Search:
Match:
2 results

Show HN: Adding Mistral Codestral and GPT-4o to Jupyter Notebooks

Published:Jul 2, 2024 14:23
1 min read
Hacker News

Analysis

This Hacker News article announces Pretzel, a fork of Jupyter Lab with integrated AI code generation features. It highlights the shortcomings of existing Jupyter AI extensions and the lack of GitHub Copilot support. Pretzel aims to address these issues by providing a native and context-aware AI coding experience within Jupyter notebooks, supporting models like Mistral Codestral and GPT-4o. The article emphasizes ease of use with a simple installation process and provides links to a demo video, a hosted version, and the project's GitHub repository. The core value proposition is improved AI-assisted coding within the popular Jupyter environment.
Reference

We’ve forked Jupyter Lab and added AI code generation features that feel native and have all the context about your notebook.

Open-source, browser-local data exploration tool

Published:Mar 15, 2024 16:02
1 min read
Hacker News

Analysis

This Hacker News post introduces Pretzel, an open-source data exploration and visualization tool that operates entirely within the browser. It leverages DuckDB-WASM and PRQL for data processing, offering a reactive interface where changes to filters automatically update subsequent data transformations. The tool supports large CSV and XLSX files, emphasizing its ability to handle sensitive data due to its offline capabilities. The post highlights key features like data transformation blocks, filtering, pivoting, and plotting, along with links to a demo and a screenshot. The use of DuckDB-WASM and PRQL is a key technical aspect, enabling in-browser data processing.
Reference

We’ve built Pretzel, an open-source data exploration and visualization tool that runs fully in the browser and can handle large files (200 MB CSV on my 8gb MacBook air is snappy). It’s also reactive - so if, for example, you change a filter, all the data transform blocks after it re-evaluate automatically.