top of page
Embedded Systems


Vector Search Caching: Building Ultra-Fast Hybrid Vector Search with QCS6490, Zvec, and Qdrant with Qualcomm AI Hub for Industry 4.0
Introduction In the world of Industrial IoT (IIoT), a millisecond can be the difference between operational efficiency and a costly halt. We are entering the era of truly autonomous systems—devices that can see, hear, and understand their environment without constantly asking the cloud for permission. The key to this autonomy is efficient Vector Search on the Edge, along with an optimized on-device model for SOC However, running sophisticated vector similarity searches on a c
harshesh0
May 44 min read


The Importance of Choosing the Right SOC for Edge AI Devices
When building edge AI devices, the choice of System on Chip (SOC) is critical. The SOC acts as the brain of the device, handling everything from data processing to power management. Picking the wrong SOC can limit performance, increase costs, or reduce battery life. In this post, I’ll explain why selecting the right SOC matters, highlight key features to consider, and show how options like the QCS8250, QCS8550, and QCS6490 can make a difference. If you’re developing or evalua
harshesh0
Apr 124 min read


Unlocking the Power of Vibe Coding for IoT and Edge Devices
What is Vibe Coding? Vibe coding is a programming framework designed specifically for embedded systems, focusing on IoT and edge device development. It simplifies the process of writing, deploying, and managing code on hardware with limited resources. Unlike traditional coding methods that require extensive setup and complex integration, Vibe coding offers a modular and user-friendly environment. This framework supports various hardware platforms and provides tools to handle
harshesh0
Dec 11, 20253 min read


LLMs vs RAG: Why It Matters to IoT
In the ever-evolving landscape of the Internet of Things (IoT), understanding the tools and technologies that drive innovation is crucial. Two prominent approaches in Artificial Intelligence (AI) that are making waves today are Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG). Each approach has its strengths and weaknesses, especially when applied to IoT systems. In this blog post, we will compare LLMs and RAG, exploring their relevance to smart devices,
harshesh0
Dec 1, 20256 min read
bottom of page
