The hidden Gem of AI interfaces: Open WebUI
Feb 10 · 9 min read · I've tried countless LLM interfaces over the past weeks, and honestly, most of them left me wanting more. Either they were locked behind paywalls, limited to single users, or they'd hallucinate so badly I couldn't trust the output. Then I discovered ...
Join discussion
🚀 7 Ways to Run Any LLMs Locally - Simple Methods
Jan 26 · 7 min read · A comprehensive guide to running Large Language Models (LLMs) locally on your machine using various tools and platforms. 🎬 Video Demonstration 1. 🦙 Ollama - The Dominant Local LLM Ecosystem Ollama is the dominant ecosystem for running LLMs such a...
Join discussion
Open Web UI with LiteLLM
Nov 5, 2025 · 2 min read · Let’s say you want a ChatGPT-like interface to access the models you’ve set up in LiteLLM. Let’s add that to the docker_compose.yaml that we’ve been building up. The first thing you’ll need is an API key access your LiteLLM server. To create one, go ...
Join discussion
Using Your Open WebUI from Anywhere
Oct 15, 2025 · 2 min read · Well, I exposed my Open WebUI server to the vast internet (for my personal use), and I thought I’d publish on how I did this. For dynamic DNS, I used DuckDNS, and to get a HTTPS-encrypted connection I set up Caddy. For both of these, I used a Raspber...
Join discussionUsing SearXNG with Quadlets
Oct 4, 2025 · 2 min read · In continuing with utilizing Quadlets to run containers, this post describes running a SearXNG server with a Podman Quadlet file. To start, you’ll need to create some config directories. I suggest the following. mkdir -p ~/.searxng/config ~/.searxng/...
Join discussionUsing Ollama with Quadlets
Aug 24, 2025 · 3 min read · There are numerous posts around the internet about getting Ollama running to do local AI, but not many seem to know about the convenience of Quadlets! Quadlets let you run Podman containers as systemd services. With my AMD GPU, I’m using the :rocm ve...
LLamri commentedSetting Up Your Self-Hosted AI Stack - Part 2: Document Processing and RAG with Apache Tika and Qdrant Vector Database
Aug 10, 2025 · 15 min read · What we're building today We're adding document processing capabilities to the foundation from Part 1. This extends your chat interface to work with your files and documents. Two key additions make th
FAFMI and 1 more commented
Setting Up Your Self-Hosted AI Stack - Part 1: Building the foundation with Open WebUI, Ollama, and Postgres
Aug 3, 2025 · 11 min read · What we're building today By the end of this post, you'll have a fully operational chat interface connected to the LLM of your choice, running completely locally. No external APIs, no data leaving you
Join discussion
I Asked My Brain “What Even Is RAG?” — and 10 Google Tabs Later, I Think I Know~
Jun 30, 2025 · 7 min read · Welcome back to my digital thought bubble — where tech meets “what am I doing again?” and somehow it all turns into a blog post. So here’s the deal: I’m currently interning (woohoo, real-world chaos unlocked), and my mentor gave me a task that sounde...
Join discussion