Skip to main content
Memvid can detect and mask Personally Identifiable Information (PII) in search results and ask responses. The original data remains searchable, but sensitive information is redacted in output.

How It Works

Example:
  • Original: "Contact john@example.com or call 555-123-4567"
  • Masked: "Contact [EMAIL] or call [PHONE]"
Key points:
  • Original data preserved: Content stored without modification
  • Searchable: You can search for emails, phones, etc.
  • Masked on output: PII hidden in results and responses
  • Query-time detection: No preprocessing required

Detected PII Types


CLI Usage

Mask PII in Ask Responses

Without masking:
With --mask-pii:

PII in Search Results


SDK Usage

Python

Node.js


Utility Functions

Check for PII

Mask PII in Text

Output:

Get PII Locations


Use Cases

Customer Support

Mask customer data in AI responses:

Compliance (GDPR, HIPAA)

Redact PII before displaying or logging:

Development & Testing

Mask real data in development environments:

Audit Logging

Log queries without exposing PII:

Configuration

Default Behavior

PII masking is disabled by default. Enable it explicitly:

Why Not Default?

  • Performance overhead for detection
  • Some use cases need raw data
  • Explicit opt-in for compliance clarity

Detection Patterns

Email Addresses

Regex: [a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}

Phone Numbers

Supports US, UK, and international formats.

Social Security Numbers

US SSN format with common separators.

Credit Card Numbers

Luhn-validated card number patterns.

IP Addresses

IPv4 addresses (IPv6 coming soon).

API Keys & Tokens

Common API key and token prefixes.

Limitations

Not Detected

Some PII types are not currently detected:

False Positives

Some patterns may be incorrectly flagged:

Context Insensitive

Detection is pattern-based, not context-aware:

Best Practices

1. Enable for User-Facing Output

2. Keep Original for Internal Use

3. Mask Before Logging

4. Combine with Encryption

For maximum protection:

5. Test Your Patterns

Verify detection works for your data:

Compliance Considerations

GDPR

  • PII masking helps with data minimization
  • Original data still stored (not anonymized)
  • Consider encryption + masking for full compliance
  • Document your data handling in privacy policy

HIPAA

  • Masks PHI in output (emails, phones)
  • Not a complete de-identification solution
  • Combine with permission-aware retrieval (ACL) and encryption
  • Consult compliance officer for healthcare data

SOC 2

  • Demonstrates data protection controls
  • Enable masking in production environments
  • Log that masking is applied
  • Include in security documentation

Performance

PII detection adds minimal overhead: Overhead is ~5-10% depending on text length.

Future Features

Coming soon:
  • Custom PII patterns
  • Named entity recognition (names, addresses)
  • Per-type masking control
  • Reversible masking with keys
  • IPv6 address detection
  • International phone formats

Next Steps

Encryption

Encrypt data at rest

Security FAQ

Security and compliance questions