We are thrilled to announce the launch of Einblick Prompt AI for JupyterLab (ai-einblick-prompt in your Extension Manager). This revolutionary extension will transform the way you work with data. Just like Prompt in our canvas-based notebooks, the extension is more than a tool, it’s an AI agent built for data scientists and data analysts to speed up all parts of the data workflow.
What is Einblick Prompt AI?
Einblick Prompt AI is your AI pair programmer, customized specifically for Python and data tasks. Blended seamlessly into the JupyterLab UI, users can now generate, modify, and fix code just with natural language requests. Whether you’re cleaning data, doing exploratory data analysis, or building complex ML models, Einblick Prompt AI accelerates your workflow, leaving you with more time to focus on the bigger picture.
Why use Einblick Prompt AI?
The Einblick team has seen the inroads made by generative AI technology over the past year, and we strongly believe that the future of code is natural language. No, natural language will not replace programming, but will serve as a vital tool that increases the efficiency of the programmer. As such, there are three modes that the Prompt extension takes on: generate, modify, and fix,
Generate: based on a natural language query and metadata, Prompt AI will write context-aware code
- There are a lot of code generators on the market these days, but Prompt AI stands out because it’s available where data scientists work: in Jupyter, and Prompt AI takes on the burden of processing the context around the data and the request.
- For example, Prompt can infer column names, and which dataset to use. Prompt will even one-hot encode categorical variables and impute missing data, without user specification if the users asks to build a regression model.
Modify: change, tweak, and refine any existing code cells. Just ask Prompt how you’d like to alter the Python code, and Prompt will do it, leaving behind comments and explanations of what it changed.
- Modify is an important mode as it speeds up the iterative process of data analysis and data science.
- This mode also allows you to easily compare different visualizations and models as you can just duplicate a cell and then modify one version.
Fix: digging through documentation is tedious and time consuming, so let Prompt debug for you. Prompt will locate and fix errors in code, while providing explanations for what needed to be fixed.
- Debugging with just a click is a feature that allows you to program much more quickly, without being interrupted by pesky syntactical updates.
If you want to learn more about how we built our extension, check out our technical blog post on domain-specific code generation.
Quick Start Guide
The ai-einblick-prompt extension is available to JupyterLab users:
- From the JupyterLab Extension Manager, install
ai-einblick-prompt.- Or, using Terminal or the Command Line, use
pip install ai-einblick-promptand start JupyterLab withjupyter lab
- Or, using Terminal or the Command Line, use
- Read in a dataset
- Click the terminal icon on the right hand side of any Python cell, and select “Generate.”
- Ask Einblick Prompt AI to write code.
About
Einblick is an AI-native data science platform that provides data teams with an agile workflow to swiftly explore data, build predictive models, and deploy data apps. Founded in 2020, Einblick was developed based on six years of research at MIT and Brown University. Einblick is funded by Amplify Partners, Flybridge, Samsung Next, Dell Technologies Capital, and Intel Capital. For more information, please visit www.einblick.ai and follow us on LinkedIn and Twitter.