CodeReview BOT
A code review robot powered by ChatGPT
Translation Versions: ENGLISH | 中文简体 | 中文繁體 | 한국어 | 日本語
Bot Usage
Due to cost considerations, BOT is only used for testing purposes and is currently deployed on AWS Lambda with ratelimit restrictions. Therefore, unstable situations are completely normal. It is recommended to deploy an app by yourself.
Install
Install: apps/cr-gpt;
Configuration
- Go to the repo homepage which you want integrate this bot
- click
settings
- click
actions
undersecrets and variables
- Change to
Variables
tab, create a new variableOPENAI_API_KEY
with the value of your open api key (For Github Action integration, set it in secrets)
Start using
- The robot will automatically do the code review when you create a new Pull request, the review information will show in the pr timeline / file changes part.
- After
git push
update the pull request, cr bot will re-review the changed files
example:
Using Github Actions
- add the
OPENAI_API_KEY
to your github actions secrets - create
.github/workflows/cr.yml
add bellow content
name: Code Review
permissions:
contents: read
pull-requests: write
on:
pull_request:
types: [opened, reopened, synchronize]
jobs:
test:
# if: ${{ contains(github.event.*.labels.*.name, 'gpt review') }} # Optional; to run only when a label is attached
runs-on: ubuntu-latest
steps:
- uses: anc95/ChatGPT-CodeReview@main
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
# Optional
LANGUAGE: Chinese
OPENAI_API_ENDPOINT: https://api.openai.com/v1
MODEL: gpt-3.5-turbo
PROMPT:
top_p: 1
temperature: 1
max_tokens: 10000
MAX_PATCH_LENGTH: 10000 # if the patch/diff length is large than MAX_PATCH_LENGTH, will be ignored and won't review. By default, with no MAX_PATCH_LENGTH set, there is also no limit for the patch/diff length.
Self-hosting
- clone code
- copy
.env.example
to.env
, and fill the env variables - install deps and run
npm i
npm -i g pm2
npm run build
pm2 start pm2.config.cjs
probot for more detail
Dev
Setup
# Install dependencies
npm install
# Run the bot
npm start
Docker
# 1. Build container
docker build -t cr-bot .
# 2. Start container
docker run -e APP_ID=<app-id> -e PRIVATE_KEY=<pem-value> cr-bot
Contributing
If you have suggestions for how cr-bot could be improved, or want to report a bug, open an issue! We'd love all and any contributions.
For more, check out the Contributing Guide.
Credit
this project is inpired by codereview.gpt
License
ISC © 2023 anc95