HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face

TL;DR

HuggingGPT is an innovative framework that uses ChatGPT as a controller to orchestrate various AI models from Hugging Face, enabling the solving of complex, multi-domain AI tasks through language-based task planning and execution.

Contribution

This paper introduces HuggingGPT, a novel approach that leverages large language models to coordinate multiple AI models for solving complex tasks across different domains.

Findings

Successfully handled multi-domain AI tasks including language, vision, and speech.

Demonstrated effective task planning and model selection via ChatGPT.

Achieved impressive results in complex AI problem solving.

Abstract

Solving complicated AI tasks with different domains and modalities is a key step toward artificial general intelligence. While there are numerous AI models available for various domains and modalities, they cannot handle complicated AI tasks autonomously. Considering large language models (LLMs) have exhibited exceptional abilities in language understanding, generation, interaction, and reasoning, we advocate that LLMs could act as a controller to manage existing AI models to solve complicated AI tasks, with language serving as a generic interface to empower this. Based on this philosophy, we present HuggingGPT, an LLM-powered agent that leverages LLMs (e.g., ChatGPT) to connect various AI models in machine learning communities (e.g., Hugging Face) to solve AI tasks. Specifically, we use ChatGPT to conduct task planning when receiving a user request, select models according to their function descriptions available in Hugging Face, execute each subtask with the selected AI model, and summarize the response according to the execution results. By leveraging the strong language capability of ChatGPT and abundant AI models in Hugging Face, HuggingGPT can tackle a wide range of sophisticated AI tasks spanning different modalities and domains and achieve impressive results in language, vision, speech, and other challenging tasks, which paves a new way towards the realization of artificial general intelligence.