Ken Collins

Product PageArcee Cloud is a fully Hosted SaaS platform offering end-to-end solutions for training, merging, and deploying custom Small Language Models (SLMs). Empower your organization with high-performance, domain-specific LLMs, accessible to businesses of all sizes. In late June we did a deep dive into Microsoft's & Apple'

Google's Gemma 2 9B is a recently released open-source language model that has garnered significant attention in our community. This lightweight model, is part of the Gemma family of models developed by Google. Despite its relatively small size, Gemma 2 9B has demonstrated impressive capabilities and performance that

A few weeks ago I had the opportunity to speak at Hampton Roads' premier developer conference, HR DevFest. Thanks to Custom Ink being a great community company, we got to discuss the Rise of AI Copilots using a basic framework to identify what evolutionary stage various AI industries or

A few weeks ago we explored using OpenAI's new Assistant's API to build a personal creative assistant capable of creating consistent on-brand artwork using Ideogram. Back then I promised we would explore expert-based architectures in a future post... and today is that day. 🥳 Two major updates

Everyone has their own unique learning style. I personally thrive on creating innovative tools and ideas, finding inspiration in the most unexpected places—be it a tweet, a snippet from a YouTube video, or the latest updates from fellow trailblazers in this exciting field. Remember, it is never too late

Better AI Images Chances are, if you're browsing an article online today, you're looking at an AI-generated image somewhere in that post. These images are typically clichéd and readily recognizable. They often feature a blue hue and depict scenes using robots or futuristic landscapes with brains

Welcome to the second part of this two-part series on using AWS Lambda to build a Retrieval-Augmented Generation (RAG) application with OpenAI. In this part, we will create a ChatGPT-style frontend that you can run locally to explore retrieval patterns with OpenAI & the Luxury Apparel dataset.

Welcome to my two-part series on using AWS Lambda to build a retrieval-augmented generation (RAG) application with OpenAI. In this first part, we will explore the basics of generative AI and retrieval. In the second part, we will build a RAG application using AWS Lambda, Express, and SQLite VSS.