Introduction As technology continues to advance, organisations and developers are constantly seeking efficient, scalable, and cost-effective solutions for their applications. In this article, we’ll explore how to create a powerful, serverless AI bot by leveraging key Amazon Web Services (AWS) technologies like Lambda, Bedrock, and DynamoDB. Implementing this solution using serverless architecture is often more […]
Creating a Serverless AI Bot Fine Read More »
Introduction: In today’s competitive job market, efficiently matching candidates to job openings is crucial for both job seekers and employers. At Parser, we are continually exploring alternatives to improve our existing processes to address challenges like this one. With this idea in mind, we’ve developed a model using BERT (Bidirectional Encoder Representations from Transformers) and
Fine-Tuning BERT to Develop a CV Job Description Matcher Read More »
Large Language Models (LLMs) have emerged as powerful tools for understanding and generating human text across various applications. However, as these models grow, they become more complex and consume a lot of resources, similar to a monolithic application. This raises a key question: Is this the most efficient path forward, or is it time to
Rethinking LLMs: A Modular, Distributed Approach to AI Read More »
In today’s fast-paced financial services sector, the ability to efficiently connect with clients and manage interactions is crucial. Read about how Ascent Funding, a private financial services firm specialising in providing tailored loans for underserved students, as well as career-transforming bootcamps, leveraged the power of cloud-based communication services like Amazon Pinpoint and Amazon Connect to
Introduction In the ever-evolving landscape of digital banking, LiveOak Bank, a cloud-based bank serving small business owners across all 50 US states, stands out with its mission to be America’s small business bank. As part of a family of companies under the parent company Live Oak Bancshares (Nasdaq: LOB), they continually strive to redefine banking
Enhancing Lambda Performance and Optimising Costs Read More »
Generative AI, often referred to as deep learning models, stands at the forefront of technology, crafting high-quality content such as text and images based on the data on which it’s trained. You might already be acquainted with the acronym GPT, which stands for Generative Pre-trained Transformer. It’s rooted in LLM (Large Language Model), a sophisticated
Generative AI cost reduction using AWS BedRock Read More »
Introduction In the realm of AI solutions, where tools like ChatGPT streamline tasks, enhance quality, and offer assistance with undiscovered challenges, data security remains a significant concern. Join us as we unveil the strategic deployment of our custom Large Language Model (LLM), a solution meticulously crafted to amplify capabilities without compromising or risking data integrity.
Generative AI – Our journey into a custom LLM Read More »
Understanding the Virtual Private Cloud (VPC) components is key to learning how the networking works in the cloud. Keep in mind the cloud is a bunch of servers connected to the internet, and although you might think there is a weird magic behind it connecting all the dots, there is no magic, just a lot
In our previous chapter we talked about how to reach our EC2 instance into the public VPC and all the different components that are involved in that communication.But let’s complicate things a little bit more. What happens if our components are on the Private Network without access to the internet? When we look at this
Are you planning on migrating your On-Premise servers to the cloud and don’t know where to start? Here are a set of tips and checks based on our experience you should always keep in mind: 1- Are we migrating just the data or also the applications? This is probably the first thing you need to
Migrating On-Premise servers to the cloud Read More »
