example_redaction.py

from transformers import pipeline


MODEL_ID = "bharathjanumpally/phi-span-detector-deberta-v3"


def redact_text(text: str) -> tuple[list[dict], str]:
    ner = pipeline(
        "token-classification",
        model=MODEL_ID,
        aggregation_strategy="simple",
    )
    spans = ner(text)

    redacted = text
    for item in sorted(spans, key=lambda x: x["start"], reverse=True):
        label = item["entity_group"]
        redacted = redacted[: item["start"]] + f"[{label}]" + redacted[item["end"] :]

    return spans, redacted


if __name__ == "__main__":
    sample = (
        "Patient John Smith (MRN: 001-23-4567) visited "
        "Boston Medical Center on 12/19/2025."
    )
    spans, redacted = redact_text(sample)
    print("Spans:")
    for span in spans:
        print(span)
    print()
    print("Redacted:")
    print(redacted)