Open

BOPE-GPT is a full stack web app acting as a dashboard to conduct the BOPE process on custom datasets via an LLM, built with Next.js, FastAPI, MongoDB, Pytorch ML library functions, and Cohere's LLM API. With rich visualizations via Plotly.

Read more at: https://github.com/imperorrp/BOPE-GPT

Premise:

BOPE-GPT facilitates the BOPE process -Bayesian Optimization with Preference Exploration- via LLMs as proxies for human preference selectors and with rich visualizations.

The BOPE process is essentially an optimization technique involving machine learning of finding optimal input parameters for 'expensive' (hard to evaluate or gather data), multi-objective functions/experiments. It was first introduced in 2022.

This app facilitates performing the BOPE process with a direct UI, visualizations, and stringing together and orchestrating all the steps involved so custom scripts and Jupyter Notebooks don't have to be used.

Upload the Fischer-Tropsch dataset (see more on the site) and set the suggested input parameters in the "About BOPE-GPT" tab on the site to try it out!

Note:

I host the live demo backend on a personal VPS and each BOPE iteration is very inference heavy, so iteration speeds can be slow (Upto 2 minutes per iteration). You can clone the repo, grab requisite API keys and try it out locally for better performance.