Metadata-Version: 2.4
Name: gemascore
Version: 0.1.0
Summary: GEMA-Score: structured evaluation of candidate vs reference radiology reports.
Author: GEMA-Score Contributors
License: MIT
Requires-Python: >=3.9
Description-Content-Type: text/markdown
License-File: LICENSE.txt
Requires-Dist: torch>=2.0
Requires-Dist: transformers>=4.40
Requires-Dist: huggingface_hub>=0.20
Requires-Dist: safetensors>=0.4
Provides-Extra: dev
Requires-Dist: pytest>=7.0; extra == "dev"
Requires-Dist: ruff>=0.4; extra == "dev"
Requires-Dist: build>=1.0; extra == "dev"
Requires-Dist: twine>=5.0; extra == "dev"
Dynamic: license-file

# gemascore

Evaluate a candidate radiology report against a reference report using a Hugging Face hosted (or locally cached) GEMA-Score distilled model.

## Install
```bash
pip install gemascore
```

## Python usage
```bash
from gemascore import evaluate_report

candidate = "no pneumothorax. mediastinal contours normal. patchy right nodular mid lung zone opacity."
reference = "no pneumothorax. mediastinum upper limits of normal in size. patchy bilateral ground-glass opacities, consolidation, or edema."

text = evaluate_report(
    candidate_report=candidate,
    reference_report=reference,
    cache_dir="/data/hf_cache",  # or model_path="/data/models/GEMA-Score-distilled-CT-Qwen"
)
print(text)
```
## CLI usage
```bash
gemascore \
  --candidate "no pneumothorax..." \
  --reference "no pneumothorax..." \
  --cache-dir /data/hf_cache
```
## Notes
First run may download several GB of model weights.
If you already have a local checkpoint folder containing model.safetensors, pass --model-path instead.
