Quickstart

Extract structured data from a document in under 2 minutes.

Prerequisites

• An API key from developers.qomplement.com (see Authentication)
• A document to process (PDF or image)
• Optional: Install the SDK — pip install qomplement or npm install qomplement

Step 1: Extract Data from a Document

Python

from qomplement import Qomplement

client = Qomplement("sd_YOUR_API_KEY")

result = client.extract("invoice.pdf")
print(result.fields)         # {'invoice_number': '12345', 'total': '1500.50'}
print(result.document_type)  # 'invoice'
print(result.confidence)     # 94

Node.js

import { Qomplement } from "qomplement";

const client = new Qomplement("sd_YOUR_API_KEY");

const result = await client.extract("invoice.pdf");
console.log(result.fields);        // { invoice_number: '12345', total: '1500.50' }
console.log(result.documentType);  // 'invoice'
console.log(result.confidence);    // 94

cURL

curl -X POST https://developer-api.qomplement.com/v1/extract \
  -H "Authorization: Bearer sd_YOUR_API_KEY" \
  -F "file=@invoice.pdf"

Step 2: Read the Response

For small documents (≤5 pages), you get the result immediately:

{
  "id": "550e8400-e29b-41d4-a716-446655440000",
  "status": "completed",
  "result": {
    "model": "qomplement-OCR-v1",
    "document_type": "invoice",
    "language": "en",
    "confidence": 95,
    "fields": {
      "invoice_number": "INV-2025-001234",
      "total_amount": "1500.50",
      "invoice_date": "2025-02-26",
      "vendor_name": "ABC Corp"
    },
    "tables": [],
    "pages_processed": 1,
    "processing_time_ms": 3456
  }
}

The fields object contains all extracted key-value pairs as a flat dictionary. Access values directly:

fields = result["result"]["fields"]
print(f"Invoice: {fields['invoice_number']}")
print(f"Total: ${fields['total_amount']}")

Step 3: Extract with a Schema (Optional)

Tell the API exactly which fields you want for higher accuracy:

Python

result = client.extract("invoice.pdf", schema=[
    {"name": "invoice_number", "type": "string"},
    {"name": "total", "type": "number"},
    {"name": "date", "type": "date"},
])

Node.js

const result = await client.extract("invoice.pdf", {
  schema: [
    { name: "invoice_number", type: "string" },
    { name: "total", type: "number" },
    { name: "date", type: "date" },
  ],
});

cURL

curl -X POST https://developer-api.qomplement.com/v1/extract \
  -H "Authorization: Bearer sd_YOUR_API_KEY" \
  -F "file=@invoice.pdf" \
  -F 'schema=[{"name":"invoice_number","type":"string"},{"name":"total","type":"number"},{"name":"date","type":"date"}]'

Step 4: Fill a PDF Form

Upload a source document and a target PDF form:

Python

result = client.fill_pdf("form_template.pdf", source="invoice.pdf")
result.save("filled_form.pdf")
print(f"Filled {result.fields_filled}/{result.fields_total} fields")

Node.js

const result = await client.fillPDF("form_template.pdf", {
  source: "invoice.pdf",
});
fs.writeFileSync("filled_form.pdf", result.fileBuffer);
console.log(`Filled ${result.fieldsFilled}/${result.fieldsTotal} fields`);

cURL

curl -X POST https://developer-api.qomplement.com/v1/fill/pdf \
  -H "Authorization: Bearer sd_YOUR_API_KEY" \
  -F "source_files=@invoice.pdf" \
  -F "target_pdf=@form_template.pdf"

The SDK automatically waits for completion and downloads the result. With cURL, you get a job ID to poll (see Jobs).

Step 5: Fill an Excel Template

Upload a source document and an Excel template:

Python

result = client.fill_excel("report_template.xlsx", source="invoice.pdf")
result.save("filled_report.xlsx")
print(f"Wrote {result.cells_written} cells in {result.sheets_modified}")

Node.js

const result = await client.fillExcel("report_template.xlsx", {
  source: "invoice.pdf",
});
fs.writeFileSync("filled_report.xlsx", result.fileBuffer);
console.log(`Wrote ${result.cellsWritten} cells in ${result.sheetsModified}`);

cURL

curl -X POST https://developer-api.qomplement.com/v1/fill/excel \
  -H "Authorization: Bearer sd_YOUR_API_KEY" \
  -F "source_files=@invoice.pdf" \
  -F "target_excel=@report_template.xlsx" \
  -F "fill_mode=smart"

What's Next

• Python SDK — Full Python SDK reference
• Node.js SDK — Full Node.js/TypeScript SDK reference
• Extract Endpoint — Full parameter reference
• Fill PDF — PDF form filling details and examples
• Fill Excel — Excel template filling with fill modes
• Jobs — Async job management
• Code Examples — Complete workflows