Note

🚧 This tool is under active development. We are looking for contributors, so please let us know if you’re interested! See the high-level roadmap of Honegumi’s development. If you like this tool, please consider starring it on GitHub.

Star Follow @sgbaird Watch Issue Discuss

Honegumi (骨組み), which means skeletal framework in Japanese, is a package for interactively creating API tutorials with a focus on optimization packages such as Meta’s Ax Platform. You can interact with Honegumi “in the flesh” using the interactive grid below. Select one option per row and watch the template dynamically appear. Click the “Open in Colab” badge to open a self-contained Google Colab notebook corresponding to the selected template. Click “Open in GitHub” to view the notebook source directly.

Honegumi

objective: single multi

model: GPEI FULLYBAYESIAN

existing_data: False True

sum_constraint: False

order_constraint: False

linear_constraint: False

composition_constraint: False

categorical: False True

custom_threshold: False True

synchrony: single batch

A Perfect Pairing with LLMs

Tip

Use Honegumi with ChatGPT to create non-halucinatory, custom Bayesian optimization scripts. See below for more info.

LLMs are good at recognizing patterns but really bad at suggesting Bayesian optimization scripts from scratch. Since Honegumi is really good at programatically giving valid Bayes opt scripts, you can use Honegumi to get a template and then ask an LLM to adapt it to your use case. The two-minute video below shows how a Honegumi template can be adapted using GPT-4 to a cookie taste optimization as a function of flour, sugar, and butter content.

Contents

• Quick Start
• License
• Note
• Contributions & Help
  • Issue Reports
  • Documentation Improvements
  • Code Contributions
  • Project Organization
  • Maintainer tasks
• License
• Authors
• Changelog
  • Version 0.1 (development)
• Module Reference
  • honegumi namespace
• GitHub Source

Indices and tables

• Index

• Module Index

• Search Page