<div align="center">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="docs/images/dark.png">
<source media="(prefers-color-scheme: light)" srcset="docs/images/light.png">
<img alt="Semantix: Infusing Meaning into Code with Large Language Models" width="500px" src="https://i.ibb.co/SR2hqgh/1.png">
</picture>
[](https://pypi.org/project/semantix/) [](https://colab.research.google.com/github/chandralegend/semantix/blob/main/try.ipynb) 
Semantix provides a simple but powerful way to infuse meaning into functions, variables and classes to leverage the power of Large Language models to generate structured typed outputs `without the need of JSON Schema or any other abstractions.`
</div>
## Key Features:
- **Semantic Type**: Add meaning to your variables. No need of additional abstractions like `InputField`, `OutputField` etc.
- **AutoPrompting**: Semantix Generate prompts using the `Meaning Typed Prompting` Technique.
- **Supercharged Functions**: Automatically augment functions enhance-powered capabilities. No Function body is needed.
- **Minimal Overhead**: Seamlessly integrate into existing Python codebases with minimal overhead.
## Minimal Example
```python
from enum import Enum
from dataclasses import dataclass
from semantix import Semantic, enhance
from semantix.llms import OpenAI
from semantix.types import Image
llm = OpenAI()
class Personality(Enum):
"""Personality of the Person"""
INTROVERT = "Introvert"
EXTROVERT = "Extrovert"
@dataclass
class Person:
full_name: str
yod: Semantic[int, "Year of Death"]
personality: Semantic[Personality, "Personality of the Person"]
@enhance("Get Person Informations use common knowledge", llm)
def get_person(name: Semantic[str, "Name of the Person"]) -> Person:
...
person_obj = get_person(name="Albert Einstein")
print(f"{person_obj.full_name} is an {person_obj.personality.value} who died in {person_obj.yod}")
# Albert Einstein is an Introvert who died in 1955
```
## Supports Vision
```python
from semantix.types import Image
@enhance("Get Person Informations use common knowledge", llm)
def get_person(img: Semantic[Image, "Image of the Person"]) -> Person:
...
person_obj = get_person(img=Image("mandela.jpg"))
print(f"{person_obj.full_name} is an {person_obj.personality.value} who died in {person_obj.yod}")
# Nelson Mandela is an Extrovert who died in 2013
```
## Installation
All you need is:
```bash
pip install semantix
```
To install the very latest from `main`:
```bash
pip install git+https://github.com/chandralegend/semantix.git
````
Or open our intro notebook in Google Colab: [<img align="center" src="https://colab.research.google.com/assets/colab-badge.svg" />](https://colab.research.google.com/github/chandralegend/semantix/blob/main/try.ipynb)
By default, Semantix doesn't install any llm packages. You can install them separately:
```bash
pip install semantix[openai]
pip install semantix[anthropic]
pip install semantix[openai, anthropic] # Install both
```
If you want to use MultiModal capabilities, you can install the following:
```bash
pip install semantix[image]
pip install semantix[video]
```
## Citation
If you find Semantix helpful, give it a ⭐️ on [GitHub](https://github/chandralegend/semantix)!
and If you have used Semantix in your project, add the badge to your README.md file.
```markdown
[](https://github/chandralegend/semantix)
```
If you used Semantix in your research, please cite it as follows:
```bibtex
@misc{semantix,
author = {Chandra Irugalbandara},
title = {Semantix: Infusing Meaning into Code with Large Language Models},
year = {2024},
publisher = {GitHub},
journal = {GitHub Repository},
howpublished = {\url{https://github/chandralegend/semantix}}
}
```
## Contributing
Please read [CONTRIBUTING.md](docs/contributing.md) for a quick guide on how to contribute to Semantix.
Raw data
{
"_id": null,
"home_page": "https://github.com/chandralegend/semantix",
"name": "semantix",
"maintainer": "Chandra Irugalbandara",
"docs_url": null,
"requires_python": "<4.0,>=3.8",
"maintainer_email": "irugalbandara@ascii.ai",
"keywords": "no-prompt, llm, meaning-typed, autoprompt",
"author": "Chandra Irugalbandara",
"author_email": "irugalbandara@ascii.ai",
"download_url": "https://files.pythonhosted.org/packages/f8/a7/06cea91c571627417c8a70e090fe249554e5d873f13133177fca5d395d41/semantix-0.1.7.tar.gz",
"platform": null,
"description": "<div align=\"center\">\n <picture>\n <source media=\"(prefers-color-scheme: dark)\" srcset=\"docs/images/dark.png\">\n <source media=\"(prefers-color-scheme: light)\" srcset=\"docs/images/light.png\">\n <img alt=\"Semantix: Infusing Meaning into Code with Large Language Models\" width=\"500px\" src=\"https://i.ibb.co/SR2hqgh/1.png\">\n </picture>\n\n [](https://pypi.org/project/semantix/) [](https://colab.research.google.com/github/chandralegend/semantix/blob/main/try.ipynb) \n\nSemantix provides a simple but powerful way to infuse meaning into functions, variables and classes to leverage the power of Large Language models to generate structured typed outputs `without the need of JSON Schema or any other abstractions.`\n\n</div>\n\n## Key Features:\n\n- **Semantic Type**: Add meaning to your variables. No need of additional abstractions like `InputField`, `OutputField` etc.\n- **AutoPrompting**: Semantix Generate prompts using the `Meaning Typed Prompting` Technique.\n- **Supercharged Functions**: Automatically augment functions enhance-powered capabilities. No Function body is needed.\n- **Minimal Overhead**: Seamlessly integrate into existing Python codebases with minimal overhead.\n\n## Minimal Example\n\n```python\nfrom enum import Enum\nfrom dataclasses import dataclass\n\nfrom semantix import Semantic, enhance\nfrom semantix.llms import OpenAI\nfrom semantix.types import Image\n\nllm = OpenAI()\n\nclass Personality(Enum):\n \"\"\"Personality of the Person\"\"\"\n\n INTROVERT = \"Introvert\"\n EXTROVERT = \"Extrovert\"\n\n@dataclass\nclass Person:\n full_name: str\n yod: Semantic[int, \"Year of Death\"]\n personality: Semantic[Personality, \"Personality of the Person\"]\n\n@enhance(\"Get Person Informations use common knowledge\", llm)\ndef get_person(name: Semantic[str, \"Name of the Person\"]) -> Person:\n ...\n\nperson_obj = get_person(name=\"Albert Einstein\")\nprint(f\"{person_obj.full_name} is an {person_obj.personality.value} who died in {person_obj.yod}\")\n# Albert Einstein is an Introvert who died in 1955\n```\n\n## Supports Vision\n\n```python\nfrom semantix.types import Image\n\n@enhance(\"Get Person Informations use common knowledge\", llm)\ndef get_person(img: Semantic[Image, \"Image of the Person\"]) -> Person:\n ...\n\nperson_obj = get_person(img=Image(\"mandela.jpg\"))\nprint(f\"{person_obj.full_name} is an {person_obj.personality.value} who died in {person_obj.yod}\")\n# Nelson Mandela is an Extrovert who died in 2013\n```\n\n## Installation\nAll you need is:\n\n```bash\npip install semantix\n```\n\nTo install the very latest from `main`:\n\n```bash\npip install git+https://github.com/chandralegend/semantix.git\n````\n\nOr open our intro notebook in Google Colab: [<img align=\"center\" src=\"https://colab.research.google.com/assets/colab-badge.svg\" />](https://colab.research.google.com/github/chandralegend/semantix/blob/main/try.ipynb)\n\nBy default, Semantix doesn't install any llm packages. You can install them separately:\n\n```bash\npip install semantix[openai]\npip install semantix[anthropic]\npip install semantix[openai, anthropic] # Install both\n```\n\nIf you want to use MultiModal capabilities, you can install the following:\n\n```bash\npip install semantix[image]\npip install semantix[video]\n```\n\n## Citation\n\nIf you find Semantix helpful, give it a \u2b50\ufe0f on [GitHub](https://github/chandralegend/semantix)!\nand If you have used Semantix in your project, add the badge to your README.md file.\n\n\n\n```markdown\n[](https://github/chandralegend/semantix)\n```\n\nIf you used Semantix in your research, please cite it as follows:\n\n```bibtex\n@misc{semantix,\n author = {Chandra Irugalbandara},\n title = {Semantix: Infusing Meaning into Code with Large Language Models},\n year = {2024},\n publisher = {GitHub},\n journal = {GitHub Repository},\n howpublished = {\\url{https://github/chandralegend/semantix}}\n}\n```\n\n## Contributing\nPlease read [CONTRIBUTING.md](docs/contributing.md) for a quick guide on how to contribute to Semantix.\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "Give Superpowers to your python function. GenAI Application development made easy.",
"version": "0.1.7",
"project_urls": {
"Documentation": "https://chandralegend.github.io/semantix/",
"Homepage": "https://github.com/chandralegend/semantix",
"Repository": "https://github.com/chandralegend/semantix"
},
"split_keywords": [
"no-prompt",
" llm",
" meaning-typed",
" autoprompt"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "49b453777d5ab744c0a87fadb1cff77334b3e177d29aa43f942d9eb053321a26",
"md5": "0a749f982ccc52a2ad1d9fbf657bd0a4",
"sha256": "3d33e5e91d68e7d21f3a0b99be236c06c1db86a358bf36f743f11c554ff93b73"
},
"downloads": -1,
"filename": "semantix-0.1.7-py3-none-any.whl",
"has_sig": false,
"md5_digest": "0a749f982ccc52a2ad1d9fbf657bd0a4",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<4.0,>=3.8",
"size": 28970,
"upload_time": "2024-10-16T11:24:14",
"upload_time_iso_8601": "2024-10-16T11:24:14.551825Z",
"url": "https://files.pythonhosted.org/packages/49/b4/53777d5ab744c0a87fadb1cff77334b3e177d29aa43f942d9eb053321a26/semantix-0.1.7-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "f8a706cea91c571627417c8a70e090fe249554e5d873f13133177fca5d395d41",
"md5": "f98e0c91eda50fabc56c161d1317d8ba",
"sha256": "493cf299518578d36a57c95a3f80dbab3b127f34b43ee0fe1dd9e3c7dde403cc"
},
"downloads": -1,
"filename": "semantix-0.1.7.tar.gz",
"has_sig": false,
"md5_digest": "f98e0c91eda50fabc56c161d1317d8ba",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<4.0,>=3.8",
"size": 21284,
"upload_time": "2024-10-16T11:24:16",
"upload_time_iso_8601": "2024-10-16T11:24:16.279471Z",
"url": "https://files.pythonhosted.org/packages/f8/a7/06cea91c571627417c8a70e090fe249554e5d873f13133177fca5d395d41/semantix-0.1.7.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-10-16 11:24:16",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "chandralegend",
"github_project": "semantix",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "semantix"
}
JSON
