gpt_jupyterlab

A JupyterLab extension.

GPT JupterLab is a JupyterLab extension to use OpenAI’s GPT models for text and code completion on your notebook cells.

This extension passes your current notebook cell to the GPT API and completes your code/text for you. You can customize the GPT parameters in the Advanced Settings menu.

This extension is composed of a Python package named gpt_jupyterlab for the server extension and a NPM package named gpt_jupyterlab for the frontend extension.

Note: You will need your own OpenAI API Key to use this extension. You can get them in the API Key page, which requires an OpenAI account.

https://user-images.githubusercontent.com/1387307/214353795-d867d9d1-caee-4494-a2ee-14d5f12005e7.mp4

Install

To install the extension, execute:

pip install gpt_jupyterlab

It should now appear on your installed extensions list.

Note: Make sure that you have enabled extensions. You may also need to restart the server(not the kernel) to make sure that it runs properly.

Installing in GCP Vertex Workbench

1. Create new notebook

2. Run pip install gpt_jupyterlab

3. Enable extensions

You should see gpt_jupyterlab installed, but you need to restart the server to make

4. Restart the notebook

Stop the notebook

Start the notebook

You should be able to see the GPT button and be able to make queries.

Uninstall

To remove the extension, execute:

pip uninstall gpt_jupyterlab

Getting Started

There are three ways to prompt the GPT API.

1. Use the GPT Button in the Toolbar

2. Click GPT Completion under the Edit Menu

3. Use the Ctrl+Space(Windows)/Cmd+Space(Mac) Keyboard Shortcut

How to Change Your Settings

Go to the Settings Menu and click Advanced Settings Editor

Click gpt_jupyterlab in the left sidebar

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

Development install

Note: You will need NodeJS to build the extension package.

The jlpm command is JupyterLab's pinned version of yarn that is installed with JupyterLab. You may use yarn or npm in lieu of jlpm below.

# Clone the repo to your local environment
# Change directory to the gpt_jupyterlab directory
# Install package in development mode
pip install -e ".[test]"
# Link your development version of the extension with JupyterLab
jupyter labextension develop . --overwrite
# Server extension must be manually installed in develop mode
jupyter server extension enable gpt_jupyterlab
# Rebuild extension Typescript source after making changes
jlpm build

You can watch the source directory and run JupyterLab at the same time in different terminals to watch for changes in the extension's source and automatically rebuild the extension.

# Watch the source directory in one terminal, automatically rebuilding when needed
jlpm watch
# Run JupyterLab in another terminal
jupyter lab

With the watch command running, every saved change will immediately be built locally and available in your running JupyterLab. Refresh JupyterLab to load the change in your browser (you may need to wait several seconds for the extension to be rebuilt).

By default, the jlpm build command generates the source maps for this extension to make it easier to debug using the browser dev tools. To also generate source maps for the JupyterLab core extensions, you can run the following command:

jupyter lab build --minimize=False

Development uninstall

# Server extension must be manually disabled in develop mode
jupyter server extension disable gpt_jupyterlab
pip uninstall gpt_jupyterlab

In development mode, you will also need to remove the symlink created by jupyter labextension develop command. To find its location, you can run jupyter labextension list to figure out where the labextensions folder is located. Then you can remove the symlink named gpt_jupyterlab within that folder.

Testing the extension

Server tests

This extension is using Pytest for Python code testing.

Install test dependencies (needed only once):

pip install -e ".[test]"
# Each time you install the Python package, you need to restore the front-end extension link
jupyter labextension develop . --overwrite

To execute them, run:

pytest -vv -r ap --cov gpt_jupyterlab

Frontend tests

This extension is using Jest for JavaScript code testing.

To execute them, execute:

jlpm
jlpm test

Integration tests

This extension uses Playwright for the integration tests (aka user level tests). More precisely, the JupyterLab helper Galata is used to handle testing the extension in JupyterLab.

More information are provided within the ui-tests README.

Packaging the extension

See RELEASE