# Optional: only needed when classifier.mode: local_encoder is configured.
# Not part of requirements.txt deliberately -- this project's dependency
# tree is pinned and bumped deliberately, and torch is large enough (and
# CPU/CUDA-wheel-specific enough) to warrant staying out of every install
# rather than every deployment paying for it whether or not the mode is used.
#
# CPU install (the classifier.encoder.device: cpu default):
#   pip install -r requirements-encoder.txt
#
# CUDA install: replace the torch line with the CUDA wheel index per
# https://pytorch.org/get-started/locally/ -- the exact index URL is
# CUDA-version-specific and changes upstream, so it is not pinned here.
transformers==4.57.1
torch==2.9.1

# TRAINING-time only, for scripts/train_encoder_head.py: fitting and
# Platt-calibrating the logistic-regression head on frozen embeddings. The
# serving side (local_encoder._TrainableHead) reads the committed
# coefficients JSON in pure Python, so deployments that never retrain the
# head need neither scikit-learn nor its scipy/joblib pulls.
scikit-learn==1.9.1