Machine Learning

That state-of-the-art LLM embedding may not work for your use case — here is why

With LLM embedding-based applications, it’s quite easy to understand and apply semantic meaning in machine learning algorithms. For example, you can use text embedding to feed to a classifier for rating user sentiment on user feedback or use it for RAG-based semantic search, etc. We understand words by mapping them in different dimensions. For example, relative terms such as good, better and best or low carb vs high carb food. If we represent the word by rating these values in...

Read
Post Image

Enhancing Domain-Driven Design with Generative AI

Creating robust and maintainable applications that align closely with business requirements is a constant challenge in software development. Domain-Driven Design (DDD) has been quite successful in tackling this challenge. By placing the domain at the heart of the development process, DDD empowers developers to create highly scalable, modular, and business-oriented solutions. In this article, we will examine the potential of using Generative AI in Domain Driven Design. In our experiment, we developed a time-tracking application using Generative AI tools to...

Read
Post Image

An Agile Kickstart with Generative AI for Business Analysis

Image courtesy of Adobe Stock Leveraging artificial intelligence (AI) tools can significantly expedite the business analysis process. By utilising advanced AI models like GPT, analysts can quickly analyse problem statements, define high-level features and objectives, and generate epics and user stories. AI tools can streamline requirements gathering and save time and effort while enabling structured and organised analysis. As part of an exploratory exercise, we tried to find out how OpenAI's GPT can be leveraged to kickstart the business analysis...

Read
Post Image

Optimising Software Engineering Practices with AI

In the world of software development, Generative AI has been a topic of both excitement and concern. Its potential to automate and enhance various aspects of the development process raises questions about its impact on the developer community. As developers, it is crucial to understand the reality behind the hype and explore how Generative AI can be effectively utilised in real-world project scenarios.In this blog series, we capture our process and learnings from an experiment to develop a time-tracking application...

Read
Post Image

MLOps: Building a healthy data platform

You know that a term you coined has made it mainstream when people use it regularly in conversations and rarely understand what you meant. — Martin Fowler (paraphrased from an in-person conversation) Rouan summarises DevOps culture well in his post on Martin’s bliki. It is easy for developers to get disinterested with operational concerns. “It works on my machine” used to be a common phrase between developers in yesteryears. Some operations folks can also be less concerned by development challenges. Increased collaboration can help...

Read
Post Image

Data science-led, game-changing solutions to disrupt OOH media

Out Of Home advertising has seen rapid growth in the UK. In 2019, OOH advertising revenue rose 7.6% from 2018 to £1.3bn. However, OOH, by and large, has operated as an offline channel until recently. OOH agencies have been traditionally managing and running campaigns manually. From campaign planning to media buying, pricing, placement and tracking, every step of the process is manual. The lack of industry standards add another layer of complexity by creating information silos that in turn make...

Read
Post Image

The impact of the evolution of data on business

At the turn of the century, the internet made remote learning a reality. Propelled by the advent of cloud computing and AI coupled with burgeoning global internet penetration, the e-learning market grew at an exponential rate and became a $200 billion behemoth in two decades. The coronavirus pandemic further created an unprecedented demand for e-learning among students, corporates, and healthcare professionals. In the next five years, the industry is expected to nearly triple in size. At Sahaj, we believe it...

Read