49
n8n + Ollama: self-hosted AI automation that actually works (discuss.tchncs.de)
submitted 7 months ago by to c/selfhosted@lemmy.world
15 comments fedilink hide all child comments
 

Been running n8n with Ollama for a few months now for work automation. Wanted to share what I've learned since it's not super well-documented.

The setup is just Docker Compose with n8n + Ollama + Postgres. n8n's HTTP Request node talks directly to Ollama's REST API — no custom nodes needed.

What I'm running:

  • Email digest every morning (IMAP → Ollama → Slack)
  • Document summarization (PDF watcher → Ollama → notes)
  • Lead scoring from form webhooks

Zero API costs, everything stays on my server. If anyone wants the workflow templates I have a pack: https://workflows.neatbites.com/

Happy to answer questions about the setup.

all 15 comments

sorted by: hot top controversial new old
[–] 11 points 7 months ago (6 children)

Happy to answer questions about the setup.

Tell me about the hardware, please and thank you.

  • permalink
  • fedilink
  • source
  • hideshow 6 child comments
    •
  • [–] 4 points 7 months ago (4 children)

    Piggybacking too as I am considering the same. Please OP and thank you.

    And what model class are you using? Lightweight (2B), reasonable ~10B or above 32B?

    Do they load fast?

    I had a look at NetworkChucks setup and don't think I can afford an overpowered rig in this economy. Depending on the rig, may have to wait >20s for a prompt answer.

    Thank you again!

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 4 child comments
    •
  • [–] 3 points 7 months ago (3 children)

    I was playing with ministral-3 3b on a 3060. It loads pretty quick, but response generation is a bit slow. It starts responding nearly instantly once the model is loaded (which is also quick), but for long responses (~5 paragraphs) it may take 15-20 seconds for the whole thing.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 3 child comments
    •
  • [–] 4 points 7 months ago (2 children)

    Cries in 1070

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 2 child comments
    •
  • [–] 2 points 7 months ago

    I do something similar with the base model m4 Mac mini. It's my inference box right now, it handles Immich ML, photo prism AI, and runs Ollama talking to a small web app I call to summarize things. It's summaries are shit. The bigger the model, the more it hallucinates. So I settle for 1B and 4th grade responses

  • permalink
  • fedilink
  • source
  • parent
    • [–] 7 points 7 months ago

    I really like n8n. It appeals to my visual sense which makes up for a lot of hard programming experience. I don't run it full with the AI aspect. Not because I have some agenda against AI, but that my equipment is not good enough to run AI efficiently. I use it for a lot of automation around the lab.

  • permalink
  • fedilink
  • source
    •
    [–] 6 points 7 months ago (1 child)

    What model do you mostly use for those tasks

  • permalink
  • fedilink
  • source
  • hideshow 1 child comment
    •
    • [–] 6 points 7 months ago (1 child)

    What is n8n?

  • permalink
  • fedilink
  • source
  • hideshow 1 child comment
    •
    • [–] 2 points 7 months ago (1 child)

    Has anyone tried ActivePieces? How does it compare?

  • permalink
  • fedilink
  • source
  • hideshow 1 child comment
    •
  • [–] 1 point 7 months ago

    Briefly. I didn't like it as much as I like n8n. Perhaps it was not suitable to my use case. I hear a lot of good things about ActivePieces tho. You know, give it a spin and see if it gehaws with your flow. From what I understand, both can acomplish about the same. I think ActivePieces is geared more towards cloud deployments whereas n8n keeps things local.

  • permalink
  • fedilink
  • source
  • parent
    • [–] -1 points 7 months ago

    Ollama has long history of exploits. PLease do not feed anything which come from outside to it.

  • permalink
  • fedilink
  • source
    •