Metadata-Version: 2.3
Name: extractor_api_lib
Version: 3.2.0
Summary: Extracts the content of documents, websites, etc and maps it to a common format.
Author: STACKIT Data and AI Consulting
Author-email: data-ai-consulting@stackit.cloud
Requires-Python: >=3.13,<4.0
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.13
Requires-Dist: atlassian-python-api (>=4.0.3,<5.0.0)
Requires-Dist: boto3 (>=1.38.10,<2.0.0)
Requires-Dist: botocore (>=1.38.10,<2.0.0)
Requires-Dist: camelot-py[cv] (>=1.0.0,<2.0.0)
Requires-Dist: datasets (>=3.5.1,<4.0.0)
Requires-Dist: debugpy (>=1.8.14,<2.0.0)
Requires-Dist: dependency-injector (>=4.46.0,<5.0.0)
Requires-Dist: docx2txt (>=0.9,<0.10)
Requires-Dist: fake-useragent (>=2.2.0,<3.0.0)
Requires-Dist: fastapi (>=0.118.0,<0.119.0)
Requires-Dist: fasttext (>=0.9.3,<0.10.0)
Requires-Dist: html5lib (>=1.1,<2.0)
Requires-Dist: langchain-community (>=0.3.23,<0.4.0)
Requires-Dist: langchain-core (==0.3.77)
Requires-Dist: lxml (>=5.4.0,<6.0.0)
Requires-Dist: markdownify (>=1.1.0,<2.0.0)
Requires-Dist: numpy (>=2.2.5,<3.0.0)
Requires-Dist: oauthlib (>=3.2.2,<4.0.0)
Requires-Dist: opencv-python (==4.12.0.88)
Requires-Dist: pandas (>=2.2.2,<3.0.0)
Requires-Dist: partial (>=1.0,<2.0)
Requires-Dist: pdf2image (==1.17.0)
Requires-Dist: pdfplumber (==0.11.7)
Requires-Dist: pydantic-settings (>=2.9.1,<3.0.0)
Requires-Dist: pypandoc-binary (>=1.15,<2.0)
Requires-Dist: pypdfium2 (==4.30.0)
Requires-Dist: pytesseract (>=0.3.10,<0.4.0)
Requires-Dist: python-multipart (>=0.0.20,<0.0.21)
Requires-Dist: pyyaml (>=6.0.2,<7.0.0)
Requires-Dist: requests-oauthlib (>=2.0.0,<3.0.0)
Requires-Dist: starlette (>=0.47.2,<0.49.0)
Requires-Dist: tabulate (>=0.9.0,<0.10.0)
Requires-Dist: unstructured[docx,pptx] (==0.18.15)
Requires-Dist: uvicorn (>=0.37.0,<0.38.0)
Requires-Dist: wheel (>=0.45.1,<0.46.0)
