Posts

Intro Large language models (LLMs) are impressive, capable of generating human-quality text, translating languages, and answering questions. However, there’s a catch: they are limited to the data they were trained on. This means their knowledge can be outdated and they may struggle with topics that emerged after their training. But what if we could give our LLMs access to the vast ocean of information available on the web? This powerful combination would allow your local LLMs to:...

Introduction In the world of software development, there are many different approaches to building applications. One approach I’ve had the pleasure of using is called “schema first development”. This approach emphasizes defining the verbs, routes, request and response structures before diving into writing code. This methodology proves especially beneficial when developing HTTP REST services. Benefits Instead of jumping straight into coding, schema first development encourages you to start by creating a formal specification of your API using a standardized format like Open API (formerly known as Swagger)....

Introduction Living in a house without central air, I’ve dreamed about getting heat pumps and mini splits installed. Until I can pull the trigger on that large project. Types of AC Units I’ve made peace with considering window AC units, which come in two main styles: window AC: They sit in your window sill. Part of the unit is inside and part of the unit is outside. portable AC: They sit entirely inside your home....

When writing software, we often need to handle various types of input arguments. To maximize flexibility and ease of use, I propose prioritizing the following methods for accepting arguments: Command-line arguments Environment variables Default hard-coded values As we move down the list, the flexibility of defining these values decreases. Command-line Arguments Command-line arguments offer the highest level of flexibility and are the easiest for end users to provide. They can be specified directly at the terminal or included in scripts that call your program....

Privately chat with your own data using RAG.

Allowing you to spin up multiple cloned VMs

A walk through of how I run LLMs locally, in a Crew-like fashion.

How to self host a web UI to interact with LLMs, local or remote

How to easily run local LLMs

A full example of this repository can be found on my Github here. I often find myself exploring data using Python, Jupyter Lab, Pandas and various graphing programs. This has caused me to want to have a light weight, easy to use, and portable approach to standing up these tools. In the past, I have found myself using tools like pyenv to install a desired version of python for each project....