Apotrox

+1, i just want to create filament profiles. Not tie them to anything. maybe being able to create copies for different colors/variants. Don't make me tie them to a printer...

To follow up on this, changing the USER to root at the bottom appears to fix the permission error. Now im running into a `RuntimeError: Failed to load shared library...

Another update: decided to try `docker compose up` and that worked flawlessly. no errors. models are loading fine. application is running. i don't know why that worked, as i don't...

Reopening this as pulling the updated repo resulted in having the same issue, libllama and libcuda couldn't be found. Did update the edited files again.

hey @lukaboljevic, concerning the new docker compose, is your snippet all thats in there or did you add the content of the previous file too?

you wanna run the scripts/setup before privategpt

So far i changed the models (LLM and embedding) in the settings.yaml and settings-docker.yaml, and after running `docker compose run --rm --entrypoint="/usr/bin/env python3 scripts/setup" private-gpt` it seems to at least...

#1445 holds the answers you seek, i think.

Hey @Robinsane, trying your suggestion didn't fix it for building the image for me. Now im trying to compose up, but get told ``` invalid interpolation format for services.private-gpt.local.llm_hf_repo_id. You...

@Robinsane thanks lots for that pointer! While i struggled to get it running as imartez described, i changed the `docker compose run --rm --entrypoint="bash -c '[ -f scripts/setup ] &&...