# --- Core and data packages --- numpy==2.2.6 pandas==2.3.3 polars==1.35.2 bleach==6.3.0 pyarrow==21.0.0 openpyxl==3.1.5 boto3==1.42.40 python-dotenv==1.0.1 defusedxml==0.7.1 Faker==37.8.0 python-levenshtein==0.27.1 rapidfuzz==3.14.1 markdown>=3.7 tabulate>=0.9.0 # --- Machine learning / NLP --- scikit-learn<=1.8.0 spacy==3.8.11 spaczz==0.6.1 en_core_web_lg @ https://github.com/explosion/spacy-models/releases/download/en_core_web_lg-3.8.0/en_core_web_lg-3.8.0.tar.gz # --- PDF / OCR / Redaction tools --- pdfminer.six==20260107 pdf2image==1.17.0 pymupdf==1.26.7 pikepdf==10.3.0 opencv-python==4.13.0.90 presidio_analyzer==2.2.360 presidio_anonymizer==2.2.360 presidio-image-redactor==0.0.57 # --- Gradio and apps --- gradio==5.49.1 https://github.com/seanpedrick-case/gradio_image_annotator/releases/download/v0.3.3/gradio_image_annotation-0.3.3-py3-none-any.whl # Custom annotator version with rotation, zoom, labels, and box IDs spaces==0.47.0 # --- AWS Lambda runtime --- awslambdaric==3.1.1 # --- Document generation --- python-docx==1.2.0 # --- Testing --- pytest>=7.0.0 pytest-cov>=4.0.0 # --- LLM libraries --- google-genai>=1.52.0 openai>=2.8.1