Frequently Asked Questions
Easy Installation
Supported Languages
Tabnine for Teams
Boost your productivity with the expert guidance of an AI code completion assistant trusted by millions of developers.
Whether you are a new dev or a seasoned pro, working solo or part of a team, Tabnine’s AI assistant will increase your development velocity with code completions in all the most popular coding languages and IDEs.
Customize Your Code Completion Experience
Tabnine for Teams provides expert inline coding guidance with an AI assistant privately trained on your team’s coding standards. Learn more
Tabnine makes it easy and secure for team admins to grant their AI assistant access to their Github, GitLab and Bitbucket repositories. Simply assign the repositories you want your AI assistant to learn from. Learn more
Whether you call it IntelliSense, intelliCode, autocomplete, AI-assisted code completion, AI-powered code completion, AI copilot, AI code snippets, code suggestion, code prediction, code hinting, or content assist, you probably already know that it can massively impact your coding velocity, cutting your coding time in half.
Powered by machine learning models and trained on more than a billion lines of open-source code with permissive licenses, Tabnine is the most trusted AI-powered code completion available today.
Easily configure Tabnine’s AI models to perform faster, stronger or balanced
Python | Javascript | Java |
---|---|---|
extended JS | React | PHP |
Typescript | C Header | Bash |
ML | Swift | Ruby |
Perl | Rust | SQL |
Vue | F# | Scala |
Julia | TOML | Shell |
YAML | C / C++/ C# | HTML |
Lua | Markdown | Haskell |
Go | Objective C | JSON |
CSS / SCSS | Angular | Kotlin |
Easily Disable Code Completions on Files and Languages You Specify
Tabnine reduces the need for expensive and distracting code searches and automates repetitive tasks, freeing developers to focus on creative coding.
Share knowledge effortlessly across countries and time zones. Tabnine learns your code patterns, providing expert guidance to every member of your team any time of day.
Tabnine Improves code consistency across your entire project, suggesting completions that align with your best practices for code that’s easier to read, manage, and maintain.
Tabnine’s AI assistant helps speed new team members through the onboarding process with instant inline coding guidance minimizing the training burden placed on senior developers.
Your Tabnine AI assistant will help you get the right code the first time. Tabnine provides code guidance that’s consistent with your team’s best practices, saving costly and frustrating code review iterations.
- Search for Tabnine in your Extensions Tab
- Click on the blue Install button
- Reload or restart your VSCode
- Press Cmd+P (mac) or Ctrl+P (Windows) in your Visual Studio Code, type
ext install Tabnine.tabnine-vscode
and press Enter - Click the Reload button in the extensions tab
- The default behavior of Tabnine uses the Enter key to accept completions. If you would rather use the Enter key to start a new line, go to Settings → Editor: Accept Suggestion On Enter and turn it off.
Got a question? We’ve got the answer - Check out our FAQ page
Having some trouble with installation? Something not working the way you hoped? Tabnine Support is always happy to help. Feel free to contact us anytime at support@tabnine.com
Head up to the top right hand corner of the Tabnine homepage and click on the ‘My Tabnine’ icon to instantly launch the app and easily update and manage all your Tabnine for Teams account options, team settings, and enable GitHub, GitLab, and Bitbucket integrations.
A quick click on Tabnine on your IDE status bar takes you directly to your Tabnine Hub where you can easily update and manage all your account options and customize your suggestion preferences.
After installation, navigate to the Tabnine Settings page (Open Settings from the Command Palette) and verify that Tabnine is successfully loaded (as shown in these screenshots).
Tabnine is a textual autocomplete extension. When you type a specific string in your editor, you will be shown the Tabnine completion dialog box with suggestions for completing the code you’ve begun typing.
Deep Tabnine is trained on millions of files from GitHub. During training, Tabnine’s goal is to predict the next token given the tokens that came before. To achieve this goal, Tabnine learns complex behavior, such as type inference in dynamically typed languages.
Deep Tabnine can use subtle clues that are difficult for traditional tools to access. For example, the return type of app.get_user()
is assumed to be an object with setter methods, while the return type of app.get_users()
is assumed to be a list.
Deep Tabnine is based on GPT-2, which uses the Transformers Network Architecture. This architecture was first developed to solve problems in natural language processing. Although modeling code and modeling natural language might appear to be unrelated tasks, modeling code requires understanding English in some unexpected ways.
- Tabnine Indexes your entire project and determines which files to ignore by reading your
.gitignore
- Tabnine cuts your number of keystrokes in half and eliminates unnecessary typos
- Tabnine works right out of the box ensuring frictionless installation and configuration
- Tabnine offers code completion suggestions in less than 10 milliseconds
Tabnine’s code completion AI uses both cloud and local models. For both models your team’s code and AI training data are only used to provide the service, and your code is never shared nor used as part of Tabnine’s open-source trained AI.
Find out more about how we keep your code private HERE.