is that we can improve our thinking and decision-making by consciously adopting different perspectives, each represented by a colored hat. Each hat represents a different way of thinking: ...
In this article, I will introduce a development process can make an incredible difference in individual and team productivity. By focusing on getting feedback faster with this concept, my team and I have greatly increased our speed of delivery, and we are learning faster. The focus upon fast feedback is an important mindset that, although quite simple and basic, is often overlooked or down prioritized. By introducing the differentiation between inner and outer development loops, it becomes much easier to discover when faster feedback is needed and how to achieve it. I will introduce a development process tweaked for AI project. The framework will help you to identify what habits and practices to focus on to improve your development process both for traditional software development and for developing AI projects. ...
This article is on using a knowledge graph for improving on a RAG system for complicated interconnected product information. The article will cover the problems with RAG, why knowledge graphs might help, and I will try to cover some design challenges of using knowledge graphs. Knowledge Graphs (KGs): A graph-based data structure that represents knowledge in a domain. It contains concepts (i.e. products) and the relationships between them (i.e. a products applications or spare parts). Using knowledge graphs, we can provide LLMs useful context needed for answering questions about pumps. ...
One of the challenges we are faced with when building a chatbot is that questions the users ask the bot is highly unstructured. There are many ways different ways to ask for the same thing. Users can ask an extremely broad range of questions that require a diverse range of strategies to answer. The first step in building an helpful chatbot is to understand the user question well and putting it into a structured format that maps to entities that exist in the knowledge base. This can be done by doing intent classification and entity recognition. ...
There are many choices to take when choosing the architecture for an LLM application, should you create a RAG flow, an agents or what about multi-agent architectures? This post will give an overview of the different types of LLM agents and how, why and if they should be used. Is the technology mature to be used in production systems? What are the challenges and can they be overcome? An agent can be used when a task is too complex to be solved by a single recipe. When there are multiple reasoning steps to solve the problem, and the steps are not always the same. Agents are relevant when they are put into a dynamic environment, where the agent needs to learn from its environment and adapt to it. ...
For consumers of advanced technical products, finding and understanding product documentation and learning about the systems can be a daunting task. With a wide range of products and complex engineering knowledge required, both our internal teams and customers often struggle to get the information they need. To address this challenge, we are developing an advanced AI chatbot designed to simplify access to documentation and provide quick answers to technical questions. This solution aims to enhance both internal efficiency and customer satisfaction. Over the past seven months, significant progress has been made, and as the AI architect, I am excited to share the results and insights gained from this project. ...
One of the reasons for me to starting this blog is to start prioritizing time for myself, to develop myself, become more visible and cut out time to dive into things I am passionate about. A month of not taking any time for myself later - I must confess this is sadly not so easy. Work has an endless appetite. It feels like the more effort I put into it, the larger appetite it get. So if I keep feeding my projects at work over personal ambitions, I will never get any nurturing meals for myself. I need play! - for me play is essential. Play is a relaxed focus and curiosity and allow myself to move into new technologies and areas just for the fun of it. ...
There are plenty of resources on the internet about testing in software engineering. However, as a data scientist, the code you need to test is often very different: The functions often input and output complicated data structures like dataframes, arrays, tensors, etc. The code is often very slow to run (e.g. a model that takes hours to train) Results of a function can be non-deterministic (e.g. a random forest model or a api call to a ML-service) The code is often very coupled to the data (e.g. a function that does preprocessing of a dataframe) The code is often very coupled to the model (e.g. a function that trains a model) We often need to test the whole pipeline (e.g. a function that trains a model and then evaluates it) Note this article is about functional testing and not evaluation of the model. The goal of testing is to make sure the code works and keeps working. The goal of evaluation is to make sure the model is good enough for the business case. ...
Introduction As more and more business problems can be solved using large language models (LLMs) in chat or QnA systems, the question of how to evaluate them has become increasingly important. Without proper evaluation, it is difficult to know if the system are providing real value to the business and users, or just misleading them and potentially inflicting harm. ...
I have always wanted to specialize into a field and become an expert. But I have always been drawn into new areas where I could see a need for focus to create value in the projects I have been involved with. Now I have decided to own it and instead go for the opposite. To the degree that it informed the name for my personal blog. This blog is about my personal journey towards growing into an archetype role that I refer to as a “Full Spectrum Data Scientist”. It is the professional path that I have decided to travel. ...