Prompto: An open source library for asynchronous querying of LLM endpoints

TL;DR

Prompto is an open source Python library that enables asynchronous, efficient querying of multiple LLM endpoints simultaneously, simplifying research, comparison, and experimentation with large language models.

Contribution

It introduces a novel library that streamlines multi-model LLM interaction, improving efficiency and reproducibility in research workflows.

Findings

Enables concurrent querying of multiple LLMs

Maximizes efficiency by respecting individual rate limits

Facilitates faster experimentation and data collection

Abstract

Recent surge in Large Language Model (LLM) availability has opened exciting avenues for research. However, efficiently interacting with these models presents a significant hurdle since LLMs often reside on proprietary or self-hosted API endpoints, each requiring custom code for interaction. Conducting comparative studies between different models can therefore be time-consuming and necessitate significant engineering effort, hindering research efficiency and reproducibility. To address these challenges, we present prompto, an open source Python library which facilitates asynchronous querying of LLM endpoints enabling researchers to interact with multiple LLMs concurrently, while maximising efficiency and utilising individual rate limits. Our library empowers researchers and developers to interact with LLMs more effectively and allowing faster experimentation, data generation and evaluation. prompto is released with an introductory video (https://youtu.be/lWN9hXBOLyQ) under MIT License and is available via GitHub (https://github.com/alan-turing-institute/prompto).