RAG Pipeline Protection

import { Blindfold } from '@blindfold/sdk';

const blindfold = new Blindfold({ apiKey: 'your-api-key' });

const documents = [
  'Customer John Smith (john@example.com) reported a billing error.',
  'Maria Garcia (+34 612 345 678) requested a data export.',
];

const safeDocuments = [];
for (const doc of documents) {
  // Redact contact info only — keep names searchable
  const result = await blindfold.redact(doc, {
    entities: ['email address', 'phone number'],
  });
  safeDocuments.push(result.text);
}

// Index safeDocuments into your vector store

from langchain_blindfold import BlindfoldPIITransformer
from langchain_core.documents import Document

# Redact contact info only — keep names searchable
transformer = BlindfoldPIITransformer(
    pii_method="redact",
    entities=["email address", "phone number"],
)

docs = [
    Document(page_content="Customer John Smith (john@example.com) reported a billing error."),
    Document(page_content="Maria Garcia (+34 612 345 678) requested a data export."),
]

safe_docs = transformer.transform_documents(docs)
# Index safe_docs into your vector store

import { Blindfold } from '@blindfold/sdk';
import OpenAI from 'openai';

const blindfold = new Blindfold({ apiKey: 'your-api-key' });
const openai = new OpenAI();

const question = "What happened with John Smith's billing issue?";

// Step 1: Search with original question — names match
const results = await collection.query({
  queryTexts: [question], nResults: 3,
});
const context = results.documents[0].join('\n\n');

// Step 2: Single tokenize call — consistent token numbering
const promptText = `Context:\n${context}\n\nQuestion: ${question}`;
const tokenized = await blindfold.tokenize(promptText);

// Step 3: Send to LLM — no PII
const response = await openai.chat.completions.create({
  model: 'gpt-4o-mini',
  messages: [
    { role: 'system', content: 'Answer using the provided context.' },
    { role: 'user', content: tokenized.text },
  ],
});
const aiResponse = response.choices[0].message.content;

// Step 4: Detokenize
const final = blindfold.detokenize(aiResponse, tokenized.mapping);
console.log(final.text);

from blindfold import Blindfold
from langchain_openai import ChatOpenAI
from langchain_core.runnables import RunnableLambda

blindfold_client = Blindfold(api_key="your-api-key")

def retrieve_and_tokenize(question: str) -> dict:
    # Retrieve with original question — names match
    docs = retriever.invoke(question)
    context = "\n\n".join(doc.page_content for doc in docs)

    # Single tokenize call — consistent token numbering
    prompt_text = f"Context:\n{context}\n\nQuestion: {question}"
    tokenized = blindfold_client.tokenize(prompt_text)
    return {"tokenized_text": tokenized.text, "mapping": tokenized.mapping}

chain = RunnableLambda(retrieve_and_tokenize) | ...  # LLM + detokenize