Skip to main content

Intuitive coding for Jupyter Notebook using natural language.

Project description

Cogram: Intuitive coding with natural language

Cogram brings intuitive coding with natural language to Jupyter Notebook.

pypi Version Cogram on Slack

📖 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

If you've installed Cogram by following the instructions on your My Account page your API token will automatically be saved. You can open a Jupyter Notebook and get started.

You may be asked for your API token when you open a new Notebook for the first time. You can find your API token on your My Account page. Paste this into the prompt box that opens when you start a new Jupyter Notebook.

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 ##. Submit 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).

💡 Tips for working with Cogram

Cogram works especially well if you give it some context. Cogram knows the cells in your notebook above the cell in which you're prompting Cogram. So the more cells you've already written, the better Cogram will work.

📚 Support

For help with Cogram please join our support channel in community.

Project details


Release history Release notifications | RSS feed

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

jupyter-cogram-0.7.4.tar.gz (19.2 kB view details)

Uploaded Source

Built Distribution

jupyter_cogram-0.7.4-py3-none-any.whl (38.8 kB view details)

Uploaded Python 3

File details

Details for the file jupyter-cogram-0.7.4.tar.gz.

File metadata

  • Download URL: jupyter-cogram-0.7.4.tar.gz
  • Upload date:
  • Size: 19.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.4.2 importlib_metadata/4.8.1 pkginfo/1.7.1 requests/2.26.0 requests-toolbelt/0.9.1 tqdm/4.62.2 CPython/3.9.7

File hashes

Hashes for jupyter-cogram-0.7.4.tar.gz
Algorithm Hash digest
SHA256 aa98ff73380a7bf423b7e125c9f782ba6ad4428cba346a8de56bb9be04299c4f
MD5 c62f38eba4e83dcf856b88fde910144f
BLAKE2b-256 cbd01e86782ddf4fe4a63c08bca805a85c7960cb1428e6436165f89086385646

See more details on using hashes here.

File details

Details for the file jupyter_cogram-0.7.4-py3-none-any.whl.

File metadata

  • Download URL: jupyter_cogram-0.7.4-py3-none-any.whl
  • Upload date:
  • Size: 38.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.4.2 importlib_metadata/4.8.1 pkginfo/1.7.1 requests/2.26.0 requests-toolbelt/0.9.1 tqdm/4.62.2 CPython/3.9.7

File hashes

Hashes for jupyter_cogram-0.7.4-py3-none-any.whl
Algorithm Hash digest
SHA256 7422b5fdf1cb0573e8ebb782e9ce417dd1cbee8732211a7981a21458a7d0880f
MD5 20ada978d1edd94434fa73d31aa0a019
BLAKE2b-256 c2bee66d723e0fc09944a0dc36f8deb39a7e05be392f711319558a16da49cf6f

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page