privateGPT in Docker #613
Replies: 5 comments 4 replies
-
Hi. Thank you for adding privategpt to a container image. when I am trying to run this in the terminal I am getting the below error. Would you know what it might be? python3 privateGPT.pyUsing embedded DuckDB with persistence: data will be stored in: db |
Beta Was this translation helpful? Give feedback.
-
@mvamsee2010 You're welcome. And this was just a quick-and-dirty pass, just to see if I could get it running. Check the issues and pull requests for others who have done more elaborate Dockerfile or docker-compose files. The "magic" is that you need to be on a system with sufficient RAM, at least 8 GB but 16GB or greater results in a more pleasant experience. I started on a 2GB system and the image built, but the container instance running privateGPT.py promptly crashed. I then moved to 16GB, which was much more pleasant. I haven't tried anything in between. FYI, since I did my development using GitHub CodeSpaces, I modified my https://github.com/rwcitek/privateGPT/blob/docker/.devcontainer/devcontainer.json Post here letting us know if that does or does not resolve your issue. |
Beta Was this translation helpful? Give feedback.
-
First of all, thank you for setting this up. After a few tries and an actual distro re-install, I managed to get the docker container running. |
Beta Was this translation helpful? Give feedback.
-
Trying to create docker image on a Window 10 PC. docker build -f Dockerfile.local , Gets most of the way through, but towards the end:
Dockerfile.local:26 24 | COPY pyproject.toml poetry.lock ./ ERROR: failed to solve: process "/bin/sh -c poetry install --with local" did not complete successfully: exit code: 1 |
Beta Was this translation helpful? Give feedback.
-
It would be nice to see an official Docker image. |
Beta Was this translation helpful? Give feedback.
-
Greetings!
I've forked the repo and created a branch that puts the instructions in a Dockerfile. Here's a link to the docker folder in the docker branch in the repo:
https://github.com/rwcitek/privateGPT/tree/docker/docker
I pushed the image that I built to Dockerhub. So you can get started quickly by simply running this command:
Regards,
Beta Was this translation helpful? Give feedback.
All reactions