Skip to main content

JupyAI

Github Actions Status

JupyAI adds AI capabilities to JupyterLab:

  • Code generation (generate code based on a prompt)
  • Code modifications (update existing code)
  • Code fixing (fix broken code)

https://github.com/ploomber/jupyai/assets/989250/18447b68-3ee2-434e-b626-18fc35cb822f

User notes

To switch the model (defaults to gpt-3.5-turbo), open JupyterLab preferences, type JupyAI and you'll see a text field to change the model name. For example, to switch to GPT-4, enter gpt-4.

To see the valid values, consult OpenAI's documentation.

Development notes

  • The prompts are hardcoded, it'd be better to add an option to customize them
  • Only OpenAI is supported for now

PRs welcome!

Requirements

  • JupyterLab >= 4.0.0

Install

pip install jupyai

Usage

# set your OpenAI key
export OPENAI_API_KEY=YOURKEY

# start JupyterLab
jupyter lab

Once installed, you'll see a magic wand on each cell, click it to trigger code completion. You can also use CMD + ENTER (see demo at the top of this file).

Uninstall

To remove the extension, execute:

pip uninstall jupyai

Troubleshoot

If you are seeing the frontend extension, but it is not working, check that the server extension is enabled:

jupyter server extension list

If the server extension is installed and enabled, but you are not seeing the frontend extension, check the frontend extension is installed:

jupyter labextension list

Contributing

See CONTRIBUTING.md

Alternatives

Jupyter AI is another extension that brings AI capabilities to Jupyter. It has a lot of great features!

However, Jupyter AI generates code in the cell's output; hence, you need to copy-paste code if you want to run it or if you want to update existing code. JupyAI adds code to the cell itself, allowing you to edit it and run it as you'd normally do.

Metadata

Release files for jupyai 0.1.2

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for jupyai 0.1.2
File Size Uploaded
jupyai-0.1.2.tar.gz 203.3 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for jupyai 0.1.2
File Interpreter ABI Platform
jupyai-0.1.2-py3-none-any.whl Python 3 none any Details

Total release size: 234.2 kB

Release files / jupyai-0.1.2.tar.gz

Download URL jupyai-0.1.2.tar.gz
Size 203.3 kB
Tags Source
SHA-256 checksum
How to use checksums
79183971de216961cab258fbaf39d3b1d1873f50b3dd3a5cc35e74c62944173c
BLAKE2b-256 checksum
How to use checksums
116b19a9451e879182cfbecb18722704a194ea1adf80690184f62e4fb170ecb2
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/4.0.2 CPython/3.11.7

Release files / jupyai-0.1.2-py3-none-any.whl

Download URL jupyai-0.1.2-py3-none-any.whl
Size 30.9 kB
Tags Python 3
SHA-256 checksum
How to use checksums
54ebf7c2ff8653b9b49f245ce3e7659197487b136a8a197086d34d172dfa81a7
BLAKE2b-256 checksum
How to use checksums
95040a4556f8f4f6363b98e9b59faeff12e871cb9da3af1fd6ba7b9437e460dd
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/4.0.2 CPython/3.11.7

Release history Release notifications | RSS feed

This release

0.1.2 This release

2 release files

0.1.1

2 release files

0.1.0

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page