> For the complete documentation index, see [llms.txt](https://fastino-1.gitbook.io/docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://fastino-1.gitbook.io/docs/models/pii.md).

# PII

## **Overview**

Fastino's PII model is designed to detect and redact Personally Identifiable Information (PII) and other sensitive information from text for a range of domains and use cases. It operates in a zero-shot manner, letting users define entity types to redact, and can be fine-tuned for your specific redaction requirements. 

## **Example Use Cases**

* Automating sensitive data redaction in documents, logs, and customer support transcripts
* Ensuring compliance with privacy regulations (e.g., GDPR, HIPAA)
* Data sanitization for analytics or public release

## Domains

Fastino's PII model was trained for a wide range of PII redaction tasks including those described below.

<table><thead><tr><th width="129.4609375">Domain</th><th width="315.125">Description</th><th width="301.9169921875">Example Entities</th></tr></thead><tbody><tr><td>Personal</td><td>Individual identifiers, contact info, and demographic attributes that can directly or indirectly reveal personal identity.</td><td>name, email address, phone number, username, gender, age, race, marital status, job title, income</td></tr><tr><td>Location</td><td>Geographic references such as street addresses, coordinates, and travel-related locations.</td><td>street address, city, postal code, us state, country, geo coordinates, flight departure airport, flight arrival airport, port of entry, apartment number</td></tr><tr><td>Temporal</td><td>Date and time values tied to individuals or transactions, such as birth dates, appointments, and admission dates.</td><td>date of birth, appointment date, transaction date, release date, coverage start date, hospital admission date, immunization date, employment start date, conviction date, wedding date</td></tr><tr><td>Healthcare</td><td>Protected health information including patient IDs, medical conditions, treatments, and lab results.</td><td>medical record number, patient id, medication, treatment, diagnosis, vaccine name, dosage, referral source, symptom, body mass index (BMI)</td></tr><tr><td>Finance</td><td>Financial account details, transaction records, loan identifiers, and card data.</td><td>credit card number, cvv, routing number, iban code, account balance, loan id, premium amount, transaction id, pension plan id, beneficiary</td></tr><tr><td>Government</td><td>Official government-issued identifiers including social security numbers, passports, and licenses.</td><td>social security number, passport number, driver license number, visa type, tax identification number, alien registration number, medicare beneficiary id number, national identity card, license plate number, utility meter id</td></tr></tbody></table>

## Usage

{% code title="Example Body" %}

```json
{
  "model_id": "fastino-pii-••••••••••",
  "input": [
    {
      "text": "9 AM for a Sedan for Jamie Derran",
      "parameters": {
        "entity_types": [
          "full_name",
          "car",
          "time"
        ],
        "threshold": 0.3
      }
    }
  ]
}
```

{% endcode %}

{% code title="Example Response" %}

```json
[{
  "input": "9 AM for a Sedan for Jamie Derran",
  "latency_ms": 77.31,
  "message": "Responses from endpoint.",
  "output": {
    "entities": [
      {
        "start": 0,
        "end": 4,
        "label": "time",
        "text": "9 AM",
        "score": 0.5893954038619995
      },
      {
        "start": 11,
        "end": 16,
        "label": "car",
        "text": "Sedan",
        "score": 0.8889331817626953
      },
      {
        "start": 21,
        "end": 33,
        "label": "full_name",
        "text": "Jamie Derran",
        "score": 0.9932531714439392
      }
    ],
    "redacted_text": "<TIME> for a <CAR> for <FULL_NAME>"
  },
  "status": "success"
}]
```

{% endcode %}