jupyter-cogram 0.4.0

Intuitive coding for Jupyter Notebook using natural language.

Cogram: Intuitive coding with natural language

Cogram brings intuitive coding with natural language to Jupyter Notebook.

📖 Documentation

Documentation
🚀️ Sign up	Sign up to get your API token and get started!
⭐️ How to	New to Cogram? Check out our videos on how to get started!
📚 Community	Have questions our comments? Join our Slack!

Features

• AI-powered coding for Jupyter Notebooks
• Supports Python: ideal for data science tasks
• Cycle through different suggestions

⏳ Install cogram

Requirements

• API token: If you don't have one yet, sign up
• Operating system: macOS · Linux · Windows
• Python version: Python 3.6+ (only 64 bit)
• Package managers: pip

Installation

The easiest way to install Cogram for Jupyter Notebook is using pip.

pip install -U jupyter-cogram
jupyter nbextension enable jupyter-cogram/main

You can now start a new Jupyter Notebook server with

jupyter notebook

and you're ready to go!

Updating Cogram

The easiest way to upgrade to a new version of Cogram is using pip:

pip install -U jupyter-cogram

You'll then have to kill any active Jupyter Notebook servers and start a new one with

jupyter notebook

📚 Use Cogram

🛫 First start

Once you've installed Cogram and open a Jupyter Notebook for the first time, you'll be asked for your API token (you can find that under My Account).

On first start, paste your API token into the prompt box. You can toggle the extension off and on by clicking the Cogram button () in the toolbar. The green circle indicates that Cogram is active.

🔮 Prompting Cogram

You can prompt Cogram by writing a comment into a code cell starting with ##. You finish off the prompt by typing ## again. The status light will turn orange , indicating that Cogram is busy.

For example, the prompt

## fibonacci sequence ##

will generate different functions that produce the Fibonacci sequence.

Once your code has been generated, you can explore different options with the ← and → keys. If you're happy with a suggestion, you can accept it by waiting for two seconds. Alternatively, you can accept it right away by hitting ⌘+⏎ (macOS) or Ctrl+⏎ (Windows & Linux).