JARVIS

# JARVIS


[![arXiv](https://img.shields.io/badge/arXiv-Paper-<COLOR>.svg)](https://arxiv.org/abs/2303.17580)
[![Open in Spaces](https://img.shields.io/badge/%F0%9F%A4%97-Open%20in%20Spaces-blue)](https://huggingface.co/spaces/microsoft/HuggingGPT)

The mission of JARVIS is to explore artificial general intelligence (AGI) and deliver cutting-edge research to the whole community.

## What's New

+  [2024.01.15] We release Easytool for easier tool usage.
   + The code and datasets are available at [EasyTool](/easytool).
   + The paper is available at [EasyTool: Enhancing LLM-based Agents with Concise Tool Instruction](https://arxiv.org/abs/2401.06201).
+  [2023.11.30] We release TaskBench for evaluating task automation capability of LLMs.
   + The code and datasets are available at [TaskBench](/taskbench).
   + The paper is available at [TaskBench: Benchmarking Large Language Models for Task Automation](https://arxiv.org/abs/2311.18760).
+  [2023.07.28] We are now in the process of planning evaluation and project rebuilding. We will release a new version of Jarvis in the near future.
+  [2023.07.24] We released a light langchain version of Jarvis. See <a href="https://github.com/langchain-ai/langchain/tree/master/libs/experimental/langchain_experimental/autonomous_agents/hugginggpt">here</a>.
+  [2023.04.16] Jarvis now supports the OpenAI service on the Azure platform and the GPT-4 model.
+  [2023.04.06] We added the Gradio demo and built the web API for `/tasks` and `/results` in `server` mode.
   +  The Gradio demo is now hosted on Hugging Face Space. (Build with `inference_mode=hybrid` and `local_deployment=standard`)
   +  The Web API `/tasks` and `/results` access intermediate results for `Stage #1`: task planning and `Stage #1-3`: model selection with execution results. See <a href="#Server">here</a>.
+  [2023.04.03] We added the CLI mode and provided parameters for configuring the scale of local endpoints.
   +  You can enjoy a lightweight experience with Jarvis without deploying the models locally. See <a href="#Configuration">here</a>.
   +  Just run `python awesome_chat.py --config configs/config.lite.yaml` to experience it.
+  [2023.04.01] We updated a version of code for building.


### Overview

Language serves as an interface for LLMs to connect numerous AI models for solving complicated AI tasks!

<p align="center">
<img width="100%" alt="image" src="./hugginggpt/assets/intro.png">    
</p>


See our paper: [HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in HuggingFace](http://arxiv.org/abs/2303.17580), Yongliang Shen, Kaitao Song, Xu Tan, Dongsheng Li, Weiming Lu and Yueting Zhuang (the first two authors contribute equally)

We introduce a collaborative system that consists of **an LLM as the controller** and **numerous expert models as collaborative executors** (from HuggingFace Hub). The workflow of our system consists of four stages:
+ **Task Planning**: Using ChatGPT to analyze the requests of users to understand thei