# Document OCR & Structured Extraction (`toumi.oussema.re/document-ocr-extractor`) Actor

Extracts text from receipt, invoice, or scanned document images (OCR via Tesseract, no GPU required) and, optionally, structures key fields (vendor, date, total, line items) via an LLM on OpenRouter.

- **URL**: https://apify.com/toumi.oussema.re/document-ocr-extractor.md
- **Developed by:** [Oussema Toumi](https://apify.com/toumi.oussema.re) (community)
- **Categories:** AI, Agents, Automation
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $8.00 / 1,000 document ocr processeds

This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events.

Learn more: https://docs.apify.com/platform/actors/running/actors-in-store#pay-per-event

## What's an Apify Actor?

Actors are web data automations that power AI and operations. They run on the Apify platform to scrape websites, process data, connect APIs, and automate workflows.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.
Actors are written with capital "A".

## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.
The best way to integrate Actors is as follows.

- **AI agents and MCP clients** — the [Apify MCP server](https://docs.apify.com/integrations/mcp.md) at `https://mcp.apify.com` (remote, streamable HTTP, OAuth on first use).
- **Agentic workflows and local Actor development** — [Agent Skills](https://apify.com/.well-known/agent-skills/index.json) with the [Apify CLI](https://docs.apify.com/cli/docs.md): `npm install -g apify-cli`, then `apify login`.
- **JavaScript/TypeScript projects** — the official [JS/TS client](https://docs.apify.com/api/client/js/docs.md): `npm install apify-client`.
- **Python projects** — the official [Python client](https://docs.apify.com/api/client/python/docs.md): `pip install apify-client`.
- **Any other language** — the [REST API](https://docs.apify.com/api/v2.md).

For usage examples, see the [API](#api) section below.

For more details, see Apify documentation as [Markdown index](https://docs.apify.com/llms.txt) and [Markdown full-text](https://docs.apify.com/llms-full.txt).

# README

## Document OCR & Structured Extraction

Extracts text from receipt, invoice, or scanned document images via OCR
(Tesseract, 100% CPU, no GPU required), with an optional structured
extraction (vendor, date, total, line items) via an LLM on OpenRouter.

### Input

| Field | Type | Description |
|---|---|---|
| `fileUrls` | array | Direct image URLs (jpg/png/webp) |
| `ocrLanguage` | string | Tesseract language code (default: `fra`) |
| `structuredExtraction` | bool | Enable structured field extraction via LLM |
| `documentType` | string | `receipt`, `invoice`, or `generic` |
| `llmModel` | string | OpenRouter model (default: `anthropic/claude-3.5-haiku`) |
| `openrouterApiKey` | string | Required when `structuredExtraction=true` |

### Output (dataset)

Each record contains: `url`, `documentType`, `ocrText`,
`ocrConfidence`, and, when enabled, `structuredData` (JSON: vendor, date,
total, items, etc. depending on document type).

### Billing (pay-per-event)

- `document-ocred` — $0.008 — per document successfully OCR'd
- `structured-extracted` — $0.006 — additionally, if structured extraction succeeds
- `document-failed` — $0 — never billed

Example: 100 invoices, OCR + structured extraction on all ≈
100 × ($0.008 + $0.006) = **$1.40** billed to the user.

### Technical notes

- **No GPU required**: Tesseract.js runs entirely on CPU. On a small server
  (low RAM), processing images one at a time (already the case in this
  skeleton) avoids memory spikes.
- **Current limitation**: only accepts images (jpg/png/webp) by direct URL.
  Scanned PDFs must be converted to images upstream (e.g. with a dedicated
  Apify PDF→image Actor, or by adding `pdf-poppler`/`pdf2pic` — requires
  additional system dependencies in the Dockerfile, deliberately omitted
  here to stay lightweight).
- Structured extraction is optional and billed only when enabled: a user who
  just wants raw text only pays for the OCR.

# Actor input Schema

## `fileUrls` (type: `array`):

Direct URLs of document images (jpg, png, webp) — receipts, invoices, or scanned documents

## `ocrLanguage` (type: `string`):

Tesseract language code (e.g. fra, eng, deu). See Tesseract docs for the full list.

## `structuredExtraction` (type: `boolean`):

When enabled, sends the OCR text to an LLM (OpenRouter) to extract vendor, date, total, and line items as JSON

## `documentType` (type: `string`):

Document type used for the structured extraction prompt

## `llmModel` (type: `string`):

OpenRouter model id used for structured field extraction

## `openrouterApiKey` (type: `string`):

Required only if structuredExtraction is enabled

## Actor input object example

```json
{
  "fileUrls": [
    "https://cdn.jsdelivr.net/gh/naptha/tesseract.js@5/tests/assets/images/testocr.png"
  ],
  "ocrLanguage": "eng",
  "structuredExtraction": false,
  "documentType": "invoice",
  "llmModel": "anthropic/claude-3.5-haiku"
}
```

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

```javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {};

// Run the Actor and wait for it to finish
const run = await client.actor("toumi.oussema.re/document-ocr-extractor").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

```

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = {}

# Run the Actor and wait for it to finish
run = client.actor("toumi.oussema.re/document-ocr-extractor").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{}' |
apify call toumi.oussema.re/document-ocr-extractor --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,toumi.oussema.re/document-ocr-extractor"
        }
    }
}

```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/T4yTYwF5iRYjliXKT/builds/krgvzWdjwezuHauYT/openapi.json