Skip to main content

Automated PR Review Application using LLM

Project description

Revus

What's Revus?

Revus is an automated pull request (PR) review application that uses large language models (LLMs) to streamline and standardize code reviews.

Install

pipx install revus

Setup

Create a configuration file called revus.toml with the following parameters:

  • OPENAI_API_KEY - your OpenAI API key, available here.
  • model_name - any available OpenAI model (default is gpt-4o-mini).
  • file_types - specify file types for the application to read using an array of strings (default is [“.py”]).
  • language - specify the language for review content (default is English).
  • exclude_paths - files or paths the application should ignore.
  • custom_rules- custom rules for review, if needed.

Usage

To review changes with Revus, first add modified files to staging:

git add <file_name>

or add all files:

git add .

Then, run the application in the project folder:

revus

Important: Revus reviews each file individually, simplifying context management.

New features will be added soon.

Additional Notes

This project is in active development, currently in alpha, and may have limited or experimental features.

Contacts

For issues or suggestions, reach out on Telegram or Linkedin.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

revus-0.0.2.tar.gz (6.3 kB view details)

Uploaded Source

Built Distribution

revus-0.0.2-py3-none-any.whl (8.2 kB view details)

Uploaded Python 3

File details

Details for the file revus-0.0.2.tar.gz.

File metadata

  • Download URL: revus-0.0.2.tar.gz
  • Upload date:
  • Size: 6.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.9.20

File hashes

Hashes for revus-0.0.2.tar.gz
Algorithm Hash digest
SHA256 a91de07a2eef4c4885f3792344ee04463fadc7bdffc815375cf02e02d06bd631
MD5 0fe46ed86481c1dc27ebede6688c7b18
BLAKE2b-256 8f42e1c83764341309aa4cc578f2fae30e5dd09a08d84c622fa964b629e4172f

See more details on using hashes here.

File details

Details for the file revus-0.0.2-py3-none-any.whl.

File metadata

  • Download URL: revus-0.0.2-py3-none-any.whl
  • Upload date:
  • Size: 8.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.9.20

File hashes

Hashes for revus-0.0.2-py3-none-any.whl
Algorithm Hash digest
SHA256 66a77dc0ae660236da46faa223ebd73fe389965cf6e7f08a9810788dcbc81231
MD5 d59eba2918319a085d27546349328d9c
BLAKE2b-256 0a3af0ff8d852506506dbd9b18a7aa95256c0ad1b3bc33d3079c50344ce9d54f

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page