Documentation API

# English (required — at least one model)
python -m spacy download en_core_web_sm

# For better accuracy (larger model)
python -m spacy download en_core_web_lg

python -m spacy download fr_core_news_sm   # French
python -m spacy download de_core_news_sm   # German
python -m spacy download es_core_news_sm   # Spanish
python -m spacy download it_core_news_sm   # Italian
python -m spacy download nl_core_news_sm   # Dutch
python -m spacy download pt_core_news_sm   # Portuguese

promptshield serve
# Starting PromptShield API server on 127.0.0.1:8000
# API docs available at http://127.0.0.1:8000/docs

PROMPTSHIELD_API_KEY=ps_live_your_key_here

# 1. Upload
DOC_ID=$(curl -s -X POST http://localhost:8000/api/documents/upload \
  -F "file=@contract.pdf" | python -c "import sys,json; print(json.load(sys.stdin)['id'])")

echo "Document ID: $DOC_ID"

# 2. Detect PII
curl -X POST http://localhost:8000/api/documents/$DOC_ID/detect
# → {"status": "completed", "regions_count": 42}

# 3. Review detected regions
curl http://localhost:8000/api/documents/$DOC_ID/regions | python -m json.tool
# → [{"type": "PERSON", "text": "John Smith", "score": 0.98}, ...]

# 4. Anonymize
curl -X POST http://localhost:8000/api/documents/$DOC_ID/anonymize
# → {"status": "completed", "tokens_created": 42}

# 5. Download the anonymized document
curl -o contract-safe.pdf \
  http://localhost:8000/api/documents/$DOC_ID/download/pdf

echo "Done! Anonymized file saved to contract-safe.pdf"

import asyncio
from pathlib import Path
from promptshield import ingest_document, detect_pii_on_page, anonymize_document

async def process(input_path: str, output_path: str):
    # Step 1 — Ingest document
    doc = await ingest_document(input_path, Path(input_path).name)
    print(f"Loaded: {doc.filename} ({len(doc.pages)} pages)")

    # Step 2 — Detect PII
    total_entities = 0
    for page in doc.pages:
        regions = detect_pii_on_page(page)
        total_entities += len(regions)
        print(f"  Page {page.number}: {len(regions)} entities found")

    print(f"Total PII entities: {total_entities}")

    # Step 3 — Anonymize
    result = await anonymize_document(doc)
    print(f"Anonymized: {result.tokens_created} tokens created")

    # Save the result
    with open(output_path, "wb") as f:
        f.write(result.content)
    print(f"Saved to {output_path}")

asyncio.run(process("contract.pdf", "contract-safe.pdf"))

import asyncio
from pathlib import Path
from promptshield import ingest_document, detect_pii_on_page, anonymize_document

async def batch_process(input_dir: str, output_dir: str):
    input_path = Path(input_dir)
    output_path = Path(output_dir)
    output_path.mkdir(parents=True, exist_ok=True)

    files = list(input_path.glob("*.pdf"))
    print(f"Processing {len(files)} files...")

    for i, file in enumerate(files, 1):
        print(f"[{i}/{len(files)}] {file.name}")
        doc = await ingest_document(str(file), file.name)

        for page in doc.pages:
            detect_pii_on_page(page)

        result = await anonymize_document(doc)

        out_file = output_path / f"anon_{file.name}"
        with open(out_file, "wb") as f:
            f.write(result.content)

        print(f"  → {result.tokens_created} tokens, saved to {out_file.name}")

    print("Batch complete!")

asyncio.run(batch_process("./documents", "./anonymized"))