Skip to main content

A JupyterLab extension to get AI code completions with Codeium

Project description

jupyterlab-codeium

Github Actions Status lite-badge

JupyterLab extension to get AI code completions with Codeium.

https://github.com/jtpio/jupyterlab-codeium/assets/591645/7ec0a6fa-9c51-49a8-89b4-77b431f4bda9

[!WARNING] This extension is still very much experimental. It is not an official Codeium extension.

✨ Try it in your browser ✨

  1. Follow the instructions in the Usage section to get your API key.
  2. Open https://jtpio.github.io/jupyterlab-codeium in your browser

Requirements

  • JupyterLab >= 4.1.0

[!NOTE] This extension is also compatible with JupyterLite >= 0.3.0

Install

To install the extension, execute:

pip install jupyterlab-codeium

Usage

[!WARNING] Setting up the extension requires a Codeium API key. This part might still be challenging as retrieving the key requires a few manual steps at the moment. This might later be improved by providing a better auth flow.

  1. Go to the Codeium website and sign up for an account: https://codeium.com/
  2. Install the browser extension: https://codeium.com/chrome_tutorial
  3. Open the settings for the chrome extension and click on "Get Token"

Get Token

  1. Right click on the extension window and select "Inspect" to open the dev tools for the extension. Then click on "Network"
  2. Copy the token and paste it the input area, and then press "Enter Token"
  3. This should log a new API request in the network tab. Click on "Preview" to get the API key.

Enter Token

  1. Start JupyterLab. At first launch you should see the following dialog:

Enter API Key

  1. Go to the settings to paste the API key:

Settings

  1. You should now be able to use the extension. Open a Python file and start typing to see the completions.

Completions

Contributing

Packaging and releasing the extension

See RELEASE

Credits

Many thanks to the codemirror-codeium project for the inspiration and the initial implementation of the Codeium integration with CodeMirror 6: https://github.com/val-town/codemirror-codeium

The protobuf files were copied from that repo and reused as is in this project.

Project details


Download files

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

Source Distribution

jupyterlab_codeium-0.1.0.tar.gz (329.0 kB view details)

Uploaded Source

Built Distribution

jupyterlab_codeium-0.1.0-py3-none-any.whl (56.4 kB view details)

Uploaded Python 3

File details

Details for the file jupyterlab_codeium-0.1.0.tar.gz.

File metadata

  • Download URL: jupyterlab_codeium-0.1.0.tar.gz
  • Upload date:
  • Size: 329.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/5.1.0 CPython/3.11.9

File hashes

Hashes for jupyterlab_codeium-0.1.0.tar.gz
Algorithm Hash digest
SHA256 74655c80a0943ceb689d7998ca8ce88ebcf2ccca0a0c133917bfff4ebcb9f565
MD5 ad66aba98e5483eb74f27997033f7b12
BLAKE2b-256 395cce741e44deec55c64e1939e6544ba1f20a642e5ac474c0b5ff992e80b848

See more details on using hashes here.

File details

Details for the file jupyterlab_codeium-0.1.0-py3-none-any.whl.

File metadata

File hashes

Hashes for jupyterlab_codeium-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 48d70a0bf480d9bba51cf5274a8c022e4f15ea0c226c4b3b00db646043e273b0
MD5 017252732324dd68870fa295553f5482
BLAKE2b-256 7716d06abfdab45f0703305b9cbc96d5a4df92b2843d145c43bbc1d8a071c0b1

See more details on using hashes here.

Supported by

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