Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[QUESTION] cannot change settings when using docker compose #2103

Open
Just-enki opened this issue Oct 16, 2024 · 1 comment
Open

[QUESTION] cannot change settings when using docker compose #2103

Just-enki opened this issue Oct 16, 2024 · 1 comment
Labels
question Further information is requested

Comments

@Just-enki
Copy link

Just-enki commented Oct 16, 2024

Problem

Im using docker to set up a local Pgpt based chatbot. Im creating a docker container with sudo docker compose --profile llamacpp-cpu up as defined in docker-compose.yaml . This starts the container with the default settings which to my understanding should be overwritten by settings-local.yaml, logs below.

private-gpt-private-gpt-llamacpp-cpu-1 | 10:25:27.459 [INFO ] private_gpt.settings.settings_loader - Starting application with profiles=['default', 'local']

Ive changed values in both settings.yaml as well as settings-local.yaml and recreated the container using sudo docker compose --profile llamacpp-cpu up --force-recreate, i've also tried deleting the old container however the changes still do not carry over into the new container. I tried forcing the use of only settings.yaml by editing settings_loader.py but this also had no effect.

Question

I've managed to change the settings by entering the container as root, editing the files inside and restarting the container, this is far from the preferable way of tweaking the GPT. As I am a fairly new docker user, is there something i'm missing? What is the correct way of tweaking/creating new profile?

@Just-enki Just-enki added the question Further information is requested label Oct 16, 2024
@jaluma
Copy link
Collaborator

jaluma commented Oct 17, 2024

You can create a new settings-X.yaml file, with your custom configuration and mount inside the image. To do that, modify private-gpt, adding a new volume line pointing your settings file to the private_folder. After, you can modify PGPT_PROFILES environment to run this profile.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
question Further information is requested
Projects
None yet
Development

No branches or pull requests

2 participants