Literate programming is now a reality through nbdev and the new visual debugger for Jupyter. — Notebooks have always been a tool for incremental development of software ideas. Data scientists use Jupyter to journal their work, explore and experiment with novel algorithms, quickly sketch new approaches and immediately observe the outcomes. However, when the time is ripe, software developers turn to classical IDEs (Integrated Development Environment)…

Turn your Windows machine into a developer workstation with WSL 2. — I used to have an Apple laptop as my daily driver. I could do almost everything there; development, proposal writing, music composition etc. But the fear of vendor lock-in, the concern that I am depended on Apple’s whims and vices — which are arguably very expensive — led me to…

Data Preparation: Dive Deeper, Optimize your Process, and Discover How to Attack the Most Crucial Step — Imagine investing a full day fine-tuning BERT, only to hit a performance bottleneck that leaves you scratching your head. You dig into your code and discover the culprit: you just didn’t do a good job preparing your features and labels. …

From Text to Tokens: Your Step-by-Step Guide to BERT Tokenization — Did you know that the way you tokenize text can make or break your language model? Have you ever wanted to tokenize documents in a rare language or a specialized domain? Splitting text into tokens, it’s not a chore; it’s a gateway to transforming language into actionable intelligence. …

Demystifying BERT: The definition and various applications of the model that changed the NLP landscape. — Part II and Part III of this story are now live. A few weeks ago, I trained and deployed my very own question-answering system using Retrieval Augmented Generation (RAG). The goal was to introduce such a system over my study notes and create an agent to help me connect the…

Decoding the art and science of prompt engineering, the secret sauce for supercharging Large Language Models. — Who would’ve thought crafting perfect prompts for Large Language Models (LLMs) or other generative models could actually be a job? As a matter of fact, a high-paying one! That was my initial reaction when I first tripped over this relatively new kid on the AI block called “prompt engineering.” …

How function calling paves the way for seamless integration of Large Language Models with external tools and APIs — The moment I discovered that Large Language Models (LLMs) had gained the ability to interact with external tools and APIs, I knew nothing would ever be the same. Does this move us closer to achieving Artificial General Intelligence (AGI)? Maybe not, but it undeniably ushers in a whole new era…

Discover the mechanics behind Kubernetes authentication and learn how it ensures secure access to your cluster. — Kubernetes is the most popular open-source system for automating deployment, scaling, and management of containerized applications. To make every operation easier, Kubernetes provides a CLI tool called kubectl. …

Is GPT-4 the next big step in AI we were all waiting for? — Today, I woke up, and the hashtag #gpt-4 was trending on Twitter. Immediately, I thought that OpenAI released the next version of the most popular language model, and people were going mad about it. So, I started reading the top threads on this topic. …