llm-kg
A knowledge graph generator using LLMs.
Dependencies :globe_with_meridians:
Python 3.11.6:
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:
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.
Metadata
Release files for llmkgext 0.0.3
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| llmkgext-0.0.3.tar.gz | 4.7 kB | Without provenance | Details |
Release files / llmkgext-0.0.3.tar.gz
| Download URL | llmkgext-0.0.3.tar.gz |
|---|---|
| Size | 4.7 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
b75c85d51531f1b1826628d736d85303472ab8dd7e0357936c34626aa160b0fc
|
|
BLAKE2b-256 checksum How to use checksums |
c663fe05e353fc5752c83b6d76213b252d948380ebedfefe8339bb4b541e1f27
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.11.6
|
Security for llmkgext 0.0.3
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.