|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.
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.
or email your comment to: firstname.lastname@example.org