Metadata-Version: 2.4
Name: omnidoc-sdk
Version: 0.2.5
Summary: Enterprise-grade SDK for extracting text, tables, structure, and entities from documents
Author-email: Ganesh Kinkar Giri <k.ganeshgiri@example.com>
License: Apache-2.0
Keywords: document-processing,pdf,ocr,table-extraction,idp,rag,agentic-ai
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Information Technology
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Topic :: Text Processing
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.9
Description-Content-Type: text/markdown
Requires-Dist: pypdf>=4.0.0
Requires-Dist: pdfplumber>=0.11.0
Requires-Dist: pdf2image>=1.17.0
Requires-Dist: Pillow>=10.0.0
Requires-Dist: pytesseract>=0.3.10
Requires-Dist: opencv-python>=4.9.0
Requires-Dist: numpy>=1.24
Requires-Dist: chardet>=5.2.0
Requires-Dist: regex>=2023.12.25
Provides-Extra: cloud-ocr
Requires-Dist: boto3>=1.34.0; extra == "cloud-ocr"
Requires-Dist: azure-ai-formrecognizer>=3.3.0; extra == "cloud-ocr"
Provides-Extra: layout
Requires-Dist: layoutparser>=0.3.4; extra == "layout"
Provides-Extra: vlm
Requires-Dist: torch>=2.0; extra == "vlm"
Requires-Dist: transformers>=4.41.0; extra == "vlm"
Provides-Extra: privacy
Requires-Dist: presidio-analyzer>=2.2.0; extra == "privacy"
Requires-Dist: presidio-anonymizer>=2.2.0; extra == "privacy"
Provides-Extra: dev
Requires-Dist: pytest>=8.0.0; extra == "dev"
Requires-Dist: pytest-cov>=4.1.0; extra == "dev"
Requires-Dist: black>=24.0.0; extra == "dev"
Requires-Dist: ruff>=0.4.0; extra == "dev"
Requires-Dist: mypy>=1.8.0; extra == "dev"
