Using textgraphs + LLM + graph ML for entity extraction, linking, and ranking
Project description
title: TextGraphs emoji: ✴ colorFrom: green colorTo: gray sdk: streamlit sdk_version: 1.28.2 app_file: app.py pinned: false license: mit
project info:
see https://huggingface.co/spaces/DerwenAI/textgraphs
requirements:
- Python 3.9+
deploy library from PyPi:
python3 -m pip install -u textgraphs
python3 -m spacy download en_core_web_sm
python3 -m pip install git+https://github.com/thunlp/OpenNRE
NB: both the spaCy and PyPi teams cause packagine errors because they have "opinionated" views against following the Python packaging standards.
install locally:
python3 -m venv venv
source venv/bin/activate
python3 -m pip install -U pip wheel setuptools
python3 -m pip install -r requirements.txt
to run the Streamlit or JupyterLab demos, or prior to working locally on the development and testing of this repo:
python3 -m pip install -r requirements-dev.txt
pre-commit install --hook-type pre-commit
test locally:
python3 -m pytest
run locally:
python3 demo.py
./venv/bin/jupyter lab
streamlit run app.py
to publish:
python3 -m build
twine check dist/*
twine upload ./dist/* --verbose
administrivia
License and Copyright
Source code for TextGraphs plus its logo, documentation, and examples have an MIT license which is succinct and simplifies use in commercial applications.
All materials herein are Copyright © 2023 Derwen, Inc.
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
textgraphs-0.1.2.tar.gz
(185.1 kB
view hashes)
Built Distribution
textgraphs-0.1.2-py3-none-any.whl
(25.6 kB
view hashes)
Close
Hashes for textgraphs-0.1.2-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | eee75a1f1591207bd64d1146959e182e635c0473aa338cf6dc8706a46c9fbf60 |
|
MD5 | 9e7a03724b1bee8bc3abfa9cea16e4fc |
|
BLAKE2b-256 | 40ba46adb3c1ea8a8338cee98fd2da0a29c2b71393faa443fe5aa03a86ef235d |