how-to

Unlock home GPU power for cloud workloads with Tailscale and Docker. I demo a simple architecture that tunnels requests to your local rig, skipping pricey cloud GPUs. All ports stay hidden, ensuring a tight, cost-effective environment.

Discover how to securely manage secrets in NixOS Home Manager using SOPS and sops-nix. Learn to set up Age encryption, create encrypted secret files, integrate SOPS with NixOS, and access secrets as environment variables. Perfect for maintaining secure, declarative NixOS configurations.

Learn how to install a custom Hugging Face GGUF model using Ollama, enabling you to try out the latest LLM models locally. This guide covers downloading the model, creating a Modelfile, and setting up the model in Ollama and Open-WebUI.

Discover how to create a synthetic dataset, select the right metrics for evaluation, and fine-tune your model using LoRA for a narrow scenario. Plus, learn how to serve your model efficiently using LLaMa.cpp on Mac/Linux.

Learn how to use Python with Supabase for web development for all your AI/LLM backend needs. Create a secure Python service that validates JWT tokens from Supabase and integrates with Next.js.

ElasticSearch [http://www.elasticsearch.com/products/elasticsearch/] is a document database, not in the typical sense, topped up with a Lucene [http://lucene.apache.org/] for doing free form text search on your document. This is kind of the storage you want to use if you expect a lot of