# pyAGI
**pyAGI** is a Python package that functions as an autonomous agent for your Python application. By interfacing with OpenAI models, it utilizes a sequence of prompts to instruct the AI in generating various outputs such as application descriptions, architecture outlines, user experience flows, and even code samples. All these are achieved using the **langchain** framework to construct chains of language models.
## Features
1. Supports several OpenAI models, including a range of GPT-3 and Davinci models.
2. Provides functionality for generating:
1. Application descriptions
1. Software architecture outlines
2. User experience flows
3. Code flow descriptions
4. Coding steps
5. Application code
## Setup
To use pyAGI, you need to have an [OpenAI account](https://www.openai.com/) and obtain your API key. Once you have your OpenAI API key, set it as an environment variable OPENAI_API_KEY in your system.
`export OPENAI_API_KEY='your-api-key-here'`
## Installation
To install pyAGI, use pip:
`pip install pyAGI`
The package is available at PyPI pyAGI (https://pypi.org/project/pyAGI/).
## Usage
After installing, you can use pyAGI to generate content for your application as follows:
```
from pyAGI.pyagi import PyAGI
Create a PyAGI instance with a selected OpenAI model
py_agi = PyAGI.create_llm_chain(selected_model="text-davinci-003")
# Run the PyAGI instance with the objective
py_agi({"objective": "Your Objective", "selected_model": "text-davinci-003"})
```
# Usage without installing the pip package
`python main.py "Objective of your app" "OpenAI Model"`
For example:
`python main.py "Build a weather app" "text-davinci-003"`
## Available Models
### Currently supported models:
- "text-davinci-002",
- "text-davinci-003",
- "gpt-3.5-turbo",
- "gpt-3.5-turbo-0301",
- "text-curie-001",
- "text-babbage-001",
- "text-ada-001"
### Upcoming models (https://openai.com/waitlist/gpt-4-api):
- "gpt-4",
- "gpt-4-0314",
- "gpt-4-32k",
- "gpt-4-32k-0314"
Please note that upcoming models will not be supported until released.
## Contributing
Contributions are welcome! Please open an issue if you encounter a bug, or a pull request if you have improvements to the existing code.
## License
This project is licensed under the MIT License.
Raw data
{
"_id": null,
"home_page": "https://github.com/sattyamjjain/pyAGI",
"name": "pyAGI",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.9",
"maintainer_email": "",
"keywords": "agi,pyagi,autonomous agent,code agi,python agi",
"author": "Sattyam Jain",
"author_email": "sattyamjain96@gmail.com",
"download_url": "https://files.pythonhosted.org/packages/2f/c3/c99974c9ef25a444539c5f16f45abb221ba2868e710ccf5f5af6c208a326/pyAGI-1.0.4.tar.gz",
"platform": null,
"description": "# pyAGI\n**pyAGI** is a Python package that functions as an autonomous agent for your Python application. By interfacing with OpenAI models, it utilizes a sequence of prompts to instruct the AI in generating various outputs such as application descriptions, architecture outlines, user experience flows, and even code samples. All these are achieved using the **langchain** framework to construct chains of language models.\n\n## Features\n1. Supports several OpenAI models, including a range of GPT-3 and Davinci models.\n2. Provides functionality for generating:\n 1. Application descriptions\n 1. Software architecture outlines\n 2. User experience flows\n 3. Code flow descriptions\n 4. Coding steps\n 5. Application code\n\n## Setup\nTo use pyAGI, you need to have an [OpenAI account](https://www.openai.com/) and obtain your API key. Once you have your OpenAI API key, set it as an environment variable OPENAI_API_KEY in your system.\n\n`export OPENAI_API_KEY='your-api-key-here'`\n\n## Installation\n\nTo install pyAGI, use pip:\n\n`pip install pyAGI`\n\nThe package is available at PyPI pyAGI (https://pypi.org/project/pyAGI/).\n\n## Usage\nAfter installing, you can use pyAGI to generate content for your application as follows:\n\n```\nfrom pyAGI.pyagi import PyAGI\n\nCreate a PyAGI instance with a selected OpenAI model\npy_agi = PyAGI.create_llm_chain(selected_model=\"text-davinci-003\")\n\n# Run the PyAGI instance with the objective\npy_agi({\"objective\": \"Your Objective\", \"selected_model\": \"text-davinci-003\"})\n```\n\n# Usage without installing the pip package\n\n`python main.py \"Objective of your app\" \"OpenAI Model\"`\n\nFor example:\n\n`python main.py \"Build a weather app\" \"text-davinci-003\"`\n\n## Available Models\n\n### Currently supported models:\n\n- \"text-davinci-002\",\n- \"text-davinci-003\",\n- \"gpt-3.5-turbo\",\n- \"gpt-3.5-turbo-0301\",\n- \"text-curie-001\",\n- \"text-babbage-001\",\n- \"text-ada-001\"\n\n### Upcoming models (https://openai.com/waitlist/gpt-4-api):\n\n- \"gpt-4\",\n- \"gpt-4-0314\",\n- \"gpt-4-32k\",\n- \"gpt-4-32k-0314\"\n\nPlease note that upcoming models will not be supported until released.\n\n## Contributing\nContributions are welcome! Please open an issue if you encounter a bug, or a pull request if you have improvements to the existing code.\n\n## License\nThis project is licensed under the MIT License.\n",
"bugtrack_url": null,
"license": "",
"summary": "Autonomous agent for building the python app using OpenAI with AGI concept",
"version": "1.0.4",
"project_urls": {
"Bug Reports": "https://github.com/sattyamjjain/pyAGI",
"Homepage": "https://github.com/sattyamjjain/pyAGI",
"Source": "https://github.com/sattyamjjain/pyAGI"
},
"split_keywords": [
"agi",
"pyagi",
"autonomous agent",
"code agi",
"python agi"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "f08cae9b08e17855a73bf0eb7f8d8401863d6783af42077f5e139bd93feddd25",
"md5": "69e7ee58084ae3598238b261c58a8e7a",
"sha256": "8231ae19a3b72340cf447838e7826efe3bcba8a6e85f62f27f3dedad717619fe"
},
"downloads": -1,
"filename": "pyAGI-1.0.4-py3-none-any.whl",
"has_sig": false,
"md5_digest": "69e7ee58084ae3598238b261c58a8e7a",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.9",
"size": 6989,
"upload_time": "2023-05-28T14:21:22",
"upload_time_iso_8601": "2023-05-28T14:21:22.407072Z",
"url": "https://files.pythonhosted.org/packages/f0/8c/ae9b08e17855a73bf0eb7f8d8401863d6783af42077f5e139bd93feddd25/pyAGI-1.0.4-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "2fc3c99974c9ef25a444539c5f16f45abb221ba2868e710ccf5f5af6c208a326",
"md5": "7f8398650bf20e8faaab56ba4d9d1fbf",
"sha256": "2743754440f9abe8c44d0f4247d50e87ccd0a0d287e086e1f9ab99260a56b859"
},
"downloads": -1,
"filename": "pyAGI-1.0.4.tar.gz",
"has_sig": false,
"md5_digest": "7f8398650bf20e8faaab56ba4d9d1fbf",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.9",
"size": 5933,
"upload_time": "2023-05-28T14:21:23",
"upload_time_iso_8601": "2023-05-28T14:21:23.867508Z",
"url": "https://files.pythonhosted.org/packages/2f/c3/c99974c9ef25a444539c5f16f45abb221ba2868e710ccf5f5af6c208a326/pyAGI-1.0.4.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-05-28 14:21:23",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "sattyamjjain",
"github_project": "pyAGI",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"requirements": [],
"lcname": "pyagi"
}
JSON
