PyPI page
Author:
Dimitrios Avellas
Summary:
Pipeline for extracting structured data (tables, sections, key/value fields) from PDF documents using docling, embeddings, and LLMs.
Latest version:
0.2.0
Required dependencies:
docling
|
docling-core
|
docling-ibm-models
|
docling-parse
|
einops
|
instructor
|
jinja2
|
joblib
|
numpy
|
openai
|
pandas
|
pydantic
|
pymupdf
|
python-dotenv
|
rapidfuzz
|
scikit-learn
|
sentence-transformers
|
yake
Optional dependencies:
pytest
Downloads last day:
0
Downloads last week:
10
Downloads last month:
22
7-day smoothing