Getting Started

Get up and running with LeapOCR in under 5 minutes. This guide will walk you through processing your first document.

What you'll need: - A LeapOCR API key (sign up here) - A PDF or image document to process - Basic knowledge of your preferred programming language

Quick Start

Get Your API Key

Sign up at leapocr.com/signup
Navigate to your dashboard
Copy your API key
Store it securely (use environment variables)

export LEAPOCR_API_KEY="your-api-key-here"

Choose Your SDK

Select the SDK for your programming language:

JavaScript/TypeScript - For Node.js and browsers
Python - For Python applications
Go - For Go applications
REST API - For direct HTTP access

Install the SDK

Install the appropriate package for your language:

JavaScript/TypeScript

npm install leapocr

Python

pip install leapocr

go get github.com/leapocr/leapocr-go

Process Your First Document

Here's a simple example in each language:

JavaScript/TypeScript

import { LeapOCR } from "leapocr";

const client = new LeapOCR({
  apiKey: process.env.LEAPOCR_API_KEY,
});

// Process a document
const job = await client.ocr.processURL("https://example.com/invoice.pdf", {
  format: "structured",
  instructions: "Extract invoice number, date, and total amount",
});

// Wait for completion
const result = await client.ocr.waitUntilDone(job.jobId);

console.log("Extracted data:", result.data);

// Delete the job
await client.ocr.deleteJob(job.jobId);

Python

import asyncio
from leapocr import LeapOCR, ProcessOptions, Format

async def main():
    async with LeapOCR(os.getenv("LEAPOCR_API_KEY")) as client:
        result = await client.ocr.process_and_wait(
            "https://example.com/invoice.pdf",
            options=ProcessOptions(
                format=Format.STRUCTURED,
                instructions="Extract invoice number, date, and total amount"
            )
        )
        print("Extracted data:", result.data)

        # Delete the job
        await client.ocr.delete_job(result.job_id)

asyncio.run(main())

package main

import (
    "context"
    "fmt"
    "log"
    "os"
    "github.com/leapocr/leapocr-go"
)

func main() {
    client, _ := ocr.New(os.Getenv("LEAPOCR_API_KEY"))
    ctx := context.Background()

    job, _ := client.ProcessURL(ctx,
        "https://example.com/invoice.pdf",
        ocr.WithFormat(ocr.FormatStructured),
        ocr.WithInstructions("Extract invoice number, date, and total amount"),
    )

    result, _ := client.WaitUntilDone(ctx, job.ID)
    fmt.Printf("Extracted data: %+v\n", result.Data)

    // Delete the job
    client.DeleteJob(ctx, job.ID)
}

Understanding the Response

When processing completes, you'll receive a result with this structure:

{
  "job_id": "job_abc123",
  "status": "completed",
  "credits_used": 3,
  "processing_time_seconds": 12.5,
  "pages": [
    {
      "page_number": 1,
      "text": "Invoice content...",
      "data": {
        "invoice_number": "INV-2024-001",
        "date": "2024-01-15",
        "total": 1234.56
      }
    }
  ],
  "data": {
    "invoice_number": "INV-2024-001",
    "date": "2024-01-15",
    "total": 1234.56
  }
}

Next Steps

Now that you've processed your first document, explore these topics:

Core Concepts

Processing Models - Choose the right AI model
Output Formats - Understand different output types
Custom Schemas - Define structured extraction

Common Use Cases

Advanced Features

Error Handling - Handle failures gracefully
Custom Models - Use specialized models

Common Issues

Authentication Error?

Make sure your API key is correctly set and valid. Check that you're using the environment variable or passing it correctly to the SDK.

Job Timing Out?

Large documents may take longer to process. The waitUntilDone method has a default timeout. For very large documents, consider polling the status manually with a longer timeout.

Ready to dive deeper? Check out the SDK documentation for your language or explore use cases for inspiration.

Getting Started

On this page