# llm-kg
<a href="https://pypi.org/project/llmkg/">
<img alt="PyPi" src="https://img.shields.io/pypi/v/llmkg">
</a>
A knowledge graph generator using LLMs.
## Dependencies :globe_with_meridians:
Python 3.11.6:
- [timefhuman](https://github.com/alvinwan/timefhuman)
- [nltk](https://www.nltk.org/)
- [instructor](https://python.useinstructor.com/)
- [groq](https://github.com/groq/groq-python)
- [pydantic](https://docs.pydantic.dev/latest/)
- [textblob](https://textblob.readthedocs.io/en/dev/)
## Raison D'être :thought_balloon:
`llm-kg` is a package that uses LLMs to extract knowledge graphs from freeform text.
## Architecture :triangular_ruler:
`llm-kg` calls an LLM using Groq to turn text into a series of triples.
## Installation :inbox_tray:
This is a python package hosted on pypi, so to install simply run the following command:
`pip install llmkgext`
or install using this local repository:
`python setup.py install --old-and-unmanageable`
## Usage example :eyes:
The use of `llmkgext` is entirely through code due to it being a library. It has exactly the same semantics as a requests session:
```python
from llmkgext import extract
triples = extract("Rodrigo Martins Vaz, known as Rodrigo (born 24 May 1971), is a retired Brazilian footballer.")
print(triples)
```
## License :memo:
The project is available under the [MIT License](LICENSE).
Raw data
{
"_id": null,
"home_page": "https://github.com/8W9aG/llm-kg",
"name": "llmkgext",
"maintainer": null,
"docs_url": null,
"requires_python": null,
"maintainer_email": null,
"keywords": "kg, knowledge, graph, llm",
"author": "Will Sackfield",
"author_email": "will.sackfield@gmail.com",
"download_url": "https://files.pythonhosted.org/packages/32/76/aaaeffa1557a28255dd96c8a7ef989ceec3dfe59d22aa2fcdffe3309277f/llmkgext-0.0.1.tar.gz",
"platform": null,
"description": "# llm-kg\n\n<a href=\"https://pypi.org/project/llmkg/\">\n <img alt=\"PyPi\" src=\"https://img.shields.io/pypi/v/llmkg\">\n</a>\n\nA knowledge graph generator using LLMs.\n\n## Dependencies :globe_with_meridians:\n\nPython 3.11.6:\n\n- [timefhuman](https://github.com/alvinwan/timefhuman)\n- [nltk](https://www.nltk.org/)\n- [instructor](https://python.useinstructor.com/)\n- [groq](https://github.com/groq/groq-python)\n- [pydantic](https://docs.pydantic.dev/latest/)\n- [textblob](https://textblob.readthedocs.io/en/dev/)\n\n## Raison D'\u00eatre :thought_balloon:\n\n`llm-kg` is a package that uses LLMs to extract knowledge graphs from freeform text.\n\n## Architecture :triangular_ruler:\n\n`llm-kg` calls an LLM using Groq to turn text into a series of triples.\n\n## Installation :inbox_tray:\n\nThis is a python package hosted on pypi, so to install simply run the following command:\n\n`pip install llmkgext`\n\nor install using this local repository:\n\n`python setup.py install --old-and-unmanageable`\n\n## Usage example :eyes:\n\nThe use of `llmkgext` is entirely through code due to it being a library. It has exactly the same semantics as a requests session:\n\n```python\nfrom llmkgext import extract\n\n\ntriples = extract(\"Rodrigo Martins Vaz, known as Rodrigo (born 24 May 1971), is a retired Brazilian footballer.\")\nprint(triples)\n```\n\n## License :memo:\n\nThe project is available under the [MIT License](LICENSE).\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "A knowledge graph generator using LLMs.",
"version": "0.0.1",
"project_urls": {
"Homepage": "https://github.com/8W9aG/llm-kg"
},
"split_keywords": [
"kg",
" knowledge",
" graph",
" llm"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "3276aaaeffa1557a28255dd96c8a7ef989ceec3dfe59d22aa2fcdffe3309277f",
"md5": "660a42ab500b21ecdd40ed26eb457412",
"sha256": "bbf5cb0a0dae71932f0f9a56e926e8b00fc5c878347d3c9f63434f482293901f"
},
"downloads": -1,
"filename": "llmkgext-0.0.1.tar.gz",
"has_sig": false,
"md5_digest": "660a42ab500b21ecdd40ed26eb457412",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 4620,
"upload_time": "2025-07-21T23:24:02",
"upload_time_iso_8601": "2025-07-21T23:24:02.040756Z",
"url": "https://files.pythonhosted.org/packages/32/76/aaaeffa1557a28255dd96c8a7ef989ceec3dfe59d22aa2fcdffe3309277f/llmkgext-0.0.1.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-07-21 23:24:02",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "8W9aG",
"github_project": "llm-kg",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"requirements": [
{
"name": "timefhuman",
"specs": [
[
">=",
"0.1.4"
]
]
},
{
"name": "nltk",
"specs": [
[
">=",
"3.9.1"
]
]
},
{
"name": "instructor",
"specs": [
[
">=",
"1.10.0"
]
]
},
{
"name": "groq",
"specs": [
[
">=",
"0.30.0"
]
]
},
{
"name": "pydantic",
"specs": [
[
">=",
"2.11.7"
]
]
},
{
"name": "textblob",
"specs": [
[
">=",
"0.19.0"
]
]
}
],
"lcname": "llmkgext"
}
JSON
