<div align="center">
<h1 align="center">Keia: A Pair Agent for AI Engineer / Researchers</h1>
<p align="center">:love_letter: Fathers' love for Keia :love_letter:</p>
<img alt="keia-llama" height="200px" src="assets/keia_llama.webp">
<a href="https://discord.gg/SgxBpENGRG"><img src="https://img.shields.io/badge/Discord-Join%20Us-purple?logo=discord&logoColor=white&style=flat" alt="Join our Discord community"></a>
</div>
## Overview
_The project is under active development. The API may change frequently._
**Keia (MLE-Agent)** is designed to be a pair agent for machine learning engineers or researchers. It includes two modes: **Baseline Mode** and **Advanced Mode**.
:coffee: **Baseline Mode** is designed to quickly build a baseline model for users' projects.
:fire: **Advanced Mode (Coming Soon)** is designed to utilize users' favorite MLOps tools, understand SOTA methods, and suggest optimizations for users' machine learning projects.
## Milestones
:rocket: June 1st, 2024: Release the **Baseline Mode** (v0.1.0)
## Get started
### Installation
install from pypi
```bash
pip install mle-agent
```
install from source
```bash
git clone git@github.com:MLSysOps/MLE-agent.git
pip install .
```
### Configuration
You need to set up an LLM and choose tools before using the agent.
```bash
mle config
```
### Usage (Baseline Mode)
Create a new project
```bash
mle new <project name>
```
Start a project
```bash
mle start
```
Other operations.
```bash
mle project ls # show all the available projects
mle project delete <project name> # delete a given project
mle project switch # switch the current working project
```
## Roadmap
The following is a list of features that we plan to implement in the future. The list is not exhaustive, and we may add more features as we go along.
### Plan, Generate, Execute and Debug Code
- [x] An easy-to-use CLI interface
- [x] Create/Select/Delete a project
- [x] Understand users' requirements to suggest the file name, dataset, task, model arch, etc
- [x] Generate a detailed coding plan
- [x] Write baseline model code
- [x] Execute the code on the local machine / cloud
- [x] Debug the code and revise the code
- [x] Googling the error message to debug the code
- [ ] Data Augmentation
- [ ] Hyperparameter tuning
- [ ] Model evaluation
### Better user experience
- [ ] web interface (coming soon)
- [ ] discord bot
### Integrate with AI/ML Tools
- [ ] snowflake / databricks
- [ ] wandb / mlflow
- [x] skypilot
- [ ] dbt / airflow
### Integrate with research tools
- [ ] huggingface
- [ ] paper with code
- [ ] arxiv
## Contributing
We welcome contributions from the community. We are looking for contributors to help us with the following tasks:
- Benchmark and Evaluate the agent
- Add more features to the agent
- Improve the documentation
- Write tests
If you are interested in contributing, please check the [CONTRIBUTING.md](CONTRIBUTING.md) file.
## Support and Community
- [Discord community](https://discord.gg/SgxBpENGRG). If you have any questions, please feel free to ask in the Discord community.
- [Twitter](https://twitter.com/MLE_Agent). Follow us on Twitter to get the latest updates.
## Acknowledgements
We would like to thank the following contributors for their help with the project:
## License
Check [LICENSE](LICENSE) file for more information.
Raw data
{
"_id": null,
"home_page": "https://github.com/MLSysOps/MLE-agent",
"name": "mle-agent",
"maintainer": null,
"docs_url": null,
"requires_python": null,
"maintainer_email": null,
"keywords": "LLM, deep learning, MLOps, shell, neural networks",
"author": "Yizheng Huang, Huaizheng Zhang",
"author_email": "huangyz0918@gmail.com",
"download_url": "https://files.pythonhosted.org/packages/73/b2/a47980d0e95b904f70dac02dfab9fdae6e9317d8c919b30d94b00a66d330/mle_agent-0.1.3.tar.gz",
"platform": null,
"description": "<div align=\"center\">\n<h1 align=\"center\">Keia: A Pair Agent for AI Engineer / Researchers</h1>\n<p align=\"center\">:love_letter: Fathers' love for Keia :love_letter:</p>\n<img alt=\"keia-llama\" height=\"200px\" src=\"assets/keia_llama.webp\">\n\n\n\n\n\n\n\n\n<a href=\"https://discord.gg/SgxBpENGRG\"><img src=\"https://img.shields.io/badge/Discord-Join%20Us-purple?logo=discord&logoColor=white&style=flat\" alt=\"Join our Discord community\"></a>\n\n</div>\n\n\n## Overview\n_The project is under active development. The API may change frequently._\n\n**Keia (MLE-Agent)** is designed to be a pair agent for machine learning engineers or researchers. It includes two modes: **Baseline Mode** and **Advanced Mode**. \n\n:coffee: **Baseline Mode** is designed to quickly build a baseline model for users' projects.\n\n:fire: **Advanced Mode (Coming Soon)** is designed to utilize users' favorite MLOps tools, understand SOTA methods, and suggest optimizations for users' machine learning projects.\n\n\n\n\n## Milestones\n\n:rocket: June 1st, 2024: Release the **Baseline Mode** (v0.1.0)\n\n## Get started\n\n### Installation\n\ninstall from pypi\n```bash\npip install mle-agent\n```\n\ninstall from source\n```bash\ngit clone git@github.com:MLSysOps/MLE-agent.git\npip install .\n```\n\n### Configuration\n\nYou need to set up an LLM and choose tools before using the agent.\n```bash\nmle config\n```\n\n### Usage (Baseline Mode)\n\nCreate a new project\n```bash\nmle new <project name>\n```\n\nStart a project\n```bash\nmle start\n```\n\nOther operations.\n```bash\nmle project ls # show all the available projects\nmle project delete <project name> # delete a given project\nmle project switch # switch the current working project\n```\n\n## Roadmap\n\nThe following is a list of features that we plan to implement in the future. The list is not exhaustive, and we may add more features as we go along.\n\n### Plan, Generate, Execute and Debug Code\n\n- [x] An easy-to-use CLI interface\n- [x] Create/Select/Delete a project\n- [x] Understand users' requirements to suggest the file name, dataset, task, model arch, etc\n- [x] Generate a detailed coding plan\n- [x] Write baseline model code\n- [x] Execute the code on the local machine / cloud\n- [x] Debug the code and revise the code\n- [x] Googling the error message to debug the code\n- [ ] Data Augmentation\n- [ ] Hyperparameter tuning\n- [ ] Model evaluation\n\n### Better user experience\n\n- [ ] web interface (coming soon)\n- [ ] discord bot\n\n### Integrate with AI/ML Tools\n\n- [ ] snowflake / databricks \n- [ ] wandb / mlflow \n- [x] skypilot\n- [ ] dbt / airflow\n\n### Integrate with research tools\n\n- [ ] huggingface\n- [ ] paper with code\n- [ ] arxiv\n\n## Contributing\n\nWe welcome contributions from the community. We are looking for contributors to help us with the following tasks:\n\n- Benchmark and Evaluate the agent\n- Add more features to the agent\n- Improve the documentation\n- Write tests\n\nIf you are interested in contributing, please check the [CONTRIBUTING.md](CONTRIBUTING.md) file.\n\n## Support and Community\n\n- [Discord community](https://discord.gg/SgxBpENGRG). If you have any questions, please feel free to ask in the Discord community.\n- [Twitter](https://twitter.com/MLE_Agent). Follow us on Twitter to get the latest updates.\n\n## Acknowledgements\n\nWe would like to thank the following contributors for their help with the project:\n\n\n## License\n\nCheck [LICENSE](LICENSE) file for more information.\n",
"bugtrack_url": null,
"license": null,
"summary": "MLE-agent: An agent to automate your MLE processes",
"version": "0.1.3",
"project_urls": {
"Download": "https://github.com/MLSysOps/MLE-agent/archive/refs/heads/main.zip",
"Homepage": "https://github.com/MLSysOps/MLE-agent"
},
"split_keywords": [
"llm",
" deep learning",
" mlops",
" shell",
" neural networks"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "91a0f8592d4fbbc9d0bae7ee67fe9ec2583734773038ca029bd76d40d65e60d3",
"md5": "4db6378dfce2d8b37592dd5d8371ff78",
"sha256": "b4ddb10bac8107c33f6b47fb5967c4c76b2034dd25ead27081adf6b5fdd4d3c7"
},
"downloads": -1,
"filename": "mle_agent-0.1.3-py3-none-any.whl",
"has_sig": false,
"md5_digest": "4db6378dfce2d8b37592dd5d8371ff78",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": null,
"size": 35947,
"upload_time": "2024-06-04T00:58:06",
"upload_time_iso_8601": "2024-06-04T00:58:06.164554Z",
"url": "https://files.pythonhosted.org/packages/91/a0/f8592d4fbbc9d0bae7ee67fe9ec2583734773038ca029bd76d40d65e60d3/mle_agent-0.1.3-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "73b2a47980d0e95b904f70dac02dfab9fdae6e9317d8c919b30d94b00a66d330",
"md5": "d1b1cf6dd6151cad6258be3d84387add",
"sha256": "d06901b238e0e873fbbff938ce6925ed9da17f3fdea487d1cd009a3d1e71f3d4"
},
"downloads": -1,
"filename": "mle_agent-0.1.3.tar.gz",
"has_sig": false,
"md5_digest": "d1b1cf6dd6151cad6258be3d84387add",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 30307,
"upload_time": "2024-06-04T00:58:07",
"upload_time_iso_8601": "2024-06-04T00:58:07.267808Z",
"url": "https://files.pythonhosted.org/packages/73/b2/a47980d0e95b904f70dac02dfab9fdae6e9317d8c919b30d94b00a66d330/mle_agent-0.1.3.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-06-04 00:58:07",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "MLSysOps",
"github_project": "MLE-agent",
"github_not_found": true,
"lcname": "mle-agent"
}
JSON
