User Persona based Personalization of LLM generated Responses ChatGPT, or the underlying large language models (LLMs) today, are able to generate contextualized responses given a prompt. As a next step in the LLM evolution, we expect the responses to be more and more personalized with respect to the persona, conversation history, current conversation context and…

Over the past year and a half, I’ve been telling everyone I know about the potential of AI, especially with Large Language Models (LLMs). It’s time for everyone, regardless of their technical background, to learn the basics of LLMs and how to use them efficiently. In the 1960s we had the Moon. Today, we have…

Adding evaluation, automated data pulling, and other improvements. From Film Search to Rosebud 🌹. Image from Unsplash.Table of Contents Introduction Offline Evaluation Online Evaluation Automated Data Pulling with Prefect Summary Relevant Links A few months ago, I released the Film Search app, a Retrieval-Augmented Generation (RAG) application designed to recommend films based on user queries.…

Managing data models at scale is a common challenge for data teams using dbt (data build tool). Initially, teams often start with simple models that are easy to manage and deploy. However, as the volume of data grows and business needs evolve, the complexity of these models increases. This progression often leads to a monolithic…

AI for fun and profit! Photo by 🇸🇮 Janko Ferlič on UnsplashIn this article, we’ll explore how to leverage large language models (LLMs) to search and scientific papers from PubMed Open Access Subset, a free resource for accessing biomedical and life sciences literature. We’ll use Retrieval-Augmented Generation, RAG, to search our digital library. AWS Bedrock…

While we ingest the data from the API, we will apply some criteria. First, we will only ingest documents where the year is between 2016 and 2022. We want fairly recent language as terms and taxonomy of certain subjects can change over long periods of time. We will also add key terms and conduct multiple…

Intelligently synergizing dynamic programming and Monte Carlo algorithms R einforcement learning is a domain in machine learning that introduces the concept of an agent learning optimal strategies in complex environments. The agent learns from its actions, which result in rewards, based on the environment’s state. Reinforcement learning is a challenging topic and differs significantly from…

And stay competitive in a saturated job market Photo by Thomas Kelley on UnsplashWith AI productivity tools like Microsoft Copilot, ChatGPT, and many others emerging, some technology professionals have drawn concerns around their skill sets becoming obsolete. Since AI is still in its infancy, it’s impossible for anyone to predict exactly how the skill sets…

How simulations outperform traditional stats in that they are easier to understand, more flexible, and economically meaningful [Image by Author]Controlled experiments such as A/B tests are used heavily by companies. However, many people are repelled by A/B testing due to the presence of intimidating statistical jargon including terms such as “confidence”, “power”, “p-value”, “t-test”, “effect…

As many of you know, the 30-Day Map Challenge is a social media event where people passionate about maps create a topic-based design for 30 days in November. You can find more information about it on the official website. Just a few people handle creating a map that is fully presentable… Source link