泰语合同与法律文件 OCR

# Encode without line wrapping: wrapped base64 breaks the JSON string.
DOC=$(base64 < invoice.pdf | tr -d '\n')
# --max-time covers a multi-page document; curl defaults to no limit.
curl -X POST https://api.paxalabs.com/v1/ocr \
  --max-time 300 \
  -H "Authorization: Bearer $PAXA_API_KEY" \
  -H "Content-Type: application/json" \
  -d "{\"document\": \"$DOC\", \"model\": \"paxa-ocr-lite-v1\"}"

DOC=$(base64 < invoice.pdf | tr -d '\n')
curl -X POST https://api.paxalabs.com/v1/ocr \
  --max-time 300 \
  -H "Authorization: Bearer $PAXA_API_KEY" \
  -H "Content-Type: application/json" \
  -d "{\"document\": \"$DOC\", \"model\": \"paxa-ocr-lite-v1\", \"output\": \"structured\"}"

import { readFile } from "node:fs/promises";

const document = (await readFile("invoice.pdf")).toString("base64");

const response = await fetch("https://api.paxalabs.com/v1/ocr", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.PAXA_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({ document, model: "paxa-ocr-lite-v1" }),
  // A multi-page document can run for minutes; give it room.
  signal: AbortSignal.timeout(300_000),
});

if (!response.ok) throw new Error(`OCR failed: ${response.status}`);
const { pages, usage } = await response.json();
console.log(pages[0].markdown, `${usage.credits} credits`);