<div id="top"></div>
<div align="center">
<img src="docs/imgs/lagent_logo.png" width="450"/>
[](https://lagent.readthedocs.io/en/latest/)
[](https://pypi.org/project/lagent)
[](https://github.com/InternLM/lagent/tree/main/LICENSE)
[](https://github.com/InternLM/lagent/issues)
[](https://github.com/InternLM/lagent/issues)
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)
</div>
<p align="center">
👋 join us on <a href="https://twitter.com/intern_lm" target="_blank">𝕏 (Twitter)</a>, <a href="https://discord.gg/xa29JuW87d" target="_blank">Discord</a> and <a href="https://r.vansin.top/?r=internwx" target="_blank">WeChat</a>
</p>
<div align="center">
https://github.com/InternLM/lagent/assets/24622904/3242f9bf-32d2-4907-8815-e16a75a4ac0e
</div>
## 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:
## 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
<p>
<a href="">
<img src="https://img.shields.io/badge/Python-007ACC?style=for-the-badge&logo=python&logoColor=yellow" alt="python" />
</a>
### All Thanks To Our Contributors:
<a href="https://github.com/InternLM/lagent/graphs/contributors">
<img src="https://contrib.rocks/image?repo=InternLM/lagent" />
</a>
## 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).
<p align="right"><a href="#top">🔼 Back to top</a></p>
Raw data
{
"_id": null,
"home_page": "https://github.com/InternLM/lagent",
"name": "lagent",
"maintainer": null,
"docs_url": null,
"requires_python": null,
"maintainer_email": null,
"keywords": "artificial general intelligence, agent, agi, llm",
"author": null,
"author_email": null,
"download_url": "https://files.pythonhosted.org/packages/46/c7/7b29bbdce40e6db55c0a55bc607841a6c6e9f8561f6c6290f0a25d4422aa/lagent-0.2.4.tar.gz",
"platform": null,
"description": "<div id=\"top\"></div>\n<div align=\"center\">\n <img src=\"docs/imgs/lagent_logo.png\" width=\"450\"/>\n\n[](https://lagent.readthedocs.io/en/latest/)\n[](https://pypi.org/project/lagent)\n[](https://github.com/InternLM/lagent/tree/main/LICENSE)\n[](https://github.com/InternLM/lagent/issues)\n[](https://github.com/InternLM/lagent/issues)\n\n\n\n\n\nEnglish | [\u7b80\u4f53\u4e2d\u6587](README_zh-CN.md) | [\u65e5\u672c\u8a9e](README_ja_JP.md) | [\u0939\u093f\u0902\u0926\u0940](README_in_HIN.md) | [\u09ac\u09be\u0982\u09b2\u09be](README_in_beng.md) | [\ud55c\uad6d\uc5b4](README_KR_Kr.md)\n\n</div>\n\n<p align=\"center\">\n \ud83d\udc4b join us on <a href=\"https://twitter.com/intern_lm\" target=\"_blank\">\ud835\udd4f (Twitter)</a>, <a href=\"https://discord.gg/xa29JuW87d\" target=\"_blank\">Discord</a> and <a href=\"https://r.vansin.top/?r=internwx\" target=\"_blank\">WeChat</a>\n</p>\n\n<div align=\"center\">\n\nhttps://github.com/InternLM/lagent/assets/24622904/3242f9bf-32d2-4907-8815-e16a75a4ac0e\n\n</div>\n\n## Getting Started\n\nPlease 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.\n\n### Installation\n\nInstall with pip (Recommended).\n\n```bash\npip install lagent\n```\n\n### Run a Web Demo\n\nYou need to install Streamlit first.\n\n```bash\n# pip install streamlit\nstreamlit run examples/internlm2_agent_web_demo.py\n```\n\n## What's Lagent?\n\nLagent 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:\n\n\n\n## Major Features\n\n- Stream Output: Provides the `stream_chat` interface for streaming output, allowing cool streaming demos right at your local setup.\n- Interfacing is unified, with a comprehensive design upgrade for enhanced extensibility, including:\n - Model: Whether it's the OpenAI API, Transformers, or LMDeploy inference acceleration framework, you can seamlessly switch between models.\n - Action: Simple inheritance and decoration allow you to create your own personal toolkit, adaptable to both InternLM and GPT.\n - 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.\n- Documentation has been thoroughly upgraded with full API documentation coverage.\n\n## \ud83d\udcbbTech Stack\n\n<p>\n <a href=\"\">\n <img src=\"https://img.shields.io/badge/Python-007ACC?style=for-the-badge&logo=python&logoColor=yellow\" alt=\"python\" />\n </a>\n\n### All Thanks To Our Contributors:\n\n<a href=\"https://github.com/InternLM/lagent/graphs/contributors\">\n <img src=\"https://contrib.rocks/image?repo=InternLM/lagent\" />\n</a>\n\n## Citation\n\nIf you find this project useful in your research, please consider cite:\n\n```latex\n@misc{lagent2023,\n title={{Lagent: InternLM} a lightweight open-source framework that allows users to efficiently build large language model(LLM)-based agents},\n author={Lagent Developer Team},\n howpublished = {\\url{https://github.com/InternLM/lagent}},\n year={2023}\n}\n```\n\n## License\n\nThis project is released under the [Apache 2.0 license](LICENSE).\n\n<p align=\"right\"><a href=\"#top\">\ud83d\udd3c Back to top</a></p>\n\n\n",
"bugtrack_url": null,
"license": "Apache 2.0",
"summary": "A lightweight framework for building LLM-based agents",
"version": "0.2.4",
"project_urls": {
"Homepage": "https://github.com/InternLM/lagent"
},
"split_keywords": [
"artificial general intelligence",
" agent",
" agi",
" llm"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "b719c67d38acb3bf8d23291527c9d67e3ac50e59038345093c74cbea90360a28",
"md5": "bfa60c9414db566bebfaea7b583eabd8",
"sha256": "0072b27b4d0aca950e15e1671c3068a258d627ca0c63e8f1049dc0957ef8df0e"
},
"downloads": -1,
"filename": "lagent-0.2.4-py3-none-any.whl",
"has_sig": false,
"md5_digest": "bfa60c9414db566bebfaea7b583eabd8",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": null,
"size": 85636,
"upload_time": "2024-10-21T08:16:16",
"upload_time_iso_8601": "2024-10-21T08:16:16.801934Z",
"url": "https://files.pythonhosted.org/packages/b7/19/c67d38acb3bf8d23291527c9d67e3ac50e59038345093c74cbea90360a28/lagent-0.2.4-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "46c77b29bbdce40e6db55c0a55bc607841a6c6e9f8561f6c6290f0a25d4422aa",
"md5": "b8239a9e12a2d8d3c5ee327428b96376",
"sha256": "788bbbedcfaa902e6f7cbb2b8df9f330812d66a34c12175d410b1fa7705df6c0"
},
"downloads": -1,
"filename": "lagent-0.2.4.tar.gz",
"has_sig": false,
"md5_digest": "b8239a9e12a2d8d3c5ee327428b96376",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 60890,
"upload_time": "2024-10-21T08:16:19",
"upload_time_iso_8601": "2024-10-21T08:16:19.051219Z",
"url": "https://files.pythonhosted.org/packages/46/c7/7b29bbdce40e6db55c0a55bc607841a6c6e9f8561f6c6290f0a25d4422aa/lagent-0.2.4.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-10-21 08:16:19",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "InternLM",
"github_project": "lagent",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"requirements": [],
"lcname": "lagent"
}
JSON
