Kite Adds Jupyter Integration
Written by Kay Ewbank   
Tuesday, 04 August 2020

The developers of the Kite autocomplete coding assistant have launched Kite for JupyterHub and JupyterLab. Kite uses AI to automate repetitive steps in programming. It goes further than the autocomplete suggestions provided by most editors, which usually suggest a variable name or class. Kite will suggest several lines of code.

Jupyter Notebooks are open source web applications that contain live code and equations along with visualizations and narrative text.


As with the other Kite autocomplete interfaces including Python and JavaScript, the Jupyter version offers code completions when typing in Jupyter notebooks. The Kite developers say that the lack of a user-friendly autocomplete interface means that at the moment most Jupyter users don't make use of autocomplete to save time and code faster.


The Kite team worked with the JupyterLab core contributors to build a Kite integration that provides ML-powered Python completions and a one-click documentation tool in the JupyterLab UI. Kite provides multi-line completions sorted by relevance, and don't need the Jupyter user to run a cell in the notebook or press Tab to make the suggested completions appear. As the user moves through the suggestions, Kite also shows documentation for the highlighted completion.


The Kite tool does still make use of Jupyter's kernel completions, making it possible to access attributes such as columns on a DataFrame. Kite for Jupyter comes in two versions - free and commercial. There's also a version for JupyterHub that provides support for teams. If this version is run on a GPU-powered server, users get smarter, longer completions. The JupyterHub version also supports custom-made Kite models for a team's specific codebase and APIs.


More Information

Kite Homepage

Related Articles

Update - Kite Launches AI-Powered JavaScript Auto-Completion

Kite - AI Powered Auto Completion for Python

Kite - Smart Copilot For Programmers

Google Restricts Autocomplete API

Jupyter Notebook 5 Adds Cell Tagging

Jupyter 4 Completed By Release Of IPython 4


To be informed about new articles on I Programmer, sign up for our weekly newsletter, subscribe to the RSS feed and follow us on Twitter, Facebook or Linkedin.


Amazon Updates Bedrock With Custom Model Support

Amazon has updated Bedrock, its tool for building with generative AI on AWS. The update adds support for importing custom models and evaluating models, as well as support for using Meta Llama 3 models [ ... ]

Apple's Walled Garden Is Crumbling

Or is it? Depends on which side of the wall you are on. Apple is doing all it can to keep control and more importantly keep the revenuse from its App Store, but from the outside it seems to be losing  [ ... ]

More News

raspberry pi books



or email your comment to: