In an era where more than 80% of enterprises are expected to use Generative AI by 2026, up from less than 5% in 2023, the integration of AI chatbots is becoming increasingly common​. This adoption is driven by the significant efficiency boosts these technologies offer, with over half of businesses now deploying conversational AI for customer interactions. In fact, 92% of Fortune 500 companies are using OpenAI’s technology, with 94% of business executives believing that AI is a key to success in the future. Challenges to GenAI implementation The implementation of large language models (LLMs) an ..read more

Blend AI assistant concepts together This series of articles starts with a general chatbot description – what it is, how to deploy the model, and how to call it. The second part is about tailoring – how to teach the bot domain knowledge and how to enable it to execute actions. Today, we’ll dive into the architecture of the application, to avoid starting with something we would regret later on. To sum up, there are three AI assistant concepts to consider: simple chatbot, RAG, and function calling. I propose to use them all at once. Let’s talk about the architecture. The perfect one may look ..read more

Making the chatbot more suitable Recently we’ve built a simple chatbot, using an Azure-hosted GPT 4 Turbo instance. It’s a great starting point, but we definitely need more to fulfill any business requirements. Let’s try to talk with our bot. Prompt: Hi, I’d like to buy a new car. Can you assist me with a choice? I’m looking for a family car with a hybrid powertrain and all-wheel drive. I’m a fan of modern design and fancy features. My budget is around 70k euro. Completion: Absolutely, I’d be happy to help you find a suitable family car that meets your criteria! Given your preferences (…), the ..read more

Artificial Intelligence is everywhere – my laundry dryer is “powered by AI” (whatever it means), and I suppose there are some fridges on the market that take photos of their content to send you a shopping list and maybe even propose a recipe for your next dinner basing on the food you have. Some people say that generative AI and large language models (LLMs) are the most important inventions since the Internet, and we observe the beginning of the next industrial revolution. However, household appliances and the newest history deliberation are not in our sphere of interest. The article about AI ..read more

In the earlier article, we’ve covered the detailed architecture of a fleet management system based on AWS IoT and on-edge virtual networks. Now, we can dive into implementation. Let’s create a prototype of an edge network with two applications running together on both virtual and physical nodes and with isolated virtual networks. As we don’t have fire trucks on hand, we use three computers (the main truck ARM computer simulated by a Raspberry Pi and two application nodes running on laptops) and a managed switch to connect them together. Overview of topics and definitions used in the material I ..read more

Remote control over a vehicle is not a new idea; it has become a trend in the modern world. The idea of vehicle remote control is highly connected with vehicle telematics, which is used to gather data using GPS technology, sensors, and onboard diagnostics codes. Managed data can include vehicle location, driver behavior, vehicle activity, and real-time engine diagnostics. Further, the technology is managed on software platforms that help fleet owners manage their assets remotely. The data collected often includes vehicle location, fuel consumption, speeding, and maintenance information. But wh ..read more

Welcome to a short cycle of articles that shows a way to combine network techniques and AWS services for a mission-critical automotive system. We’ll show you how to design and implement an IoT system with a complex edge architecture. The cycle consists of three articles and shows the architecture design, a step-by-step implementation guide, and some pitfalls with the way to overcome these. Let’s start! AWS IoT usage to manage vehicle fleet Let’s create an application. But this won’t be a typical, yet another CRUD-based e-commerce system. This time, we’d like to build an IoT-based fleet-wise sy ..read more

Generative AI is quickly emerging as one of the key drivers of automotive innovation. This shift is not just a future possibility; it’s already happening. In 2023, the generative AI market in the automotive sector was valued at approximately USD 387.54 million. Looking ahead, it’s projected to surge to about USD 2,691.92 million by 2032, demonstrating a robust Compound Annual Growth Rate (CAGR) of 24.03% from 2023 to 2032. Major Original Equipment Manufacturers (OEMs) are integrating sophisticated AI algorithms into various aspects of the industry, from vehicle design to enhancing customer int ..read more

In this article, we’ll give an overview of the Quarkus framework and compare it with Spring Boot –  the most popular Java backend framework. Quarkus is an open-source Java framework for developing web applications. It is designed to build apps in a modern approach with microservices and cloud-native applications. Quarkus has built-in support for the two most popular package managers: Gradle and Maven. By default, a new starter project created using the official Quarkus CLI uses Maven, although it may be easily switched to generate a grade-based project instead. Features Comparison to Spri ..read more

Android Automotive OS, AAOS in short, is a vehicle infotainment operating system that has gained a lot of traction recently, with most of the OEMs around the world openly announcing new versions of their infotainment based on Android. AAOS is based on the AOSP (Android Open Source Project) source code, which makes it fully compatible with Android, with additions that make it more useful in cars – different UI, integration with hardware layer, or vehicle-specific apps. For OEMs and Tier1s, who are deeply accustomed to infotainment based on QNX/Autosar/Docker/Linux, and software developers worki ..read more