langchain-data-handling

# LangChain Data Handling

## Overview
Best practices for handling sensitive data, PII protection, and compliance in LangChain applications.

## Prerequisites
- Understanding of data privacy regulations (GDPR, CCPA)
- LangChain application processing user data
- Data classification framework

## Instructions

### Step 1: PII Detection and Masking
```python
import re
from typing import List, Tuple
from dataclasses import dataclass

@dataclass
class PIIPattern:
    name: str
    pattern: str
    replacement: str

PII_PATTERNS = [
    PIIPattern("email", r"\b[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Z|a-z]{2,}\b", "[EMAIL]"),
    PIIPattern("phone", r"\b\d{3}[-.]?\d{3}[-.]?\d{4}\b", "[PHONE]"),
    PIIPattern("ssn", r"\b\d{3}-\d{2}-\d{4}\b", "[SSN]"),
    PIIPattern("credit_card", r"\b\d{4}[-\s]?\d{4}[-\s]?\d{4}[-\s]?\d{4}\b", "[CREDIT_CARD]"),
    PIIPattern("ip_address", r"\b\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}\b", "[IP_ADDRESS]"),
    PIIPattern("date_of_birth", r"\b\d{1,2}/\d{1,2}/\d{2,4}\b", "[DOB]"),
]

class PIIDetector:
    """Detect and mask PII in text."""

    def __init__(self, patterns: List[PIIPattern] = None):
        self.patterns = patterns or PII_PATTERNS

    def detect(self, text: str) -> List[Tuple[str, str, int, int]]:
        """Detect PII in text. Returns list of (type, value, start, end)."""
        findings = []
        for pattern in self.patterns:
            for match in re.finditer(pattern.pattern, text, re.IGNORECASE):
                findings.append((
                    pattern.name,
                    match.group(),
                    match.start(),
                    match.end()
                ))
        return findings

    def mask(self, text: str) -> str:
        """Mask all PII in text."""
        masked = text
        for pattern in self.patterns:
            masked = re.sub(pattern.pattern, pattern.replacement, masked, flags=re.IGNORECASE)
        return masked

    def redact(self, text: str) -> Tuple[str, dict]:
        """Redact