ctrl+shift+p filters: :st2 :st3 :win :osx :linux
Browse

Tab​Nine

by Jacob Jackson ALL Trending

Sublime Text client for TabNine

Labels auto-complete

Details

Installs

  • Total 35K
  • Win 19K
  • Mac 10K
  • Linux 6K
Sep 19 Sep 18 Sep 17 Sep 16 Sep 15 Sep 14 Sep 13 Sep 12 Sep 11 Sep 10 Sep 9 Sep 8 Sep 7 Sep 6 Sep 5 Sep 4 Sep 3 Sep 2 Sep 1 Aug 31 Aug 30 Aug 29 Aug 28 Aug 27 Aug 26 Aug 25 Aug 24 Aug 23 Aug 22 Aug 21 Aug 20 Aug 19 Aug 18 Aug 17 Aug 16 Aug 15 Aug 14 Aug 13 Aug 12 Aug 11 Aug 10 Aug 9 Aug 8 Aug 7 Aug 6 Aug 5
Windows 51 79 81 61 78 78 57 63 78 69 60 64 63 49 59 57 65 60 63 63 55 58 72 65 59 85 53 54 53 51 72 83 62 51 50 38 55 53 58 82 64 58 42 54 65 57
Mac 12 23 22 22 28 17 12 13 28 15 16 27 17 11 13 21 25 20 19 15 13 14 21 14 13 23 12 13 8 10 17 14 12 20 23 13 19 16 11 13 18 8 11 12 19 19
Linux 11 13 11 8 17 18 16 12 13 22 12 20 20 13 12 17 18 17 24 17 13 18 14 15 17 12 17 15 9 13 16 12 18 17 8 11 21 17 10 20 12 10 8 22 23 14

Readme

Source
raw.​githubusercontent.​com

TabNine For Sublime

TabNine Overview:


This is the Sublime Text client for TabNine, advanced AI based autocomplete for all programming languages. TabNine Indexes your entire project by reading your .gitignore or others, and determines which files to index.

  • Enter long variable names using minimal keystrokes and leverage a mnemonic completion engine.
  • Zero configuration. TabNine works out of the box.
  • Highly responsive: Produces a list of suggestions in less than 10 milliseconds on average.

TabNine is part of Codota

Deep Completion:


Deep TabNine is trained on around 2 million 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 behaviour, 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 Transformer network architecture. This architecture was first developed to solve problems in natural language processing. Although modelling code and modelling natural language might appear to be unrelated tasks, modelling code requires understanding English in some unexpected ways.

TabNine Deep Cloud:


TabNine requires consumption of memory resources when being run locally on your computer. It may incur some latency that is not optimal to all PC’s. With that in mind, TabNine has developed a Cloud solution, called TabNine Deep Cloud.

We understand that users concerned with their privacy prefer to keep their code on their own machine. Rest assured that we’re taking the following steps to address this concern: For individual developers, we are working on a reduced-size model which can run on a laptop with reasonable latency. Update: we’ve released TabNine Local. For enterprise users, we will soon roll-out the option to license the model and run it on your own hardware. We can also train a custom model for you which understands the unique patterns and style within your codebase. If this could be relevant to you or your team, we would love to hear more about your use case at enterprise@tabnine.com. Enabling TabNine Deep Cloud sends small parts of your code to our servers to provide GPU-accelerated completions. Other than for the purpose of fulfilling your query, your data isn’t used, saved or logged in any way.

You can enable TabNine Deep Cloud for free by signing up TabNine Professional

You can read more about Deep Completion

auto_complete: false


The TabNine sublime plugin disables sublime's built in autocomplete.
It does that, because sublime's builtin autocomplete does not support all the features required by TabTine.
If you ever uninstall TabNine, remember to re-enable it.

Frequently Asked Questions:


Is TabNine simple to use?

TabNine works for all programming languages. TabNine does not require any configuration in order to work. TabNine does not require any external software (though it can integrate with it). Since TabNine does not parse your code, it will never stop working because of a mismatched bracket.

Will TabNine leak my source code?

By default, TabNine makes web requests only for the purposes of downloading updates and validating registration keys. In this case your code is not sent anywhere, even to TabNine servers. You may opt in to TabNine Deep Cloud, which allows you to use TabNine’s servers for GPU-accelerated completions powered by a deep learning model. If sending code to a cloud service is not possible, we also offer a self-hosted option. Contact us at enterprise@tabnine.com.

Note:


A note on licensing: this repo includes source code as well as packaged TabNine binaries. The MIT license only applies to the source code, not the binaries. The binaries are covered by the TabNine End User License Agreement.