Asking the LLM to self-diagnose and self-correct the prompt to improve answer quality. — Retrieval Augmented Generation (RAG) is undoubtedly a powerful tool, easily crafted using frameworks like LangChain or LlamaIndex. Such ease of integration might give an impression that RAG is a magic solution that is easy to build for every use case. However, in our journey to upgrade our editorial article search…

Using hybrid search, hierarchical ranking and instructor embedding to address domain-specific documents that bear similarities for our RAG setup. — Carsales stands as a leading automotive platform, serving the car and lifestyle vehicle markets across Australia, Chile, South Korea, and the United States. Our ambition is to redefine the car buying and selling experience, setting unparalleled standards. To this end, one…

Utilising the fine-tuned Stable Diffusion 2.1 on Amazon SageMaker JumpStart, I developed an AI tech called Owly that crafts personalised comic videos with music, starring my son’s toys as the lead characters — Every evening, it has become a cherished routine to share bedtime stories with my 4-year-old son Dexie, who absolutely adores them. His collection of books is impressive, but he’s especially captivated when I create tales from scratch. Crafting stories this way also allows me to incorporate moral values I want…

How I built a robotic teddy bear that can move its head and converse naturally. — I had a pretty long three-week Christmas break, and despite spending most of this time with my family, I had some time to kill about a week before the end of the break, so I decided to build something fun! I always wanted to find a good use case for…

Career development and progression have many forms and are subjective to individuals. For some it can mean stepping up the ladder, leading a bigger team or focusing on being an individual contributor. Don’t copy others or expect others to tell you, but find which pathway fits you and that you…

Model registry is a centralised repository to store our models. Why do we need one? Why can we not just store them on our laptop? We take a walk through a Machine Learning Development Life Cycle (MLDLC) to answer these questions — Searchable centralised storage MLDLC consists of two phases: experimentation followed by product-ionisation. During experimentation, data scientists build many models using different datasets, algorithms and hyper-parameters with the goal of finding the best model. In their Jupyter notebook, they record the metrics for each model and comment on what they learn about it. Should…

Using a pose estimation model, an object detection model built using Amazon SageMaker JumpStart, a gesture recognition system and a 3D game engine written in OpenGL running on an NVIDIA Jetson AGX Xavier, I built Griffin, a game that let my toddler use his body to fly as an eagle in a fantasy 3D world. — My wife and I have a super active 2.5-year-old boy named Dexie. He loves animals, and one of his favourites is the eagle — he often cruises around the house pretending to fly like one.

I used the knowledge and wisdom I gained from my work in Artificial Intelligence to understand and teach my two-year-old son more effectively and regain my sanity. — Overview The knowledge I have gained from building Artificial Intelligence (AI) tech is directly applicable to raising my toddler. Not only does it help me teach him more effectively, but it also helps me understand why he does naughty things, which I had previously thought he did merely for the sake…

I used a Neural Machine Translation model trained on Amazon SageMaker, Amazon Polly, Google Speech API, and an audio routing tool, to build Jarvis — a chatbot who can talk to you in a video conference call. — Carsales.com, the company I work for, is holding a hackathon event. This is an annual event where everyone (tech or non tech) comes together to form a team and build anything — anything at all. Well, preferably you would build something that has a business purpose, but it is really…