Self-Hosting

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:

Here is a Docker cheat sheet covering the 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.

When I started experimenting with LLMs the UIs for them were in active development and now some of them are really good.

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..

Testing how models with different number of parameters and quantization are behaving.