Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

https://github.com/InternLM/lagent

A lightweight framework for building LLM-based agents
https://github.com/InternLM/lagent

agent gpt llm transformers

Last synced: about 1 month ago
JSON representation

A lightweight framework for building LLM-based agents

Host: GitHub
URL: https://github.com/InternLM/lagent
Owner: InternLM
License: apache-2.0
Created: 2023-08-20T12:45:45.000Z (10 months ago)
Default Branch: main
Last Pushed: 2024-04-27T12:50:56.000Z (about 2 months ago)
Last Synced: 2024-05-06T00:03:35.417Z (about 2 months ago)
Topics: agent, gpt, llm, transformers
Language: Python
Homepage:
Size: 348 KB
Stars: 852
Watchers: 10
Forks: 90
Open Issues: 16
Metadata Files:
- Readme: README.md
- License: LICENSE

Lists

awesome-langchain - Lagent - based agents ![GitHub Repo stars](https://img.shields.io/github/stars/InternLM/lagent?style=social) (Other LLM Frameworks / Videos Playlists)
awesome-langchain-zh - Lagent
awesome-stars - InternLM/lagent - A lightweight framework for building LLM-based agents (Python)
awesome-LLM-resourses - Lagent - based agents. (Agents)

README

        




  

[![docs](https://img.shields.io/badge/docs-latest-blue)](https://lagent.readthedocs.io/en/latest/)

[![PyPI](https://img.shields.io/pypi/v/lagent)](https://pypi.org/project/lagent)

[![license](https://img.shields.io/github/license/InternLM/lagent.svg)](https://github.com/InternLM/lagent/tree/main/LICENSE)

[![issue resolution](https://img.shields.io/github/issues-closed-raw/InternLM/lagent)](https://github.com/InternLM/lagent/issues)

[![open issues](https://img.shields.io/github/issues-raw/InternLM/lagent)](https://github.com/InternLM/lagent/issues)

![Visitors](https://api.visitorbadge.io/api/visitors?path=InternLM%2Flagent%20&countColor=%23263759&style=flat)

![GitHub forks](https://img.shields.io/github/forks/InternLM/lagent)

![GitHub Repo stars](https://img.shields.io/github/stars/InternLM/lagent)

![GitHub contributors](https://img.shields.io/github/contributors/InternLM/lagent)

English | [简体中文](README_zh-CN.md) | [日本語](README_ja_JP.md) | [हिंदी](README_in_HIN.md) | [বাংলা](README_in_beng.md) | [한국어](README_KR_Kr.md)





    👋 join us on 𝕏 (Twitter), Discord and WeChat





https://github.com/InternLM/lagent/assets/24622904/3242f9bf-32d2-4907-8815-e16a75a4ac0e



## Getting Started

Please see the [overview](docs/en/get_started/overview.md) for the general introduction of Lagent. Meanwhile, we provide extremely simple code for quick start. You may refer to [examples](examples/) for more details.

### Installation

Install with pip (Recommended).

```bash

pip install lagent

```

### Run a Web Demo

You need to install Streamlit first.

```bash

# pip install streamlit

streamlit run examples/internlm2_agent_web_demo.py

```

## What's Lagent?

Lagent is a lightweight open-source framework that allows users to efficiently build large language model(LLM)-based agents. It also provides some typical tools to augment LLM. The overview of our framework is shown below:

![image](https://github.com/InternLM/lagent/assets/24351120/cefc4145-2ad8-4f80-b88b-97c05d1b9d3e)

## Major Features

- Stream Output: Provides the `stream_chat` interface for streaming output, allowing cool streaming demos right at your local setup.

- Interfacing is unified, with a comprehensive design upgrade for enhanced extensibility, including:

  - Model: Whether it's the OpenAI API, Transformers, or LMDeploy inference acceleration framework, you can seamlessly switch between models.

  - Action: Simple inheritance and decoration allow you to create your own personal toolkit, adaptable to both InternLM and GPT.

  - Agent: Consistent with the Model's input interface, the transformation from model to intelligent agent only takes one step, facilitating the exploration and implementation of various agents.

- Documentation has been thoroughly upgraded with full API documentation coverage.

## 💻Tech Stack



  

    

  

### All Thanks To Our Contributors:



  



## Citation

If you find this project useful in your research, please consider cite:

```latex

@misc{lagent2023,

    title={{Lagent: InternLM} a lightweight open-source framework that allows users to efficiently build large language model(LLM)-based agents},

    author={Lagent Developer Team},

    howpublished = {\url{https://github.com/InternLM/lagent}},

    year={2023}

}

```

## License

This project is released under the [Apache 2.0 license](LICENSE).

🔼 Back to top