v1.0 is now live in public beta

Extract structured data from any document

Turn messy PDFs, receipts, and forms into clean, actionable JSON. Built for developers with a powerful API, custom schemas, and open-source flexibility.

Star on GitHubOpen Dashboard
POST/api/v1/extract
Request payload
{
  "documentUrl": "https://example.com/invoice-129.pdf",
  "schema": {
    "type": "object",
    "properties": {
      "invoiceId": { "type": "string" },
      "totalAmount": { "type": "number" },
      "lineItems": {
        "type": "array",
        "items": { "type": "string" }
      }
    }
  }
}
Response
{
  "success": true,
  "data": {
    "invoiceId": "INV-2023-001",
    "totalAmount": 1450.00,
    "lineItems": [
      "Struxio Cloud Subscription",
      "API Overage Fees"
    ]
  },
  "confidenceScore": 0.98,
  "processingTimeMs": 1420
}

Powerful features for modern teams

Everything you need to automate document processing at scale, with developer-first tooling.

Schema-driven extraction

Define exactly what you want using JSON Schema. Struxio intelligently finds and maps the data to your exact structure.

Multi-format support

Process complex PDFs, standard images (PNG, JPG, WebP), and direct text inputs with equal precision and speed.

Batch processing

Send hundreds of documents at once. Our engine scales to handle large workloads effortlessly.

API-first design

Integrate seamlessly into your existing stack with our RESTful API and comprehensive SDKs.

Template library

Don't want to write schemas? Use our pre-built, battle-tested templates for invoices, receipts, and identity documents.

Open source

Self-host entirely on your own infrastructure for maximum data privacy and control.

How it works

Extracting data is as simple as defining your schema and firing an API request.

1

1Upload Document

invoice.pdf
2

2Provide Schema

const schema = {
  type: "object",
  properties: {
    vendor: { type: "string" },
    total: { type: "number" },
    date: { type: "string" }
  }
};
3

3Get Structured Data

{
  "vendor": "Acme Corp",
  "total": 149.99,
  "date": "2024-03-15"
}