My latest LinkedIn post on how teams need to learn to "think" in AI to build reasoning-based systems. https://www.linkedin.com/feed/update/urn:li:activity:7259561349947473920/ I hope you like it!

New LinkedIn post. Let me know what you think ... https://www.linkedin.com/feed/update/urn:li:activity:7234180533696548864/

This article provides an excellent overview of all the RAG components, techniques, and issues. https://towardsdatascience.com/17-advanced-rag-techniques-to-turn-your-rag-app-prototype-into-a-production-ready-solution-5a048e36cdc8

My day-job company posted a video interview on LinkedIn regarding a project I just completed. It was a perfect opportunity to repost. https://www.linkedin.com/feed/update/urn:li:share:7209917498735890435/ The video itself was posted on AWS, https://www.thecube.net/events/aws/financial-services-symposium/content/Videos/e0ad5225-02fe-4a8c-bb06-a7ea606561b7 I hope you like it!

OpenAI has some really nice APIs, but you have to pay for their service. It's the easy way. But, I wanted to run LLMs locally on my laptop. That way, I had much more control and could write code to learn more about how to make thing work. Here's how I did it. 1. Download and install Ollama, https://ollama.ai/ It runs on Mac (ARM, M1, M2, etc.) or Linux. Not Windows yet, but WSL should work. 2. Check out the models they have, https://ollama.ai/library 3. I've had good luck with the mistral model. Go to your command line and type ollama run mistral. There you go. Right on your laptop—your own LLM experience. There's a lot more I could add. If this is interesting, please send me a Like and ask your questions.