Dokumentacja API

# Set the install directory (add to your shell profile)
export PROMPTSHIELD_ASSETS_DIR="$HOME/.local/share/promptshield/assets"
# Windows: $env:PROMPTSHIELD_ASSETS_DIR = "$env:APPDATA\promptshield\assets"

# English pack — required (medium is recommended)
promptshield models install spacy-en-md

# For maximum accuracy (larger download)
promptshield models install spacy-en-lg

promptshield models install spacy-fr-md   # French
promptshield models install spacy-de-md   # German
promptshield models install spacy-es-md   # Spanish
promptshield models install spacy-it-md   # Italian
promptshield models install spacy-nl-md   # Dutch
promptshield models install spacy-pt-md   # Portuguese

promptshield serve
# Starting PromptShield API server on 127.0.0.1:8000
#   Health: http://127.0.0.1:8000/health  (no auth)
#   Schema: http://127.0.0.1:8000/openapi.json  (send: Authorization: Bearer <your-api-key>)
#   /docs and /redoc are served but require that same header, so a browser cannot open them directly.

PROMPTSHIELD_API_KEY=ps_live_your_key_here

# 1. Upload
AUTH="Authorization: Bearer ps_live_your_key_here"

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

echo "Document ID: $DOC_ID"

# 2. Detect PII (with optional inline overrides)
curl -X POST http://localhost:8000/api/documents/$DOC_ID/detect \
  -H "$AUTH" \
  -H "Content-Type: application/json" \
  -d '{"confidence_threshold": 0.7, "regex_enabled": true, "ner_enabled": true}'
# → {"doc_id": "...", "total_regions": 42, "regions": [...]}

# 3. Review detected regions
curl -H "$AUTH" http://localhost:8000/api/documents/$DOC_ID/regions | python -m json.tool
# → [{"id": "...", "pii_type": "PERSON", "text": "John Smith", "confidence": 0.98,
#     "action": "TOKENIZE", ...}, ...]

# 3b. Bulk-update region actions before anonymizing (region_ids from step 3)
curl -X PUT http://localhost:8000/api/documents/$DOC_ID/regions/batch-action \
  -H "$AUTH" \
  -H "Content-Type: application/json" \
  -d '{"region_ids": ["<id1>", "<id2>"], "action": "REMOVE"}'

# 4. Anonymize
curl -X POST http://localhost:8000/api/documents/$DOC_ID/anonymize \
  -H "$AUTH"
# → {"doc_id": "...", "tokens_created": 42, "regions_removed": 0}

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

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

from promptshield import PromptShield

ps = PromptShield()

def process(input_path: str, output_path: str):
    # Step 1 — Detect PII (runs the full local pipeline)
    result = ps.detect(input_path)
    print(f"Loaded: {result.file} ({result.pages} pages)")
    print(f"Total PII entities: {result.total_regions}")
    for page in result.regions:
        for entity in page["entities"]:
            print(f"  Page {page['page']}: [{entity['type']}] {entity['text']}")

    # Step 2 — Anonymize (reversible tokens by default; pass redact=True
    # for permanent removal). Output is always a PDF.
    out = ps.anonymize(input_path, output_path)
    print(f"Anonymized: {out.tokens_created} tokens, saved to {out.output_file}")

    # Step 3 — Restore the originals later from the local token vault
    restored = ps.detokenize(output_path, "contract-restored.pdf")
    print(f"Restored {restored.tokens_replaced} tokens")

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

# Async variants are available too: ps.adetect / ps.aanonymize / ps.adetokenize

from pathlib import Path
from promptshield import PromptShield

ps = PromptShield()

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}")
        out_file = output_path / f"anon_{file.stem}.pdf"
        result = ps.anonymize(str(file), str(out_file))
        print(f"  → {result.tokens_created} tokens, saved to {out_file.name}")

    print("Batch complete!")

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