requirements-eval.txt

# =============================================================================
# requirements-eval.txt — caption-quality metrics. Used by `scripts/evaluate.py`
# and by the `model-eval.yml` GitHub Action; NOT bundled into the serving image.
# -----------------------------------------------------------------------------
# pycocoevalcap drags Java for METEOR; we keep it in a separate file so the
# slim production image stays Java-free.
# =============================================================================

-r requirements.txt

# ---- Metrics -----------------------------------------------------------------
sacrebleu==2.4.2                 # BLEU-1..4, corpus + sentence level
nltk==3.8.1                      # BLEU + tokenisation utilities
rouge-score==0.1.2               # ROUGE-L for caption quality
pycocoevalcap==1.2               # CIDEr + METEOR (the COCO standard)

# ---- Plotting / reports ------------------------------------------------------
matplotlib==3.9.0