Files
fil/docs/snippets/wasm/ocr/ocr_elements.md

25 lines
549 B
Markdown
Raw Normal View History

2026-06-01 23:40:55 +02:00
```typescript title="WASM"
import init, { extractBytes } from "kreuzberg-wasm";
await init();
const documentData = await fetch("scanned.pdf").then((res) => res.arrayBuffer());
const result = await extractBytes(documentData, "application/pdf", {
ocr: {
backend: "tesseract",
language: "eng",
element_config: {
include_elements: true,
},
},
});
if (result.ocr_elements) {
for (const element of result.ocr_elements) {
console.log("Text:", element.text);
console.log("Confidence:", element.confidence);
}
}
```