ChatGPT Boosts Research Power With GitHub Integration

ChatGPT Deep Research Now Taps into GitHub Repositories

OpenAI is enhancing ChatGPT's capabilities by introducing a feature that allows users to connect their GitHub repositories directly to the chatbot. Announced recently, this integration is part of the sophisticated Deep Research agent, designed to empower the AI to generate comprehensive reports by analyzing code and documentation within user-specified repositories, including both personal and public ones.

Availability and Access

This new functionality is currently being rolled out, but initially, it's exclusive to paid subscribers of the ChatGPT platform. According to an announcement shared by OpenAI Developers on X, the Deep Research with GitHub feature is available globally for Team users. Subscribers to the Plus and Pro plans can also access it, with the current exception of users located in the European Economic Area (EEA), Switzerland, and the United Kingdom.

It's worth noting that there might be a slight delay; OpenAI mentions it can take up to five minutes for a newly created or recently updated repository to become accessible through the Deep Research GitHub connector.

How It Works

Eligible users can leverage this feature by first posing a query to the Deep Research agent within ChatGPT. They will then see an option to connect to GitHub. Authorizing this connection grants ChatGPT access to the selected repositories.

OpenAI explains the process: “Ask a question and the deep research agent will read and search the repo's source code and PRs, returning a detailed report with citations.”

This means ChatGPT can pull real-time data from connected GitHub repositories, including source code, README files, pull requests, and other documents. It then analyzes this data to provide detailed insights and summaries based on the user's request.

Beta Status and Data Privacy

The feature is currently in beta, and users should be aware that GitHub's standard terms and conditions apply when using the connector.

Regarding data privacy, OpenAI provides clarity based on user type and settings. For ChatGPT Plus and Pro users who have the “Improve the model for everyone” setting enabled, the data accessed from GitHub may be used by OpenAI to train its models. However, if this setting is turned off, the data will not be stored or used for training.

Importantly, OpenAI states that data from its business-tier offerings – including Team, Enterprise, and Edu plans, as well as data processed via its API – is not stored or used for model training, irrespective of user settings.