Document OCR

import requests
import base64
import os

url = "https://api.neosantara.xyz/v1/ocr"
headers = {
    "Authorization": f"Bearer {os.environ['NEOSANTARA_API_KEY']}",
    "Content-Type": "application/json"
}

with open("invoice.png", "rb") as f:
    encoded_image = base64.b64encode(f.read()).decode("utf-8")

payload = {
    "model": "deepseek-ocr",
    "image": encoded_image,
    "image_type": "base64",
    "prompt": "Extract all line items into a Markdown table."
}

response = requests.post(url, headers=headers, json=payload)
data = response.json()
print(data.get("extracted_text"))

curl -X POST https://api.neosantara.xyz/v1/ocr \
  -H "Authorization: Bearer $NEOSANTARA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-ocr",
    "image": "https://example.com/invoice.jpg",
    "image_type": "url"
  }'