Which specific Large Language Models does CodeReviewBot utilize for its analysis?
CodeReviewBot leverages several prominent Large Language Models, including OpenAI's GPT-4, GPT-4o, and Google's Gemini, to perform its code review functions.
How does CodeReviewBot handle intellectual property concerns regarding suggested code snippets?
By default, CodeReviewBot avoids providing direct code snippets. Instead, it describes the proposed changes, leaving the implementation to the developer. Users can enable code snippet suggestions via the repository options in the dashboard if desired.
Can CodeReviewBot be deployed within a private cloud or on-premise environment?
Yes, for Enterprise plan customers, CodeReviewBot offers the option to download and run the service on their own cloud infrastructure or hardware, providing greater control and customization.
Does CodeReviewBot use my private code to train its AI models?
No, CodeReviewBot explicitly states that it never uses private code to train its models. It may, however, use user feedback signals, such as reactions to bot review messages, to improve its models.
What is the difference in review capacity between the 'Opensource' and 'Starter' plans?
The 'Opensource' plan includes 100 reviews per month for public repositories, while the 'Starter' plan offers 40 reviews per month for private repositories, with additional reviews available at a per-review cost.