FastPII is an AI Data Security Platform with an open-source SDK for European personal identifiers. It detects, validates, and transforms sensitive data in text using checksum validation for identifiers like rodné číslo, PESEL, Steuer-ID, and SIREN.

How do I install FastPII?

Install FastPII with pip: pip install fastpii. It requires Python 3.10 or newer and has zero core dependencies.

What countries does FastPII support?

FastPII supports 4 regions: Czech Republic (15 detectors), Poland (6 detectors), Germany (6 detectors), and France (6 detectors). This includes identifiers like rodné číslo, IČO, DIČ, PESEL, NIP, REGON, Steuer-ID, USt-IdNr, SIREN, SIRET, and INSEE/NIR.

Does FastPII have external dependencies?

No. FastPII has zero core dependencies. Optional integrations like FastAPI and LangChain are available through pip extras: pip install fastpii[fastapi] or pip install fastpii[langchain].

How does FastPII validate identifiers?

FastPII uses country-specific checksum algorithms: Mod 11 for rodné číslo and IČO, Mod 10 for PESEL, ISO 7064 MOD 11,10 for Steuer-ID, Luhn for SIREN/SIRET, and Mod-97 for INSEE/NIR. This ensures only structurally valid identifiers are detected.

Log, query, export, and analyze FastPII Gateway audit events and dashboard metrics.

Gateway Audit

Name: FastPII
Author: FastPII

Audit logging gives you an event-by-event record of what the Gateway saw and what it did. Each audit event can capture the request ID, user ID, workspace, auth mode, provider, model, action, entity types, confidence scores, risk level, latency, and request metadata.

Use audit data for compliance review, operations, incident response, and policy tuning.

For policy design, see Policies. For initial configuration, see Gateway Setup.

What gets logged

An audit event can include fields like:

{
  "request_id": "req_01J9X9BZ47A0P2QK3W4Q9D0M7J",
  "user_id": "user_123",
  "workspace_id": "ws_prod_eu",
  "auth_mode": "api_key",
  "provider": "openai",
  "model": "gpt-4o-mini",
  "action": "MASK",
  "entity_types": ["EMAIL", "PHONE"],
  "confidence_scores": [0.98, 0.91],
  "risk_level": "MEDIUM",
  "country": "CZ",
  "policy_id": "pol_default_mask",
  "policy_name": "Default mask policy",
  "latency_ms": 123.4,
  "detection_latency_ms": 40.1,
  "protection_latency_ms": 83.3,
  "is_streaming": false,
  "request_method": "POST",
  "request_path": "/v1/chat/completions",
  "response_status": 200
}

Risk levels

The Gateway audit API supports these risk levels:

Risk level	Meaning
`LOW`	Low sensitivity or low-impact exposure
`MEDIUM`	Moderate sensitivity, should usually be protected
`HIGH`	Sensitive personal data, usually needs strong controls
`CRITICAL`	Strictly controlled or prohibited data

Log an audit event

Use POST /api/v1/gateway/audit to record a gateway event. The endpoint returns 202 Accepted.

curl

curl -X POST "$FASTPII_BASE_URL/api/v1/gateway/audit" \
  -H "Content-Type: application/json" \
  -H "X-Service-Token: $FASTPII_SERVICE_TOKEN" \
  -d '{
    "request_id": "req_01J9X9BZ47A0P2QK3W4Q9D0M7J",
    "user_id": "user_123",
    "workspace_id": "ws_prod_eu",
    "auth_mode": "api_key",
    "provider": "openai",
    "model": "gpt-4o-mini",
    "action": "MASK",
    "entity_types": ["EMAIL", "PHONE"],
    "confidence_scores": [0.98, 0.91],
    "risk_level": "MEDIUM",
    "country": "CZ",
    "policy_id": "pol_default_mask",
    "policy_name": "Default mask policy",
    "latency_ms": 123.4,
    "detection_latency_ms": 40.1,
    "protection_latency_ms": 83.3,
    "is_streaming": false,
    "request_method": "POST",
    "request_path": "/v1/chat/completions",
    "response_status": 200
  }'

Python

import requests

base_url = "https://gateway.fastpii.com"
service_token = "your-gateway-service-token"

payload = {
    "request_id": "req_01J9X9BZ47A0P2QK3W4Q9D0M7J",
    "user_id": "user_123",
    "workspace_id": "ws_prod_eu",
    "auth_mode": "api_key",
    "provider": "openai",
    "model": "gpt-4o-mini",
    "action": "MASK",
    "entity_types": ["EMAIL", "PHONE"],
    "confidence_scores": [0.98, 0.91],
    "risk_level": "MEDIUM",
    "country": "CZ",
    "policy_id": "pol_default_mask",
    "policy_name": "Default mask policy",
    "latency_ms": 123.4,
    "detection_latency_ms": 40.1,
    "protection_latency_ms": 83.3,
    "is_streaming": False,
    "request_method": "POST",
    "request_path": "/v1/chat/completions",
    "response_status": 200,
}

response = requests.post(
    f"{base_url}/api/v1/gateway/audit",
    headers={
        "X-Service-Token": service_token,
        "Content-Type": "application/json",
    },
    json=payload,
    timeout=30,
)
response.raise_for_status()
print(response.status_code)
print(response.json())

Example response:

{
  "id": "evt_01J9X9C6AK6SRF5NXAK2J2J58W",
  "timestamp": "2026-07-10T10:22:17.321000Z",
  "request_id": "req_01J9X9BZ47A0P2QK3W4Q9D0M7J",
  "user_id": "user_123",
  "workspace_id": "ws_prod_eu",
  "auth_mode": "api_key",
  "provider": "openai",
  "model": "gpt-4o-mini",
  "action": "MASK",
  "entity_types": ["EMAIL", "PHONE"],
  "confidence_scores": [0.98, 0.91],
  "risk_level": "MEDIUM",
  "country": "CZ",
  "policy_id": "pol_default_mask",
  "policy_name": "Default mask policy",
  "latency_ms": 123.4,
  "detection_latency_ms": 40.1,
  "protection_latency_ms": 83.3,
  "is_streaming": false,
  "request_method": "POST",
  "request_path": "/v1/chat/completions",
  "response_status": 200
}

Query audit events

Use GET /api/v1/gateway/audit to list events by workspace. The API supports filters for user_id, action, provider, risk_level, plus pagination with page and page_size.

curl

curl -X GET "$FASTPII_BASE_URL/api/v1/gateway/audit?workspace_id=$FASTPII_WORKSPACE_ID&user_id=user_123&action=MASK&provider=openai&risk_level=MEDIUM&page=1&page_size=50" \
  -H "X-Service-Token: $FASTPII_SERVICE_TOKEN"

Python

import requests

workspace_id = "ws_prod_eu"

response = requests.get(
    f"{base_url}/api/v1/gateway/audit",
    params={
        "workspace_id": workspace_id,
        "user_id": "user_123",
        "action": "MASK",
        "provider": "openai",
        "risk_level": "MEDIUM",
        "page": 1,
        "page_size": 50,
    },
    headers={"X-Service-Token": service_token},
    timeout=30,
)
response.raise_for_status()
print(response.json())

Example response:

{
  "events": [
    {
      "id": "evt_01J9X9C6AK6SRF5NXAK2J2J58W",
      "timestamp": "2026-07-10T10:22:17.321000Z",
      "request_id": "req_01J9X9BZ47A0P2QK3W4Q9D0M7J",
      "user_id": "user_123",
      "workspace_id": "ws_prod_eu",
      "auth_mode": "api_key",
      "provider": "openai",
      "model": "gpt-4o-mini",
      "action": "MASK",
      "entity_types": ["EMAIL", "PHONE"],
      "confidence_scores": [0.98, 0.91],
      "risk_level": "MEDIUM",
      "country": "CZ",
      "policy_id": "pol_default_mask",
      "policy_name": "Default mask policy",
      "latency_ms": 123.4,
      "detection_latency_ms": 40.1,
      "protection_latency_ms": 83.3,
      "is_streaming": false,
      "request_method": "POST",
      "request_path": "/v1/chat/completions",
      "response_status": 200
    }
  ],
  "total": 1,
  "page": 1,
  "page_size": 50
}

Get a single event

Use GET /api/v1/gateway/audit/{event_id} when you need the full record for one event.

curl

curl -X GET "$FASTPII_BASE_URL/api/v1/gateway/audit/evt_01J9X9C6AK6SRF5NXAK2J2J58W" \
  -H "X-Service-Token: $FASTPII_SERVICE_TOKEN"

Python

import requests

event_id = "evt_01J9X9C6AK6SRF5NXAK2J2J58W"

response = requests.get(
    f"{base_url}/api/v1/gateway/audit/{event_id}",
    headers={"X-Service-Token": service_token},
    timeout=30,
)
response.raise_for_status()
print(response.json())

Export audit events

Use GET /api/v1/gateway/audit/export to export events in JSON or CSV. Supported filters include start_date, end_date, action, provider, and risk_level.

Export as JSON

curl -X GET "$FASTPII_BASE_URL/api/v1/gateway/audit/export?workspace_id=$FASTPII_WORKSPACE_ID&format=json&start_date=2026-07-01T00:00:00&end_date=2026-07-10T23:59:59&action=MASK&provider=openai&risk_level=MEDIUM" \
  -H "X-Service-Token: $FASTPII_SERVICE_TOKEN"

import requests

response = requests.get(
    f"{base_url}/api/v1/gateway/audit/export",
    params={
        "workspace_id": workspace_id,
        "format": "json",
        "start_date": "2026-07-01T00:00:00",
        "end_date": "2026-07-10T23:59:59",
        "action": "MASK",
        "provider": "openai",
        "risk_level": "MEDIUM",
    },
    headers={"X-Service-Token": service_token},
    timeout=60,
)
response.raise_for_status()
print(response.json())

Example JSON response:

[
  {
    "id": "evt_01J9X9C6AK6SRF5NXAK2J2J58W",
    "timestamp": "2026-07-10T10:22:17.321000Z",
    "request_id": "req_01J9X9BZ47A0P2QK3W4Q9D0M7J",
    "user_id": "user_123",
    "workspace_id": "ws_prod_eu",
    "auth_mode": "api_key",
    "provider": "openai",
    "model": "gpt-4o-mini",
    "action": "MASK",
    "entity_types": ["EMAIL", "PHONE"],
    "confidence_scores": [0.98, 0.91],
    "risk_level": "MEDIUM",
    "country": "CZ",
    "policy_id": "pol_default_mask",
    "policy_name": "Default mask policy",
    "latency_ms": 123.4,
    "detection_latency_ms": 40.1,
    "protection_latency_ms": 83.3,
    "is_streaming": false,
    "request_method": "POST",
    "request_path": "/v1/chat/completions",
    "response_status": 200
  }
]

Export as CSV

curl -X GET "$FASTPII_BASE_URL/api/v1/gateway/audit/export?workspace_id=$FASTPII_WORKSPACE_ID&format=csv&start_date=2026-07-01T00:00:00&end_date=2026-07-10T23:59:59" \
  -H "X-Service-Token: $FASTPII_SERVICE_TOKEN" \
  -o gateway-audit-export.csv

import requests

response = requests.get(
    f"{base_url}/api/v1/gateway/audit/export",
    params={
        "workspace_id": workspace_id,
        "format": "csv",
        "start_date": "2026-07-01T00:00:00",
        "end_date": "2026-07-10T23:59:59",
    },
    headers={"X-Service-Token": service_token},
    timeout=60,
)
response.raise_for_status()

with open("gateway-audit-export.csv", "wb") as f:
    f.write(response.content)

Example CSV output:

id,timestamp,request_id,user_id,workspace_id,auth_mode,provider,model,action,entity_types,confidence_scores,risk_level,country,policy_id,policy_name,latency_ms,detection_latency_ms,protection_latency_ms,is_streaming,request_method,request_path,response_status
evt_01J9X9C6AK6SRF5NXAK2J2J58W,2026-07-10T10:22:17.321000Z,req_01J9X9BZ47A0P2QK3W4Q9D0M7J,user_123,ws_prod_eu,api_key,openai,gpt-4o-mini,MASK,EMAIL;PHONE,0.98;0.91,MEDIUM,CZ,pol_default_mask,Default mask policy,123.4,40.1,83.3,False,POST,/v1/chat/completions,200

Dashboard metrics

The dashboard endpoints summarize audit data for a workspace.

Time periods

The metrics and violation trends endpoints accept these periods:

Period	Meaning
`7d`	Last 7 days
`30d`	Last 30 days
`90d`	Last 90 days

Get summary metrics

Use GET /api/v1/gateway/dashboard?workspace_id=...&period=30d.

curl

curl -X GET "$FASTPII_BASE_URL/api/v1/gateway/dashboard?workspace_id=$FASTPII_WORKSPACE_ID&period=30d" \
  -H "X-Service-Token: $FASTPII_SERVICE_TOKEN"

Python

import requests

response = requests.get(
    f"{base_url}/api/v1/gateway/dashboard",
    params={"workspace_id": workspace_id, "period": "30d"},
    headers={"X-Service-Token": service_token},
    timeout=30,
)
response.raise_for_status()
print(response.json())

Example response:

{
  "total_requests": 12450,
  "protected_requests": 9830,
  "blocked_requests": 315,
  "masked_requests": 9515,
  "allowed_requests": 2620,
  "period_start": "2026-06-10T00:00:00Z",
  "period_end": "2026-07-10T23:59:59Z"
}

Get violation trends

Use GET /api/v1/gateway/dashboard/violations?workspace_id=...&period=30d.

curl

curl -X GET "$FASTPII_BASE_URL/api/v1/gateway/dashboard/violations?workspace_id=$FASTPII_WORKSPACE_ID&period=30d" \
  -H "X-Service-Token: $FASTPII_SERVICE_TOKEN"

Python

import requests

response = requests.get(
    f"{base_url}/api/v1/gateway/dashboard/violations",
    params={"workspace_id": workspace_id, "period": "30d"},
    headers={"X-Service-Token": service_token},
    timeout=30,
)
response.raise_for_status()
print(response.json())

Example response:

{
  "period": "30d",
  "trends": [
    {
      "date": "2026-07-08",
      "blocked": 11,
      "masked": 304,
      "warned": 27,
      "allowed": 82
    },
    {
      "date": "2026-07-09",
      "blocked": 9,
      "masked": 289,
      "warned": 21,
      "allowed": 95
    }
  ]
}

Get risk distribution

Use GET /api/v1/gateway/dashboard/risk?workspace_id=....

curl

curl -X GET "$FASTPII_BASE_URL/api/v1/gateway/dashboard/risk?workspace_id=$FASTPII_WORKSPACE_ID" \
  -H "X-Service-Token: $FASTPII_SERVICE_TOKEN"

Python

import requests

response = requests.get(
    f"{base_url}/api/v1/gateway/dashboard/risk",
    params={"workspace_id": workspace_id},
    headers={"X-Service-Token": service_token},
    timeout=30,
)
response.raise_for_status()
print(response.json())

Example response:

{
  "risk_distribution": [
    {
      "entity_type": "EMAIL",
      "count": 4210,
      "risk_level": "MEDIUM"
    },
    {
      "entity_type": "CREDIT_CARD",
      "count": 87,
      "risk_level": "CRITICAL"
    }
  ],
  "by_provider": {
    "openai": {
      "MEDIUM": 3900,
      "CRITICAL": 80
    },
    "anthropic": {
      "MEDIUM": 310,
      "CRITICAL": 7
    }
  },
  "by_model": {
    "gpt-4o-mini": {
      "MEDIUM": 3700,
      "CRITICAL": 60
    },
    "claude-3-5-sonnet": {
      "MEDIUM": 510,
      "CRITICAL": 27
    }
  }
}

Get provider usage

Use GET /api/v1/gateway/dashboard/providers?workspace_id=....

curl

curl -X GET "$FASTPII_BASE_URL/api/v1/gateway/dashboard/providers?workspace_id=$FASTPII_WORKSPACE_ID" \
  -H "X-Service-Token: $FASTPII_SERVICE_TOKEN"

Python

import requests

response = requests.get(
    f"{base_url}/api/v1/gateway/dashboard/providers",
    params={"workspace_id": workspace_id},
    headers={"X-Service-Token": service_token},
    timeout=30,
)
response.raise_for_status()
print(response.json())

Example response:

{
  "providers": [
    {
      "provider": "openai",
      "model": "gpt-4o-mini",
      "request_count": 9200,
      "blocked_count": 210,
      "masked_count": 7150
    },
    {
      "provider": "anthropic",
      "model": "claude-3-5-sonnet",
      "request_count": 3250,
      "blocked_count": 105,
      "masked_count": 2365
    }
  ],
  "total_requests": 12450
}

Operational tips

Export JSON when you want to feed events into downstream systems
Export CSV for manual review, spreadsheet analysis, or audit handoff
Check violation trends after policy changes to confirm the expected effect
Review provider usage to spot drift between primary and fallback routes
Revisit risk distributions often, especially after adding new detectors or models

Gateway Audit

On this page