Pretzel is a fork of JupyterLab that improves the user experience of the JupyterLab computational environment.
Project description
Pretzel
Pretzel is a fork of Jupyter with the goal to improve Jupyter's capabilities.
Switching to Pretzel from Jupyter is extremely easy. We use your existing Jupyter extensions, settings and keybindings.
We're building features such as:
- Native AI features similar to Cursor
- Frictionless realtime collaboration: pair-programming, comments, version history, etc.
- SQL support (both in code cells and as a standalone SQL IDE)
- Visual analysis builder (see more here)
- VSCode like code-writing experience using Monaco
- 1-click dashboard creation from data analysis results
- End-to-end analysis on datasets for non-data folks
Installation
Just as with Jupyter, you can install Pretzel by using pip:
pip install pretzelai
If using conda, first install pip with conda install pip
followed by pip install pretzelai
.
Then, start Pretzel with:
pretzel lab
Just as with Jupyter, you should see a URL to access the Pretzel interface.
Bleeding Edge Version
Bugs possible. To use the latest version of Pretzel:
- Make sure Node.js is installed and is version 18 or above
- Clone and install the package
git clone https://github.com/pretzelai/pretzelai.git
cd pretzelai
pip install .
Configuration
Pretzel comes with out-of-the-box support for a free AI server. You should be able to start using it with no configuration needed.
OpenAI Support You can configure Pretzel to use your own OpenAI API key. To do so:
- Open the
Settings
menu in the top menubar - Go down to
Settings Editor
, open it and search forPretzel
in the search box. SelectPretzel AI Settings
on the left bar. - From the
AI Service
dropdown, selectOpenAI API Key
and fill out your API key underOpenAI Settings > API Key
- If your company uses OpenAI Enterprise, then you can also enter the base URL for OpenAI call under
OpenAI Settings
Azure Support
Just as with OpenAI settings, you can also use Azure hosted models if you select Use Azure API
in the AI Service
dropdown. We haven't tested this so there may be bugs.
Usage
- When in a cell, press
Cmd+K
(Mac)/Ctrl+K
(Windows/Linux) to open AI prompting textbox to write your prompt- You can use
@variable
syntax to refer to variables and dataframes in memory. Press "Enter" to submit
- You can use
- You can accept/reject the response or edit your prompt if you want to re-submit with modifications
- Support for editing code
- If there's existing code in a cell, you can instruct the AI to edit code
- Selecting some code in a cell only edits the selected code
- Fix errors with AI: When there's an error, you'll see a button on top-right "Fix Error with AI"
Feedback, bugs and docs
- Please report bugs here: https://github.com/pretzelai/pretzelai/issues/
- Have any feedback? Any complains? We'd love feedback: founders@withpretzel.com
- Additional documentation will become available on our website by end of May!
Jupyter specific information
The original Jupyter documentation is available here and the Jupyterlab README is available here.
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
Built Distribution
Hashes for pretzelai-4.2.0-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 92a1fffef5ca67678202490e1257fff986536fc8cfe588d6d840b2879f628867 |
|
MD5 | 1f56f0e4dc653b46b3fa80f1e5b7f5b9 |
|
BLAKE2b-256 | 42aa0348e67df6ae7539a4a32cca78a7232655946bdcbd04f60a9c9ab379e397 |