CodeRabbit - AI-based code reviewer

Overview

CodeRabbit AI simplifies the pull request review process via analysing it by AI tools. It analyses the code and provides feedback for changes required in pull request. Also provides a chat communication mechanism to correct or get suggestion for changes suggested.

How to integrate

  • Supports integration with GitHub and Gitlab source code managers.

  • Log in with your GitHub or GitLab account at https://coderabbit.ai/login

  • On the GitHub page, you will be prompted to choose the organisation where you want to install the CodeRabbit app. Select the organisation to proceed.

  • After selecting the organisation, you will be directed to a GitHub repositories page where you will install and authorize the CodeRabbit GitHub app. You can choose to grant access to all your organisation's repositories or select specific repositories.

  • After you have installed the CodeRabbit app, the reviews will start automatically with the new pull requests or incremental commits to existing pull requests. To trigger reviews on existing pull requests, post @coderabbitai review as a comment on the pull request.

 

Process Workflow:

  1. CodeRabbit listens to the Pull Request event.

  2. It pre-processes the request and constructs prompts for the Large Language Model (LLM).

  3. The prompts are sent to multiple LLMs for a diverse range of insights.

  4. LLMs return their responses to the prompts.

  5. Post-processing takes place to suppress noise and compile a coherent answer.

  6. The review state, including all relevant insights, is stored directly on the PR.

  7. The refined response is then posted on the PR, ready for developers to review and act upon.

Data Integrity and Security

CodeRabbit AI ensures stringent data privacy, with no data retention post-review, safeguarding the integrity of proprietary code and adhering to strict security protocols.

It does not use data collected during code reviews to train or influence the models. Queries to the Large Language Model (LLM) are ephemeral. Neither we nor the LLM we use share any data collected during the code review process with other third parties.

Does CodeRabbit store my Data? We store embeddings of your conversations, which are used to improve future reviews for your organisation.

Compliance and Data Privacy: Your data is kept confidential, isolated by organisation, and used only to improve your organisation reviews. Data storage complies with SOC2 Type II, GDPR, and HIPAA standards.

Opting Out: You can choose to opt out of data storage at any time. Opting out won't affect your access but will limit the personalization of the reviews.

In-Depth Features

  • Pull Request Summary: Automatically generates and updates with each commit, providing a digestible overview of the PR’s content.

Screenshot from 2024-02-23 09-58-22.png
  • Walkthrough: A detailed code walkthrough to understand the changes in each file that is part of the pull request, followed by a celebratory poem about the changes.

image-20240223-043009.png

  • Code Review Feedback: Delivers line-specific comments in diff format for direct application or review.

 

  • Chat with CodeRabbit: Facilitates developer-bot dialogues for real-time code discussion and clarification.

 

  • Issue Validation: Aligns PR changes with associated GitHub/GitLab issues, ensuring consistency.

  • Review Status Updates: A comprehensive review log, including examined and ignored files and provided feedback.

  • Customise CodeRabbit

CodeRabbit offers various customization options to tailor the reviews to your specific requirements. Customizations can be made using one of the below options :

  1. Customization via CodeRabbit YAML File (Recommended)

  2. Customization via CodeRabbit UI

Dashboard Analytics:

CodeRabbit Dashboard displays organisation's pull request activity and value provided by CodeRabbit reviews. This includes the number of pull requests reviewed, actionable items,optional comments and more.

Reference PR Link: https://github.com/sivajiganesh-dev/service-request/pull/9

Pricing Plans

To onboard CodeRabbit AI, access the platform’s free tier or trial the Pro subscription. The pro tier comes with a price of per developer 15$ per month, but as it follows the best practices of Copilot, Pro features come free for open-source projects.

Pro Plan Features

  • GitHub/GitLab organisation owners can purchase or make changes to the subscription.

  • You can choose to manually purchase seats and assign them to developers, or have them assigned automatically as developers create pull requests.

  • During the trial period, seat assignment is automatic, but the number of seats can be adjusted when purchasing the subscription.

Review Configuration/Settings

Review Filters

 

https://coderabbit.ai/pricing

https://github.com/sivajiganesh-dev/service-request/pull/9

 

Summary:

  • Pro features come free for open-source projects.

  • Coderabbit provides review comments for in context code with the help of Chat GPT internally