Self-Hosting

Use PyInstaller to package Python programs as standalone executables. It works on Linux, Windows, and Mac.

Not the most efficient way, but usable.

There is a whole world of mainstream social networks platforms. And there is a small world of alternative platforms - fediverse. I will show how popular fediverse is.

Google is showing in search results some enhancements like Movie details, Job postings, Event and Course information, which it takes from website’s Structured Data. Here is - How to add Structured Data to the site using Hugo generator.

This Ollama CLI cheatsheet focuses on the commands you use every day (ollama ls, ollama serve, ollama run, ollama ps, model management, and common workflows), with examples you can copy/paste.

Not long ago was released. Let’s catch up and test how Mistral Small performs comparing to other LLMs.

Integration systems could be Commercial with a lot of paid connection modules and a bit of free ones; Or kind of free but with some strange license; Or ready for self-hosting and not.

YaCy is a decentralized, peer-to-peer (P2P) search engine that allows individuals and organizations to run their own search portals or join a global network of search peers.

Howto: installing Kubernetes using Kubespray, including setting up the environment, configuring the inventory, and running the Ansible playbooks.

Here is my k8s cheat sheet covering kubenetes most important commands and concepts from installing to running containers and cleaning up:

Recently Black Forest Labs published a set of text-to-image AI models. These models are told have much higher output quality. Let’s try them out

Testing how Perplexica performs with various LLMs running on local Ollama: Llama3, Llama3.1, Hermes 3, Mistral Nemo, Mistral Large, Gemma 2, Qwen2, Phi 3 and Command-r of various quants and selecting The best LLM for Perplexica

Awesome food is the pleasure for your eyes too. But in this post we will compare two AI-based search systems, Farfalle and Perplexica.

That’s very exciting! Instead of calling copilot or perplexity.ai and telling all the world what you are after, you can now host similar service on your own PC or laptop!

Recently we have seen several new LLMs were released. Exciting times. Let’s test and see how they perform when detecting logical fallacies.

I’ve tried different tools and came to conclusion I like floccus the most.

When I trained object detector AI some time ago - LabelImg was a very helpful tool, but the export from Label Studio to COCO format wasn’t accepted by MMDetection framework..