Deepread Pii

{
  "id": "550e8400-e29b-41d4-a716-446655440000",
  "status": "queued"
}

{
  "id": "550e8400-...",
  "status": "completed",
  "progress_percent": 100,
  "redacted_file_url": "https://...(signed URL)...",
  "report": {
    "id": "550e8400-...",
    "page_count": 3,
    "processing_time_ms": 4200,
    "pii_detected": {
      "NAME": {
        "count": 4,
        "pages": [1, 2, 3],
        "confidence_avg": 0.93,
        "confidence_min": 0.87,
        "below_threshold": 0,
        "allowed": 0
      },
      "SSN": {
        "count": 1,
        "pages": [1],
        "confidence_avg": 0.98,
        "confidence_min": 0.98,
        "below_threshold": 0,
        "allowed": 0
      }
    },
    "total_redactions": 5,
    "redaction_policy": "black_bar",
    "confidence_threshold_used": 0.85,
    "below_threshold_count": 0
  },
  "error": null
}

{
  "id": "550e8400-...",
  "status": "failed",
  "progress_percent": 0,
  "redacted_file_url": null,
  "report": null,
  "error": {
    "code": "DOCUMENT_CORRUPTED",
    "message": "Unable to process the document"
  }
}

import requests
import time

API_KEY = "sk_live_YOUR_KEY"
BASE = "https://api.deepread.tech"

# Submit document for redaction
with open("patient_record.pdf", "rb") as f:
    resp = requests.post(
        f"{BASE}/v1/pii/redact",
        headers={"X-API-Key": API_KEY},
        files={"file": f},
    )
job_id = resp.json()["id"]

# Poll with backoff
delay = 3
while True:
    time.sleep(delay)
    result = requests.get(
        f"{BASE}/v1/pii/{job_id}",
        headers={"X-API-Key": API_KEY}
    ).json()

    if result["status"] == "completed":
        # Download redacted file
        redacted_url = result["redacted_file_url"]
        redacted_pdf = requests.get(redacted_url).content
        with open("patient_record_redacted.pdf", "wb") as f:
            f.write(redacted_pdf)

        # Review detection report
        report = result["report"]
        print(f"Redacted {report['total_redactions']} PII instances")
        for pii_type, summary in report["pii_detected"].items():
            print(f"  {pii_type}: {summary['count']} found on pages {summary['pages']}")
        break

    elif result["status"] == "failed":
        print(f"Failed: {result['error']['message']}")
        break

    delay = min(delay * 1.5, 15)

import fs from "fs";

const API_KEY = "sk_live_YOUR_KEY";
const BASE = "https://api.deepread.tech";

// Submit document
const form = new FormData();
form.append("file", fs.createReadStream("contract.pdf"));

const { id: jobId } = await fetch(`${BASE}/v1/pii/redact`, {
  method: "POST",
  headers: { "X-API-Key": API_KEY },
  body: form,
}).then((r) => r.json());

// Poll with backoff
let delay = 3000;
let result;
do {
  await new Promise((r) => setTimeout(r, delay));
  result = await fetch(`${BASE}/v1/pii/${jobId}`, {
    headers: { "X-API-Key": API_KEY },
  }).then((r) => r.json());
  delay = Math.min(delay * 1.5, 15000);
} while (!["completed", "failed"].includes(result.status));

if (result.status === "completed") {
  console.log(`Redacted file: ${result.redacted_file_url}`);
  console.log(`Total redactions: ${result.report.total_redactions}`);
}

# Redact a PDF
curl -X POST https://api.deepread.tech/v1/pii/redact \
  -H "X-API-Key: $DEEPREAD_API_KEY" \
  -F "file=@document.pdf"

# Redact a scanned image
curl -X POST https://api.deepread.tech/v1/pii/redact \
  -H "X-API-Key: $DEEPREAD_API_KEY" \
  -F "file=@id_card.png"

# Redact with language hint
curl -X POST https://api.deepread.tech/v1/pii/redact \
  -H "X-API-Key: $DEEPREAD_API_KEY" \
  -F "file=@documento.pdf" \
  -F "language=es"

# Check status
curl https://api.deepread.tech/v1/pii/JOB_ID \
  -H "X-API-Key: $DEEPREAD_API_KEY"

# Step 1: Extract structured data (keeps the data you need)
curl -X POST https://api.deepread.tech/v1/process \
  -H "X-API-Key: $DEEPREAD_API_KEY" \
  -F "file=@claim.pdf" \
  -F 'schema={"type":"object","properties":{"claim_number":{"type":"string"},"amount":{"type":"number"}}}'

# Step 2: Redact PII from original (clean copy for filing)
curl -X POST https://api.deepread.tech/v1/pii/redact \
  -H "X-API-Key: $DEEPREAD_API_KEY" \
  -F "file=@claim.pdf"

# 1. Redact the document
resp = requests.post(f"{BASE}/v1/pii/redact",
    headers={"X-API-Key": API_KEY},
    files={"file": open("report.pdf", "rb")})
job_id = resp.json()["id"]

# 2. Wait for completion, download redacted version
# 3. Now safe to send to any LLM for analysis

# Step 1: Fill the form
curl -X POST https://api.deepread.tech/v1/form-fill \
  -H "X-API-Key: $DEEPREAD_API_KEY" \
  -F "file=@w4_form.pdf" \
  -F 'form_fields={"full_name":"Jane Smith","ssn":"456-78-9012"}'

# Step 2: Redact the filled form for internal records
curl -X POST https://api.deepread.tech/v1/pii/redact \
  -H "X-API-Key: $DEEPREAD_API_KEY" \
  -F "file=@w4_filled.pdf"

curl -X POST https://api.deepread.tech/v1/pii/redact \
  -H "X-API-Key: $DEEPREAD_API_KEY" \
  -F "file=@document.pdf" \
  -F "webhook_url=https://your-app.com/webhooks/pii"

report = result["report"]

# Check if anything was below confidence threshold
if report["below_threshold_count"] > 0:
    print(f"Warning: {report['below_threshold_count']} detections below threshold")
    print("Consider manual review of the original document")

# See breakdown by type
for pii_type, summary in report["pii_detected"].items():
    print(f"{pii_type}: {summary['count']} on pages {summary['pages']}")

-F "language=zh"   # Chinese
-F "language=es"   # Spanish
-F "language=hi"   # Hindi
-F "language=ar"   # Arabic

delay = 3
while True:
    time.sleep(delay)
    result = check_status(job_id)
    if result["status"] in ("completed", "failed"):
        break
    delay = min(delay * 1.5, 15)  # cap at 15s