Make all your private packages accessible in one place
with this github-hosted PyPi index
Description • Try it ! • Get Started • Modify indexed packages • FAQ • Contribute • References
- Github-hosted
- 🚀 Template ready to deploy
- 🔆 Easy to use through Github Actions
This repository is a Github page used as a PyPi index, conform to PEP503.
You can use it to group all your packages in one place, and access it easily through pip
, almost like any other package publicly available !
While the PyPi index is public, private packages indexed here are kept private : you will need Github authentication to be able to retrieve it.
Visit astariul.github.io/github-hosted-pypi/ and try to install packages indexed there !
Try to install the package public-hello
:
pip install public-hello --extra-index-url https://astariul.github.io/github-hosted-pypi/
It will also install the package mydependency
, automatically !
Try it with :
from public_hello import hi
print(hi())
You can also install a specific version :
pip install public-hello==0.1 --extra-index-url https://astariul.github.io/github-hosted-pypi/
Now try to install the package private-hello
:
pip install private-hello --extra-index-url https://astariul.github.io/github-hosted-pypi/
It will not work, because it's private and only me can access it !
- Use this template and create your own repository :
- Go to
Settings
of your repository, and enable Github Page - Customize
index.html
andpkg_template.html
to your liking - You're ready to go ! Visit
<user>.github.io/<repo_name>
to see your PyPi index
Now that your PyPi index is setup, you can register / update / delete packages indexed.
Github actions are setup to do it automatically for you.
You just have to :
- Go to the
Actions
tab of your repository - Click the right workflow (
register
/update
/delete
) and trigger it manually - Fill the form and start the workflow
- Wait a bit
- Check the new PR opened (ensure the code added correspond to what you want)
- Merge the PR
As you may know, pip
can install Github-hosted package if given in the form pip install git+<repo_link>
. This PyPi index is just an index of links to other Github repository.
Github pages are public, so this PyPi index is public. But it just contain links to other Github repositories, no code is hosted on this PyPi index !.
If the repository hosting code is private, you will need to authenticate with Github to be able to clone it, effectively making it private.
When running pip install <package_name> --extra-index-url https://astariul.github.io/github-hosted-pypi/
, the following happen :
pip
will look athttps://pypi.org/
, the default, public index, trying to find a package with the specified name.- If it can't find, it will look at
https://astariul.github.io/github-hosted-pypi/
. - If the package is found there, the link of the package is returned to
pip
(git+<repo_link>@<tag>
). - From this link,
pip
understand it's a Github repository and will clone the repository (at the specific tag) locally. - From the cloned repository,
pip
install the package. pip
install any missing dependency with the same steps.
Authentication happen at step 4, when cloning the repository.
The single best practice is using Github releases. This allow your package to have a version referred by a specific tag.
To do this :
- Push your code in a repository.
- Create a new Github release. Ensure you follow semantic versioning. It will create a tag.
- Ensure you can install the package with
pip install git+<repo_link>@<tag>
- When putting the package on this index, put the full link (
git+<repo_link>@<tag>
).
You can just specify a different name for your indexed package. Just give it a different name in the form when registering it.
For example if you have a private package named tensorflow
, when you register it in this index, you can name it my_cool_tensorflow
, so there is no name-collision with the public package tensorflow
.
Then you can install it with pip install my_cool_tensorflow --extra-index-url https://astariul.github.io/github-hosted-pypi/
.
Then from python
, you can just do :
import tensorflow
Note : While it's possible to do like this, it's better to have a unique name for your package, to avoid confusion.
Building a Docker image is not interactive, so there is no prompt to type username and password.
Instead, you should put your Github credentials in a .netrc
file, so pip
can authenticate when cloning from Github.
To do this securely on Docker, you should use Docker secrets. Here is a quick tutorial on how to do :
Step 1 : Save your credentials in a secret file. Follow this example :
machine github.com
login <gh_user>
password <gh_pass>
\n
.
So careful if you're using a IDE that replace tabs by spaces or if you're on Windows (where line endings are \r\n
) !
Let's name this file gh_auth.txt
.
Step 2 : Create your Docker file. In the docker file you should mount the secret file in .netrc
, and run the command where you need authentication. For example :
# syntax=docker/dockerfile:experimental
FROM python:3
RUN --mount=type=secret,id=gh_auth,dst=/root/.netrc pip install <package_name> --extra-index-url https://astariul.github.io/github-hosted-pypi/
Step 3 : Build your Docker image, specifying the location of the secret created in step 1 :
sudo DOCKER_BUILDKIT=1 docker build --secret id=gh_auth,src=./gh_auth.txt .
If you have any questions or ideas to improve this FAQ, please open a PR / blank issue !
Issues and PR are welcome !
If you come across anything weird / that can be improved, please get in touch !
This is greatly inspired from this repository.
It's just a glorified version, with cleaner pages and github actions for easily adding, updating and removing packages from your index.
Also check the blogpost of the original author !