อ่านเอกสารด้วย 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\"}"

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`);

import base64
import os

import requests

with open("invoice.pdf", "rb") as file:
    document = base64.b64encode(file.read()).decode()

response = requests.post(
    "https://api.paxalabs.com/v1/ocr",
    headers={"Authorization": f"Bearer {os.environ['PAXA_API_KEY']}"},
    json={"document": document, "model": "paxa-ocr-lite-v1"},
    # A multi-page document can run for minutes; give it room.
    timeout=300,
)
response.raise_for_status()
body = response.json()
print(body["pages"][0]["markdown"], body["usage"]["credits"], "credits")

{
  "pages": [
    {
      "page": 1,
      "markdown": "# ใบเสร็จรับเงิน\n\nร้านข้าวแกงบ้านสวน สาขาสีลม\n\n| รายการ | จำนวน | ราคา |\n| --- | --- | --- |\n| ข้าวแกงเขียวหวานไก่ | 1 | 60 |\n| น้ำเปล่า | 1 | 10 |\n\nรวมทั้งสิ้น 70 บาท"
    }
  ],
  "usage": {
    "pages": 1,
    "credits": 6.5
  }
}

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\"}"

{
  "pages": [
    {
      "page": 1,
      "blocks": [
        {
          "type": "heading",
          "level": 1,
          "text": "ใบเสร็จรับเงิน"
        },
        {
          "type": "paragraph",
          "text": "ร้านข้าวแกงบ้านสวน สาขาสีลม"
        },
        {
          "type": "table",
          "rows": [
            [
              "รายการ",
              "จำนวน",
              "ราคา"
            ],
            [
              "ข้าวแกงเขียวหวานไก่",
              "1",
              "60"
            ],
            [
              "น้ำเปล่า",
              "1",
              "10"
            ]
          ]
        },
        {
          "type": "paragraph",
          "text": "รวมทั้งสิ้น 70 บาท"
        }
      ]
    }
  ],
  "usage": {
    "pages": 1,
    "credits": 6.5
  }
}