Quick post about a change I made that’s worked out well.

I was using OpenAI API for automations in n8n — email summaries, content drafts, that kind of thing. Was spending ~$40/month.

Switched everything to Ollama running locally. The migration was pretty straightforward since n8n just hits an HTTP endpoint. Changed the URL from api.openai.com to localhost:11434 and updated the request format.

For most tasks (summarization, classification, drafting) the local models are good enough. Complex reasoning is worse but I don’t need that for automation workflows.

Hardware: i7 with 16GB RAM, running Llama 3 8B. Plenty fast for async tasks.

  • irmadlad@lemmy.world
    link
    fedilink
    English
    arrow-up
    1
    ·
    2 hours ago

    In as much as I rail against regulation, or more so…over regulation, AI needs some heavy regulation. We stand at the crossroads of a very useful tool that is unfortunately hung up in the novelty stage of pretty pictures and AI rice cookers. It could be so much more. I use AI in a few things. For one, I use AI to master the music I create. I am clinically deaf, so there are frequencies that I just can’t hear well enough to make a call. So, I lean on AI to do that, and it does it quite well actually. I use AI to solve small programming issues I’m working on, but I wouldn’t dare release anything I’ve done, AI or not, because I can always see some poor chap who used my ‘code’, and now smoke is billowing out of his computer. It’s also pretty damn good at compose files. I’ve read about medical uses that sound very efficient in ingesting tons of patient records and reports and pinpointing where services could do better in aiding the patient so that people don’t fall through the cracks and get the medical treatment they need. So, it has some great potential if we could just get some regulation and move past this novelty stage.