https://github.com/ray-project/docu-mentor
https://github.com/ray-project/docu-mentor
Last synced: 9 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/ray-project/docu-mentor
- Owner: ray-project
- License: mit
- Created: 2023-09-07T09:34:23.000Z (over 2 years ago)
- Default Branch: main
- Last Pushed: 2024-06-02T20:52:46.000Z (over 1 year ago)
- Last Synced: 2025-03-26T18:51:57.158Z (10 months ago)
- Language: Python
- Size: 91.8 KB
- Stars: 10
- Watchers: 2
- Forks: 3
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Docu-Mentor
Automatically get suggestions to improve the writing in your PRs from this
GitHub app powered by [Anyscale Endpoints](https://app.endpoints.anyscale.com/).
## Installation
Simply install the app on your project on GitHub: [Docu-Mentor App](https://github.com/apps/docu-mentor)
## Usage
Then in any PR in your project, create a new comment that says:
```bash
@docu-mentor run
```
and I will start my analysis. I only look at what you changed
in this PR. If you only want me to look at specific files or folders,
you can specify them like this:
```bash
@docu-mentor run doc/ README.md
```
In this example, I'll have a look at all files contained in the
"doc/" folder and the file "README.md".
## Checking that it works
Simply run
```bash
pytest . -s
```
to evaluate the doc sanitation bot against GPT-4.
## Deployment
The bot is built for deployment with [Anyscale Services](https://anyscale.com),
using the `service.yaml` with the `main.py` entrypoint provided in this repo.
You can also deploy it on Heroku, using the `Procfile` and `heroku.py`.
With Anyscale you can parallelize your bot using Ray, reducing the total
wallclock time, with Heroku that doesn't work.