This commit is contained in:
21
docs/snippets/php/config/config_ocr.md
Normal file
21
docs/snippets/php/config/config_ocr.md
Normal file
@@ -0,0 +1,21 @@
|
||||
```php title="PHP"
|
||||
<?php
|
||||
declare(strict_types=1);
|
||||
|
||||
use Kreuzberg\Kreuzberg;
|
||||
use Kreuzberg\ExtractionConfig;
|
||||
use Kreuzberg\OcrConfig;
|
||||
|
||||
$config = new ExtractionConfig(
|
||||
ocr: new OcrConfig(
|
||||
backend: 'tesseract',
|
||||
language: 'eng'
|
||||
)
|
||||
);
|
||||
|
||||
$result = Kreuzberg::extractFileSync('scanned.pdf', null, $config);
|
||||
|
||||
echo "Content length: " . strlen($result->getContent()) . " characters\n";
|
||||
echo "Tables detected: " . count($result->getTables()) . "\n";
|
||||
?>
|
||||
```
|
||||
Reference in New Issue
Block a user