I spent a Saturday afternoon fighting a local RAG system with Open WebUI and Ollama that kept “forgetting” the PDFs I’d just uploaded, and the fix turned out to be something I’d never have guessed. Once you get the pieces lined up, this setup gives you a private, offline way to chat with your own … Read more
If you’ve been looking for a way to turn Obsidian into a private, AI-assisted knowledge base — one that doesn’t send your notes to a third-party server — setting up a local LLM alongside it is the way to do it. I spent a few evenings getting this working, and there were more rough edges … Read more
Got a CSV full of duplicate rows and no patience left for Excel’s “Remove Duplicates” button acting weird on you? Yeah, I’ve been there. You can actually remove duplicate rows from a CSV file with one ChatGPT prompt, and it works better than people expect — as long as you know what you’re asking for. … Read more
Converting a 300-page PDF into a searchable knowledge base with NotebookLM sounds like it should be a five-minute job, and for small files it basically is. But once I tried this with an actual 300-page technical manual, I ran into chunking limits, garbled OCR text, and source citations that pointed at the wrong page entirely. … Read more
If you’ve ever pasted the same 40-page spec into Claude for the fifth time in a week, Projects exist specifically to stop you from doing that. I started using them when a client project ballooned to about 80 documents — style guides, API references, internal policies, past meeting notes — and the copy-paste workflow became … Read more
Setting up an automated Gmail newsletter summarizer with N8N and Claude will save you hours of inbox triage every week. I built one after my newsletter subscriptions got out of hand — 20+ emails a day I actually wanted to read but never had time to. Here’s the full setup, including the parts that broke … Read more
Got Open WebUI running great on my home server, then immediately ran into the obvious wall — it only worked on my home Wi-Fi. First instinct was port forwarding, which I then learned is basically dead for a lot of people now thanks to Carrier Grade NAT. Tailscale ended up being the actual fix, and … Read more
If Ollama just told you it requires more system memory than what’s available and flat-out refused to load your model, you’re not imagining a bug — it’s doing exactly what it’s built to do when there isn’t enough RAM to safely hold the model. I hit this on a machine that, on paper, had plenty … Read more
I run Ollama on a 16GB laptop, and the first time I loaded a 13B model, my system basically choked — Chrome tabs crashed, Slack froze, and the fan sounded like it was preparing for takeoff. If you’re dealing with the same thing, reducing Ollama RAM usage on a 16GB laptop is mostly about picking … Read more
I tried loading the full DeepSeek-R1 model on my 6GB RTX 2060 laptop expecting it to just work, and instead got an out-of-memory crash before it even finished loading the model weights. If you’ve hit the same wall, the short answer is you’re not running the full 671B model on 6GB no matter what you … Read more