OCR ภาษาไทยสำหรับคลังความรู้และการนำเอกสารเข้าระบบ

# 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 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")