Function: createRapidOcr()

function createRapidOcr(opts?): Promise<OcrEngine & AsyncDisposable>;

Defined in: src/helpers/ocr/rapidOcr.ts:46

Default OCR engine: the RapidOCR stack (PaddleOCR PP-OCR models on ONNX Runtime) through the optional peer dependencies ppu-paddle-ocr and onnxruntime-node. Models are downloaded and cached on first use.

Create one engine and pass it as ocr to reuse the loaded models across documents; release them with dispose(), or let await using do it:

await using ocr = await createRapidOcr();
for (const buf of pdfs) await toMarkdown(buf, { tableStrategy: "pixels", ocr });

Parameters

opts?

RapidOcrOptions = {}

Returns

Promise<OcrEngine & AsyncDisposable>