Leveraging Large Language Models to Build and Execute Computational Workflows

TL;DR

This paper investigates how large language models can be used to automatically generate and execute complex scientific workflows, reducing the need for traditional coding.

Contribution

It introduces a strategy for integrating LLMs with workflow management systems, exemplified by initial experiments with Phyloflow and OpenAI's API.

Findings

Successful initial integration with Phyloflow and OpenAI API

Proposed framework for LLM-driven scientific workflows

Potential to simplify complex scientific computations

Abstract

The recent development of large language models (LLMs) with multi-billion parameters, coupled with the creation of user-friendly application programming interfaces (APIs), has paved the way for automatically generating and executing code in response to straightforward human queries. This paper explores how these emerging capabilities can be harnessed to facilitate complex scientific workflows, eliminating the need for traditional coding methods. We present initial findings from our attempt to integrate Phyloflow with OpenAI's function-calling API, and outline a strategy for developing a comprehensive workflow management system based on these concepts.