Detectar PII en PDF con carga de archivo
Detecta PII (Información de Identificación Personal) en un archivo PDF sin redacción. Acepta PDF como carga de archivo multipart/form-data. Devuelve entidades PII detectadas y métricas de procesamiento. Admite múltiples idiomas OCR, detección de texto rotado y detección personalizable de etiquetas PII. Solo procesa la primera página del PDF.
Authorization
APIKeyHeader In: header
Request Body
multipart/form-data
PDF file to detect PII in
binaryForce OCR processing even if text is extractable from PDF
trueEnable detection and recognition of rotated text in the document
trueList of custom tags to detect. These tags are added to the standard PII tags
List of predefined PII tags to detect. If empty, all available tags are used. Available tags: DATE, PERSON_NAME, ORGANIZATION, LOCATION, EMAIL, PHONE, ID, ACCOUNT, ZIP_CODE, ADDRESS, IP, URL, SSN, DRIVER_LICENSE, PASSPORT, PASSWORD, AGE, CREDIT_CARD, MONEY_AMOUNT. Can be comma-separated string like 'PERSON_NAME,EMAIL,PHONE' or list of strings.
List of OCR languages to use for text recognition. Available languages: eng (English), spa (Spanish), fra (French), deu (German), ita (Italian), por (Portuguese), rus (Russian). Defaults to English only. Multiple languages can improve accuracy for multilingual documents. Can be comma-separated string like 'eng,spa' or list of strings.
[["eng"]]Response Body
application/json
application/json
application/json
application/json
curl -X POST "https://api.pdf-redaction.com/api/detect/pii/file/pdf" \ -F pdf="document.pdf"{
"detected_pii": {
"path": "string",
"entities": [
{
"entity_group": "string",
"score": 0,
"word": "string",
"start": 0,
"end": 0,
"boxes": [
{
"text": "string",
"score": 0,
"x": 0,
"y": 0,
"width": 0,
"height": 0,
"angle": 0
}
]
}
],
"exception": "string",
"json": ""
},
"processing_time": {
"total": 0,
"stages": {
"property1": 0,
"property2": 0
}
}
}{
"detail": "Invalid document type"
}{
"error_code": "LLM_CALL_ERROR",
"message": "string"
}{
"detail": [
{
"loc": [
"string"
],
"msg": "string",
"type": "string"
}
]
}