Onigam / ai-mistral-pr-reviewer

AI-based Pull Request Summarizer and Reviewer with Chat Capabilities.

AI-based PR reviewer and summarizer

Overview

CodeRabbit's fork ai-mistral-pr-reviewer is an AI-based code reviewer and summarizer for GitHub pull requests using OpenAI compatible APIs like MistralAI API. It is designed to be used as a GitHub Action and can be configured to run on every pull request and review comments

Reviewer Features:

• PR Summarization: It generates a summary and release notes of the changes in the pull request.
• Line-by-line code change suggestions: Reviews the changes line by line and provides code change suggestions.
• Continuous, incremental reviews: Reviews are performed on each commit within a pull request, rather than a one-time review on the entire pull request.
• Cost-effective and reduced noise: Incremental reviews save on OpenAI costs and reduce noise by tracking changed files between commits and the base of the pull request.
• Chat with bot: Supports conversation with the bot in the context of lines of code or entire files, useful for providing context, generating test cases, and reducing code complexity.
• Smart review skipping: By default, skips in-depth review for simple changes (e.g. typo fixes) and when changes look good for the most part. It can be disabled by setting review_simple_changes and review_comment_lgtm to true.
• Customizable prompts: Tailor the system_message, summarize, and summarize_release_notes prompts to focus on specific aspects of the review process or even change the review objective.

To use this tool, you need to add the provided YAML file to your repository and configure the required environment variables, such as GITHUB_TOKEN, the openai compatible API key OPENAI_API_KEY, the base url of the API openai_base_url, the light model openai_light_model and the heavy model openai_heavy_model. By default it assume you will use OPENAI so no need to specify openai_base_url, openai_light_model and openai_heavy_model unless you want to use something else like Mistral where you should specify those values:

For more information on usage, examples, contributing, and FAQs, you can refer to the sections below.

• Overview
• Professional Version of CodeRabbit
• Reviewer Features
• Install instructions
• Conversation with CodeRabbit
• Examples
• Contribute
• FAQs

Install instructions

ai-pr-reviewer runs as a GitHub Action. Add the below file to your repository at .github/workflows/ai-pr-reviewer.yml

If you want to use OpenAI

name: Code Review

permissions:
  contents: read
  pull-requests: write

on:
  pull_request_target:
    types: [opened, synchronize, reopened]
  pull_request_review_comment:
    types: [created]

concurrency:
  group:
    ${{ github.repository }}-${{ github.event.number || github.head_ref ||
    github.sha }}-${{ github.workflow }}-${{ github.event_name ==
    'pull_request_review_comment' && 'pr_comment' || 'pr' }}
  cancel-in-progress: ${{ github.event_name != 'pull_request_review_comment' }}

jobs:
  review:
    runs-on: ubuntu-latest
    steps:
      - uses: Onigam/ai-mistral-pr-reviewer@latest
        env:
          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
        with:
          debug: false

If you prefer MistralAI

name: Code Review

permissions:
  contents: read
  pull-requests: write

on:
  pull_request_target:
    types: [opened, synchronize, reopened]
  pull_request_review_comment:
    types: [created]

concurrency:
  group: ${{ github.repository }}-${{ github.event.number || github.head_ref ||
    github.sha }}-${{ github.workflow }}-${{ github.event_name ==
    'pull_request_review_comment' && 'pr_comment' || 'pr' }}
  cancel-in-progress: ${{ github.event_name != 'pull_request_review_comment' }}

jobs:
  review:
    runs-on: ubuntu-latest
    steps:
      - name: AI-based PR Reviewer & Summarizer with Mistral 8x7B Chat Capabilities
        uses: Onigam/ai-mistral-pr-reviewer@latest
        env:
          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
          OPENAI_API_KEY: ${{ secrets.MISTRAL_API_KEY }}
        with:
          debug: false
          openai_base_url: "https://api.mistral.ai/v1"
          openai_light_model: "mistral-tiny"
          openai_heavy_model: "mistral-small"

Environment variables

• GITHUB_TOKEN: This should already be available to the GitHub Action environment. This is used to add comments to the pull request.
• OPENAI_API_KEY: use this to authenticate with OpenAI API or OpenAI compatible API like Mistral. You can get one here or a Mistral one here. Please add this key to your GitHub Action secrets.
• OPENAI_API_ORG: (optional) use this to use the specified organization with OpenAI API if you have multiple. Please add this key to your GitHub Action secrets.
• openai_base_url: (optional) use this to specify the base url of the OpenAI compatible API. Default is https://api.openai.com/v1
• openai_light_model: (optional) use this to specify the light model to use. Default is gpt-3.5-turbo
• openai_heavy_model: (optional) use this to specify the heavy model to use. Default is gpt-4

Models: gpt-4 and gpt-3.5-turbo, or mistral-small and mistral-tiny

Recommend using mistral-tiny or mistral-small for lighter tasks such as summarizing the changes (openai_light_model in configuration) and mistral-small or mistral-medium for more complex

Cost are really cheaper than OpenAI and the results quite similar.

If you want to use openai we recommend using gpt-3.5-turbo for lighter tasks such as summarizing the changes (openai_light_model in configuration) and gpt-4 for more complex review and commenting tasks (openai_heavy_model in configuration).

Costs: gpt-3.5-turbo is dirt cheap. gpt-4 is orders of magnitude more expensive, but the results are vastly superior. We are typically spending $20 a day for a 20 developer team with gpt-4 based review and commenting.

Prompts & Configuration

See: action.yml

Tip: You can change the bot personality by configuring the system_message value. For example, to review docs/blog posts, you can use the following prompt:

Blog Reviewer Prompt

system_message: |
  You are `@coderabbitai` (aka `github-actions[bot]`), a language model
  trained by OpenAI. Your purpose is to act as a highly experienced
  DevRel (developer relations) professional with focus on cloud-native
  infrastructure.

  Company context -
  CodeRabbit is an AI-powered Code reviewer.It boosts code quality and cuts manual effort. Offers context-aware, line-by-line feedback, highlights critical changes,
  enables bot interaction, and lets you commit suggestions directly from GitHub.

  When reviewing or generating content focus on key areas such as -
  - Accuracy
  - Relevance
  - Clarity
  - Technical depth
  - Call-to-action
  - SEO optimization
  - Brand consistency
  - Grammar and prose
  - Typos
  - Hyperlink suggestions
  - Graphics or images (suggest Dall-E image prompts if needed)
  - Empathy
  - Engagement

Conversation with CodeRabbit

You can reply to a review comment made by this action and get a response based on the diff context. Additionally, you can invite the bot to a conversation by tagging it in the comment (@coderabbitai).

Example:

@coderabbitai Please generate a test plan for this file.

Note: A review comment is a comment made on a diff or a file in the pull request.

Ignoring PRs

Sometimes it is useful to ignore a PR. For example, if you are using this action to review documentation, you can ignore PRs that only change the documentation. To ignore a PR, add the following keyword in the PR description:

@coderabbitai: ignore

Examples

Some of the reviews done by ai-pr-reviewer

Any suggestions or pull requests for improving the prompts are highly appreciated.

Contribute

Developing

First, you'll need to have a reasonably modern version of node handy, tested with node 17+.

Install the dependencies

$ npm install

Build the typescript and package it for distribution

$ npm run build && npm run package

FAQs

Inspect the messages between OpenAI server

Set debug: true in the workflow file to enable debug mode, which will show the messages

Disclaimer

• Your code (files, diff, PR title/description) will be sent to your AI API's servers for processing. Please check with your privacy policy before using this on your private code repositories.
• Regarding which API you are using check OpenAI API specific data usage policy or MistralAI API specific data usage policy.
• This action is not affiliated with OpenAI or Mistral AI.