<img src="./docs/assets/img/icon.svg" title="iauto" height="128">
[Documentation](https://shellc.github.io/iauto)
# iauto
`iauto` is a low-code engine for building and deploying AI agents.
- **AI**: Cutting-edge AI capabilities.
- **Low-Code**: Define your agents using YAML.
- **Automation**: Integrated automation frameworks like [Appium](https://github.com/appium/appium) and [Playwright](https://playwright.dev/python/).
- **Extensible**: Well-designed Python API.
## News
- Integrated [autogen](https://github.com/microsoft/autogen): Create your Multi-Agent system efficiently with iauto.
- Run most open source LLMs locally using [llama.cpp](https://github.com/ggerganov/llama.cpp) and [llama-cpp-python](https://github.com/abetlen/llama-cpp-python).
## Quick Start
### Installation
Python version requirement: >=3.8
`iauto` can be installed from PyPI using `pip`. It is recommended to create a new virtual environment before installation to avoid conflicts.
```bash
pip install -U iauto
```
If you want to run LLM locally, you can enable hardware acceleration in the following ways.
To enable cuBLAS acceleration on NVIDIA GPU:
```bash
CMAKE_ARGS="-DGGML_CUBLAS=ON" pip install -U iauto
```
To enable Metal on Apple silicon devices:
```bash
CMAKE_ARGS="-DGGML_METAL=ON" pip install -U iauto
```
## Command-line tool
Usage:
```bash
python -m iauto --help
or
ia --help
```
Run playbook:
```bash
ia run ./your-plabook.yaml
```
**[Example playbooks](./playbooks)**
## Playground
`iauto` provides a web-based application for running playbooks, LLM Chat, ReAct reasoning, and Multi-Agent tasks.
Launch playground:
```bash
ia playground
```
**Screenshot:**
## Contribution
We are extremely open to contributions, whether it be in the form of a new feature, improved infrastructure, or better documentation.
### Development setup
- Code Style: [PEP-8](https://peps.python.org/pep-0008/)
- Docstring Style: [Google Style](https://sphinxcontrib-napoleon.readthedocs.io/en/latest/example_google.html)
```bash
# Create python venv
python -m venv .venv
source .venv/bin/activate
# Install dependencies
pip install -r requirements.txt
pip install -r requirements-dev.txt
# Apply autopep8, isort and flake8 as pre commit hooks
pre-commit install
```
### Build
```bash
./build.sh
```
## License
[MIT](./LICENSE)
<img src="./docs/assets/img/icon.svg" title="iauto" height="16"> icon license: https://openmoji.org/library/emoji-1F9BE
Raw data
{
"_id": null,
"home_page": "https://github.com/shellc/iauto",
"name": "iauto",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.8",
"maintainer_email": null,
"keywords": "AI, Automation, LLM, RPA",
"author": "shellc",
"author_email": "shenggong.wang@gmail.com",
"download_url": null,
"platform": null,
"description": "<img src=\"./docs/assets/img/icon.svg\" title=\"iauto\" height=\"128\">\n\n[Documentation](https://shellc.github.io/iauto)\n\n# iauto\n\n`iauto` is a low-code engine for building and deploying AI agents.\n\n- **AI**: Cutting-edge AI capabilities.\n- **Low-Code**: Define your agents using YAML.\n- **Automation**: Integrated automation frameworks like [Appium](https://github.com/appium/appium) and [Playwright](https://playwright.dev/python/).\n- **Extensible**: Well-designed Python API.\n\n## News\n\n- Integrated [autogen](https://github.com/microsoft/autogen): Create your Multi-Agent system efficiently with iauto.\n- Run most open source LLMs locally using [llama.cpp](https://github.com/ggerganov/llama.cpp) and [llama-cpp-python](https://github.com/abetlen/llama-cpp-python).\n\n## Quick Start\n\n### Installation\n\nPython version requirement: >=3.8\n\n`iauto` can be installed from PyPI using `pip`. It is recommended to create a new virtual environment before installation to avoid conflicts.\n\n```bash\npip install -U iauto\n```\n\nIf you want to run LLM locally, you can enable hardware acceleration in the following ways.\n\nTo enable cuBLAS acceleration on NVIDIA GPU:\n\n```bash\nCMAKE_ARGS=\"-DGGML_CUBLAS=ON\" pip install -U iauto\n```\n\nTo enable Metal on Apple silicon devices:\n\n```bash\nCMAKE_ARGS=\"-DGGML_METAL=ON\" pip install -U iauto\n```\n\n## Command-line tool\n\nUsage:\n\n```bash\npython -m iauto --help\n\nor\n\nia --help\n```\n\nRun playbook:\n\n```bash\nia run ./your-plabook.yaml\n```\n\n**[Example playbooks](./playbooks)**\n\n## Playground\n\n`iauto` provides a web-based application for running playbooks, LLM Chat, ReAct reasoning, and Multi-Agent tasks.\n\nLaunch playground:\n\n```bash\nia playground\n```\n\n**Screenshot:**\n\n\n\n## Contribution\n\nWe are extremely open to contributions, whether it be in the form of a new feature, improved infrastructure, or better documentation.\n\n### Development setup\n\n- Code Style: [PEP-8](https://peps.python.org/pep-0008/)\n- Docstring Style: [Google Style](https://sphinxcontrib-napoleon.readthedocs.io/en/latest/example_google.html)\n\n```bash\n# Create python venv\npython -m venv .venv\nsource .venv/bin/activate\n\n# Install dependencies\npip install -r requirements.txt\npip install -r requirements-dev.txt\n\n# Apply autopep8, isort and flake8 as pre commit hooks\npre-commit install\n```\n\n### Build\n\n```bash\n./build.sh\n```\n\n## License\n\n[MIT](./LICENSE)\n\n<img src=\"./docs/assets/img/icon.svg\" title=\"iauto\" height=\"16\"> icon license: https://openmoji.org/library/emoji-1F9BE\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "iauto is a low-code engine for building and deploying AI agents",
"version": "0.1.10",
"project_urls": {
"Homepage": "https://github.com/shellc/iauto"
},
"split_keywords": [
"ai",
" automation",
" llm",
" rpa"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "85044e462459785be0c73cebb41c124628207c8efb5ce75f105bf65b6a825a75",
"md5": "791e53cc662ab6834ff28c9841cf1afc",
"sha256": "5bfd921c2ddf6172f583eabd0f9652e8a7ab4f9d082d66bbe5a6c2da5ac7a242"
},
"downloads": -1,
"filename": "iauto-0.1.10-py3-none-any.whl",
"has_sig": false,
"md5_digest": "791e53cc662ab6834ff28c9841cf1afc",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8",
"size": 80567,
"upload_time": "2024-03-31T02:06:23",
"upload_time_iso_8601": "2024-03-31T02:06:23.492953Z",
"url": "https://files.pythonhosted.org/packages/85/04/4e462459785be0c73cebb41c124628207c8efb5ce75f105bf65b6a825a75/iauto-0.1.10-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-03-31 02:06:23",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "shellc",
"github_project": "iauto",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"requirements": [
{
"name": "pydantic",
"specs": []
},
{
"name": "PyYAML",
"specs": []
},
{
"name": "python-dotenv",
"specs": []
},
{
"name": "prompt_toolkit",
"specs": []
},
{
"name": "openai",
"specs": []
},
{
"name": "pyautogen",
"specs": []
},
{
"name": "llama-cpp-python",
"specs": []
},
{
"name": "playwright",
"specs": []
},
{
"name": "Appium-Python-Client",
"specs": []
},
{
"name": "SQLAlchemy",
"specs": []
},
{
"name": "pandas",
"specs": []
},
{
"name": "streamlit",
"specs": []
},
{
"name": "watchdog",
"specs": []
}
],
"lcname": "iauto"
}
JSON
