Reidentify Text

This route is intended to improve integrations with LLMs such as ChatGPT. Entities that are removed prior to sending to the LLM can be re-injected into the response from the LLM to improve user experience.

Request
header Parameters
x-api-key
string (X-Api-Key)
Default:
Request Body schema: application/json
required
processed_text
required
Array of strings (Processed Text)

The text with redaction markers. The markers will be replaced with the entity texts. E.g. Hi [NAME_1], nice to meet you.

required
Array of objects (Entities)

A list of all entities found in the text.

model
string (Model)

The LLM that provides the completions. E.g. gpt3.5-turbo. Whilst optional, this is used to improve the re-identification process by accounting for the model's unique behaviour surrounding redaction markers

reidentify_sensitive_fields
boolean (Reidentify Sensitive Fields)
Default: true

When this parameter is set to False, the re-identifier will mask fields ['BANK_ACCOUNT', 'CREDIT_CARD', 'CREDIT_CARD_EXPIRATION', 'CVV', 'ROUTING_NUMBER', 'ACCOUNT_NUMBER', 'DRIVER_LICENSE', 'HEALTHCARE_NUMBER', 'PASSPORT_NUMBER', 'PASSWORD', 'SSN', 'VEHICLE_ID'] with '#' instead of re-identifying them. The last quarter of CREDIT_CARD will be re-identified. When the parameter is set to True, all fields will be re-identified.

project_id
string (Project Id) <= 60 characters ^[a-zA-Z0-9\-_\:]*$
Default: "main"

Used to categorize requests for reporting purposes. Limited to alphanumeric characters or the following special characters :_-

Responses
200

Successful Response

400

Bad Request

500

Internal Server Error

4XX

Client Error

post/process/text/reidentify
Request samples 
Response samples 
application/json
[
  • "string"
]
© Copyright 2024 Private AI. 
We use analytics and minimal tracking across our websites to help improve performance and user experience. Our privacy policy.