Skip to main content

A tool for reviewing GitHub PRs using OpenAI, developed by AFILALABS

Project description

AFILALABS PR Reviewer

A command-line tool developed by AFILALABS (Chicago) that reviews GitHub pull requests using OpenAI's GPT-4 API.

Features

  • Automatically analyzes pull requests from a GitHub URL
  • Reviews each file in the PR individually
  • Provides overall assessment of the PR
  • Can add comments directly to GitHub (optional)
  • Configurable through environment variables or config file

Installation

pip install afila-pr-reviewer

Requirements

  • Python 3.7+
  • GitHub personal access token with repo scope
  • OpenAI API key

Usage

Quick Start

First time setup:

pr-reviewer --setup

Review a PR:

pr-reviewer https://github.com/owner/repo/pull/123

Command line options

pr-reviewer https://github.com/owner/repo/pull/123 \
  --github-token your-github-token \
  --openai-key your-openai-api-key \
  --comment \  # Add comments to the PR
  --output review.md  # Save the review to a file

Environment Variables

You can use environment variables instead of passing tokens as arguments:

export GITHUB_TOKEN=your-github-token
export OPENAI_API_KEY=your-openai-api-key
pr-reviewer https://github.com/owner/repo/pull/123

License

MIT

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

afila_pr_reviewer-0.1.0.tar.gz (6.8 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

afila_pr_reviewer-0.1.0-py3-none-any.whl (7.8 kB view details)

Uploaded Python 3

File details

Details for the file afila_pr_reviewer-0.1.0.tar.gz.

File metadata

  • Download URL: afila_pr_reviewer-0.1.0.tar.gz
  • Upload date:
  • Size: 6.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.11.6

File hashes

Hashes for afila_pr_reviewer-0.1.0.tar.gz
Algorithm Hash digest
SHA256 5d12f569180b32d0c94275c01a254e70cacbdcda3fbefdcc247fb1d6429f8513
MD5 ec21a6a5008d98c1ba52f0668d0a3dff
BLAKE2b-256 c9f8a5ad850d2b7b37eeaed0ee4d681b56058f33f86d794f13fb2f1edfdbf549

See more details on using hashes here.

File details

Details for the file afila_pr_reviewer-0.1.0-py3-none-any.whl.

File metadata

File hashes

Hashes for afila_pr_reviewer-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 5f282716c44807c7912db95148e0d2f651ba487153c0628d890ad6636abf65b1
MD5 74cfd392f3cb98b52d82f9c71584cccb
BLAKE2b-256 f084e2c50012ac644485b21f99634a8f38833ea29e1980132a85cd4b1703aeed

See more details on using hashes here.

Supported by

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