Personal Projects and Fun Stuff
-
Prompting Local Models with Node.js and Ollama’s API – Classifying Food Items
I’ve created a script to scrape local flyer data. It’s a great start for a larger project but it gets all items in the flyer. When it comes to stores that sell groceries and non-edible merchandise, the list is full of potentially unwanted items. The goal of this project is to create a meal plan…
-
Building a Semantic Search for Subtitles with Python, Streamlit, and PostgreSQL
Since I’ve got the tools to create GIFs, I needed a way to find these clips in videos. In a movie for instance, Office Space, I remember a scene where Peter was talking to his neighbour about getting out of working the weekend. The phrase “I’m doing the drywall at the new McDonald’s” was somewhere…
-
Using FFMPEG to Slice a Video
There’s plenty of software out there that will allow you to record a slice of a video. I like command line tools for this sort or thing because I find they often are a little more flexible and precise. I also hope to use some of these command line tools in a future automation. That…
-
Use Less Common or Customized LLMs in Ollama and Docker
This is sort of a continuation of my previous post on how to get Ollama and Open WebUI running using Docker found here. So, you’ve got a way to access LLMs to chat, but you’re using Ollama and there’s a subset of models that are easy to pull and serve. But HuggingFace has all these…
-
Creating GIFs from Video with FFMPEG
I love reacting with GIFs, pretty much every chance I get. There’s a ton I still don’t understand about my brain, but I find it very easy to relate a situation to a clip from a show or movie I’ve watched. This leads me to search the internet for this very specific scene and I…
-
Private LLM Chats with Ollama and Open WebUI – including LLaMa 3.1
Perhaps you’re concerned about chatting with one of these publicly hosted LLMs, or you’ve continuously hit your limit on the number of questions asked. These are just a few of the reasons you may want to run an LLM locally. I’ll be using docker to run these applications because I like being able to easily…
Got any book recommendations?