latestSwagger 2.02026-08-2053114259.7 KB

41da8739a690

Text Redaction

Plain text

Returns a modified version of the provided text string that redacts or synthesizes the detected entity values.

post/api/Redact

Request body

generatorConfigobject

A dictionary of entity types to their transformation type.

generatorDefault'Off' | 'Synthesis' | 'Redaction' | 'GroupingSynthesis' | 'ReplacementSynthesis'

Possible values: <ul> <li>Off: Ignore the PII type</li> <li>Synthesis: Synthesize a new, realistic entity</li> <li>Redaction: Tokenize the entity, e.g. [NAME_GIVEN_ssys5]</li> <li>GroupingSynthesis: Synthesize entities using consistent grouping across the document</li> <li>ReplacementSynthesis: Replace entities with LLM generated values. ReplacementSynthesis is no longer used</li> </ul>

docXImagePolicy'Redact' | 'Ignore' | 'Remove'

Possible values: <ul> <li>Redact: Run images through OCR and redact sensitive text</li> <li>Ignore: Leave images alone</li> <li>Remove: Cover image with opaque black box</li> </ul>

rtfImagePolicy'Ignore' | 'Remove'

Possible values: <ul> <li>Ignore: Leave images alone</li> <li>Remove: Replace each image with an opaque black box of the same size</li> </ul>

docXCommentPolicy'Remove' | 'Ignore'

Possible values: <ul> <li>Remove: Remove all comments for file</li> <li>Ignore: Leave comments alone</li> </ul>

pdfSignaturePolicy'Redact' | 'Ignore'

Possible values: <ul> <li>Redact: Cover signature with opaque black box</li> <li>Ignore: Do not attempt to detect signature</li> </ul>

pdfSynthModePolicy'V1' | 'V2' | 'V5'

Possible values: <ul> <li>V1: Original mode with incorrect font, size and style</li> <li>V2: Legacy style-aware mode. Persisted V2 values now use the V5 font detector.</li> <li>V5: Style-aware mode backed by the V5 OpenVINO font model</li> </ul>

docXTablePolicy'Redact' | 'Remove'

Possible values: <ul> <li>Redact: Treat table content normally, feed into redaction process.</li> <li>Remove: Replace all characters and symbols in table with a placeholder.</li> </ul>

llmClassificationPolicy'Disabled' | 'Enabled' | 'PdfIdentificationAndSynthesis'

Possible values: <ul> <li>Disabled: Do not use LLM for structured data classification</li> <li>Enabled: Use LLM to classify structured data for PII detection</li> <li>PdfIdentificationAndSynthesis: Use an LLM instead of the NER model and C# generators for PDF PII identification and synthesis. Other file types continue to use their existing detection and synthesis paths.</li> </ul>

llmTableClassificationPolicy'Disabled' | 'Enabled' | 'PdfIdentificationAndSynthesis'

labelBlockListsobject

A list of regexes to match against the specified entity type for exclusion. Legacy strings inputs are accepted and normalized into regexes.

labelAllowListsobject

A list of regexes to match against the specified entity type for inclusion. Legacy strings inputs are accepted and normalized into regexes.

generatorMetadataobject

A dictionary mapping entity type names to their transformation metadata configuration.

customPiiEntityIdsstring[] nullable

A list of custom Pii Entity names to use for NER

customEntityRankingModesobject nullable

Optional per-entity ranking overrides for custom-PII and model-based entities detected in this request. Keys are entity Names (the same identifiers used in Solar.Core.Models.BaseApiRedactionRequest.CustomPiiEntityIds); values control whether the custom entity always wins an exact-boundary overlap against a built-in entity (Prioritized) or is compared by score (Standard). Omit to keep today's behavior of treating every requested custom entity as Prioritized. Supplying a key that does not match any requested custom-PII or model-based entity Name is rejected as a 400 error.

customEntityConfidenceThresholdsobject nullable

Optional per-entity minimum detection confidence thresholds for custom-PII and model-based entities detected in this request. Keys are entity Names (the same identifiers used in Solar.Core.Models.BaseApiRedactionRequest.CustomPiiEntityIds); each value is in (0, 1], and detections for that entity whose score falls below it are ignored. Omit to keep today's behavior of no confidence cutoff. Supplying a key that does not match any requested custom-PII or model-based entity Name, or a value outside (0, 1], is rejected as a 400 error.

textstring

The plain text to redact

Example request

{
  "generatorConfig": {
    "NAME_GIVEN": "Redaction",
    "NAME_FAMILY": "Redaction"
  },
  "labelBlockLists": {
    "NAME_FAMILY": {
      "regexes": [
        ".*\\s(disease|syndrom|disorder)"
      ]
    }
  },
  "labelAllowLists": {
    "HEALTHCARE_ID": {
      "regexes": [
        "[a-z]{2}\\d{9}"
      ]
    }
  },
  "customEntityRankingModes": {
    "MY_CUSTOM_ENTITY": "Standard"
  },
  "customEntityConfidenceThresholds": {
    "MY_CUSTOM_ENTITY": 0.5
  },
  "text": "My name is John Smith"
}

Response

Returns the redacted text

originalTextstring

The original input text before redaction.

redactedTextstring

The text after redaction has been applied.

usageinteger

The number of words processed.