PyPI page
Home page
Author:
Stellars Henson <konrad.jelen+github@gmail.com>
Summary:
Project that uses theory of From Word Embeddings To Document Distances / Optimal Transport to give meaningful distance from one document to another, useful if building agentic projects that convert or extract information from one document to another using frontier models but without the ability to calculate KL divergence from logits
Latest version:
1.1.3
Required dependencies:
loguru
|
numpy
|
openvino
|
pot
|
python-dotenv
|
rich
|
torch
|
tqdm
|
transformers
|
typer
|
wtpsplit
Optional dependencies:
accelerate
|
boto3
|
botocore
|
build
|
datasets
|
docdistance
|
einops
|
flagembedding
|
ipykernel
|
ipython
|
matplotlib
|
nbdime
|
nncf
|
optimum-intel
|
pdfplumber
|
pip
|
polars
|
pylate
|
pytest
|
pytest-cov
|
ruff
|
sacremoses
|
seaborn
|
sentencepiece
|
torchao
|
twine
Downloads last day:
5
Downloads last week:
175
Downloads last month:
782