You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
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.
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?
The text was updated successfully, but these errors were encountered:
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.
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.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?
The text was updated successfully, but these errors were encountered: