<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Posts on Lance Carlson's Blog</title><link>https://lancecarlson.com/posts/</link><description>Recent content in Posts on Lance Carlson's Blog</description><generator>Hugo -- gohugo.io</generator><language>en-us</language><lastBuildDate>Fri, 15 Sep 2023 15:53:33 -0400</lastBuildDate><atom:link href="https://lancecarlson.com/posts/index.xml" rel="self" type="application/rss+xml"/><item><title>Setting up Ruby</title><link>https://lancecarlson.com/posts/setting-up-ruby/</link><pubDate>Fri, 15 Sep 2023 15:53:33 -0400</pubDate><guid>https://lancecarlson.com/posts/setting-up-ruby/</guid><description>So you heard about this really cool language called Ruby. Perhaps you&amp;rsquo;re here to learn Rails, or maybe you were enchanted by the elegance and simplicity that Ruby promises. Perhaps you&amp;rsquo;re a seasoned Rubyist and just got a new machine and need to set it up again (yay). Whatever the reason, we&amp;rsquo;ve got you covered. Let&amp;rsquo;s get your environment set up and ready to rock!
To install Ruby, I normally reach out to my favorite tool for the job: rvm.</description></item><item><title>Vector Database with Rails using pgvector</title><link>https://lancecarlson.com/posts/vector-database-with-rails-using-pgvector/</link><pubDate>Sun, 13 Aug 2023 00:00:00 +0000</pubDate><guid>https://lancecarlson.com/posts/vector-database-with-rails-using-pgvector/</guid><description>Imagine a system that not only stores data but grasps its very essence. A system that can swiftly navigate through myriad data points to pinpoint the most relevant. That&amp;rsquo;s the power of vector databases. They&amp;rsquo;re tailor-made for QA systems, acting as memory boosters for large language models. Their ability to seamlessly link questions to exact answers showcases their pivotal role in modern AI. I&amp;rsquo;m going to show you how you can setup your very own vector database using Ruby on Rails so you can ask your data questions!</description></item><item><title>Heroku Is Dead</title><link>https://lancecarlson.com/posts/heroku-is-dead/</link><pubDate>Thu, 29 Jun 2023 15:34:06 -0400</pubDate><guid>https://lancecarlson.com/posts/heroku-is-dead/</guid><description>UPDATE: In response to the clamor from its users, Heroku has made an announcement on July 28th 2023:
We are prioritizing this work and are now actively working on it! I will update with more information once we are working through readiness checks. Aiming to GA within the next quarter.
@bf4 You are right that this has been on our radar for a while. To be transparent, we are heavily investing (and prioritizing) in our Postgres infrastructure revamp work, which can provide better performance, more flexibility/elasticity, as well as solid foundation to build up more features, including more extensions (incl.</description></item><item><title>What is a Transformer?</title><link>https://lancecarlson.com/posts/what-is-a-transformer/</link><pubDate>Wed, 28 Jun 2023 00:00:00 +0000</pubDate><guid>https://lancecarlson.com/posts/what-is-a-transformer/</guid><description>The paper &amp;ldquo;Attention Is All You Need&amp;rdquo; kept coming up in my circles to read and I finally found time to look at it. It talks about a revolutionary architecture that has been a game-changer in the field, particularly when it comes to natural language processing. For those in the know, the concept is called a Transformer. It&amp;rsquo;s old news at this point, but for the uninitiated, what exactly is a Transformer, and how does it work?</description></item><item><title>Chatcopy - A ChatGPT Assisted Coding Utility</title><link>https://lancecarlson.com/posts/chatcopy-chain-of-thought-coding/</link><pubDate>Tue, 27 Jun 2023 00:00:00 +0000</pubDate><guid>https://lancecarlson.com/posts/chatcopy-chain-of-thought-coding/</guid><description>I was helping a colleague get setup with my semi-autonomous coding assistant utility called guppi recently and realized that he didn&amp;rsquo;t have access to GPT-4 through the API. GPT-4 is a lot better at coding. This got me thinking that I need to create a solution that works for him that he can use in Chat GPT directly (for now). So, inspired by the work I did on guppi, I made ChatCopy.</description></item><item><title>Openai.cr 0.3.0 Release</title><link>https://lancecarlson.com/posts/openai.cr-0.3.0-release/</link><pubDate>Fri, 23 Jun 2023 13:42:37 -0400</pubDate><guid>https://lancecarlson.com/posts/openai.cr-0.3.0-release/</guid><description>Functions! We love when our jobs are made easier. Recently OpenAI announced the support for functions on their blog. Functions allow you to specify the structure of your output in a JSON compatible format. In the past, you&amp;rsquo;d have to wrangle the output by asking the GPT API to return a computer readable format like YAML or JSON, and specify the fields in natural language. The output would be unreliable. Most of the time I would resort to asking for YAML and I&amp;rsquo;d have to be very specific about the kinds of fields I would get back so I would get consistent results.</description></item><item><title>OpenAI Crystal Library</title><link>https://lancecarlson.com/posts/openai-crystal-library/</link><pubDate>Wed, 21 Jun 2023 11:23:32 -0400</pubDate><guid>https://lancecarlson.com/posts/openai-crystal-library/</guid><description>Hello everyone! I&amp;rsquo;ve been developing a new library for OpenAI in Crystal Lang.
My fascination with autonomous systems led me to create a semi-autonomous assistant to aid my coding process. There was an existing OpenAI library in Crystal, but it didn&amp;rsquo;t quite meet my needs and lacked some key features. The most significant addition I&amp;rsquo;ve made is streaming, which is necessary for streaming code output to the user that guppi is writing.</description></item></channel></rss>