DeepAI AI Chat
Log In Sign Up

HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in HuggingFace

by   Yongliang Shen, et al.
Zhejiang University

Solving complicated AI tasks with different domains and modalities is a key step toward advanced artificial intelligence. While there are abundant AI models available for different domains and modalities, they cannot handle complicated AI tasks. Considering large language models (LLMs) have exhibited exceptional ability 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 and language could be a generic interface to empower this. Based on this philosophy, we present HuggingGPT, a framework 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 is able to cover numerous sophisticated AI tasks in different modalities and domains and achieve impressive results in language, vision, speech, and other challenging tasks, which paves a new way towards advanced artificial intelligence.


page 5

page 8

page 9

page 10

page 11

page 13

page 14

page 15


Visual Abstraction and Reasoning through Language

While Artificial Intelligence (AI) models have achieved human or even su...

The System Model and the User Model: Exploring AI Dashboard Design

This is a speculative essay on interface design and artificial intellige...

AutoML-GPT: Automatic Machine Learning with GPT

AI tasks encompass a wide range of domains and fields. While numerous AI...

Data-Copilot: Bridging Billions of Data and Humans with Autonomous Workflow

Various industries such as finance, meteorology, and energy generate vas...

On Controllability of AI

Invention of artificial general intelligence is predicted to cause a shi...

Choose, not Hoard: Information-to-Model Matching for Artificial Intelligence in O-RAN

Open Radio Access Network (O-RAN) is an emerging paradigm, whereby virtu...

Code Repositories


JARVIS, a system to connect LLMs with ML community

view repo