Data & Compliance

GateFlow provides enterprise-grade data handling and compliance features for regulated industries.

Overview

Data Pillar

Secure document processing and retrieval for AI applications.

Document Ingestion

Upload and process documents:

curl -X POST https://api.gateflow.ai/v1/data/documents \
  -H "Authorization: Bearer gw_prod_..." \
  -F "file=@contract.pdf" \
  -F "classification=confidential"

Supported formats: PDF, DOCX, TXT, MD, HTML

Learn more →

PII/PHI Detection

Automatic detection and handling of sensitive data:

{
  "detected_entities": [
    {"type": "PERSON", "text": "John Smith", "confidence": 0.98},
    {"type": "SSN", "text": "***-**-1234", "confidence": 0.99},
    {"type": "PHONE", "text": "(555) ***-****", "confidence": 0.95}
  ],
  "action_taken": "redacted"
}

Powered by Microsoft Presidio.

Learn more →

Vector Store

Enterprise vector database with:

• pgvector with HNSW indexing
• Row-level security
• Multi-tenant isolation

Learn more →

Semantic Search

Query your documents:

curl -X POST https://api.gateflow.ai/v1/data/search \
  -H "Authorization: Bearer gw_prod_..." \
  -H "Content-Type: application/json" \
  -d '{
    "query": "termination clause",
    "limit": 10,
    "classification_max": "confidential"
  }'

Learn more →

RAG Injection

Automatically inject relevant context into LLM requests:

response = client.chat.completions.create(
    model="gpt-5.2",
    messages=[{"role": "user", "content": "What's our refund policy?"}],
    extra_body={
        "gateflow": {
            "rag": {
                "enabled": True,
                "collection": "policies",
                "top_k": 5
            }
        }
    }
)

Learn more →

Data Security

Classification Levels

Level	Description	Access
public	Publicly available	All users
internal	Internal use only	Authenticated users
confidential	Sensitive business	Role-based
restricted	Highly sensitive	Named individuals
top_secret	Maximum protection	Special clearance

Learn more →

Data Isolation

Multi-tenant security:

• Row-level security in PostgreSQL
• Tenant-scoped encryption keys
• Network isolation

Learn more →

Data Residency

Control where data is stored:

{
  "residency": {
    "primary_region": "eu-west-1",
    "allowed_regions": ["eu-west-1", "eu-central-1"],
    "prohibited_regions": ["us-*", "cn-*"]
  }
}

Learn more →

Compliance Framework

Audit Trail

Immutable, hash-chained audit logs:

{
  "event_id": "evt_abc123",
  "timestamp": "2024-01-15T10:30:00Z",
  "action": "document.accessed",
  "actor": "user_xyz",
  "resource": "doc_456",
  "hash": "sha256:abc123...",
  "previous_hash": "sha256:xyz789..."
}

Learn more →

Compliance Regimes

Pre-configured policies for:

Regime	Features
HIPAA	PHI handling, BAA support, audit requirements
Legal Hold	Litigation preservation, discovery support
GDPR	Right to erasure, data portability, consent
EU AI Act	Risk classification, human oversight

Learn more →

Compliance Reports

Generate compliance attestations:

curl -X POST https://api.gateflow.ai/v1/compliance/reports \
  -H "Authorization: Bearer gw_prod_..." \
  -H "Content-Type: application/json" \
  -d '{
    "type": "hipaa_audit",
    "period": {
      "start": "2024-01-01",
      "end": "2024-03-31"
    },
    "format": "pdf"
  }'

Learn more →

Document OCR

Mistral Document AI

Enterprise OCR for complex documents:

curl -X POST https://api.gateflow.ai/v1/data/ocr \
  -H "Authorization: Bearer gw_prod_..." \
  -F "file=@scanned_contract.pdf" \
  -F "extract_tables=true"

Features:

• Table extraction
• Handwriting recognition
• Multi-page documents
• 100+ languages

Learn more →

Quick Start

1. Upload a Document

curl -X POST https://api.gateflow.ai/v1/data/documents \
  -H "Authorization: Bearer gw_prod_..." \
  -F "file=@policies.pdf" \
  -F "classification=internal"

2. Search

curl -X POST https://api.gateflow.ai/v1/data/search \
  -H "Authorization: Bearer gw_prod_..." \
  -H "Content-Type: application/json" \
  -d '{"query": "vacation policy"}'

3. Use with RAG

response = client.chat.completions.create(
    model="gpt-5.2",
    messages=[{"role": "user", "content": "How much vacation do I get?"}],
    extra_body={
        "gateflow": {
            "rag": {"enabled": True, "collection": "hr_policies"}
        }
    }
)

API Reference

• Documents API - Upload, list, manage documents
• Search API - Semantic search and retrieval
• Compliance API - Audit logs and reports

Next Steps

• Document Ingestion - Upload documents
• PII Detection - Configure PII handling
• Compliance Overview - Set up compliance