Create Document

To create a new Document send POST request with body containing a JSON hash of the required fields. The file content must be encoded as url safe base64 string (Base64URL in validator https://base64.guru/tools/validator). Online Base64 encoder https://www.base64encode.org/

POST/api/v1_2/documents

Only one file per document is allowed, but you can create multiple documents in one request or post files in compressed archive.

In case of multipage file with enabled split max 200 pages are allowed.

For each new created document is returned document id. All created documents are automatically queued for processing.

Big files (big request bodies) can lead to timeouts or unreasonable response times. Rule of thumb is to keep the size of uploaded data under 20MB.

Supported file formats:

Format Description

PDF Containing text or scanned documents

single page PDF document, multipage PDF document, multiple documents in PDF

TIFF, JPEG, PNG image, color/grayscale/b&w

ZIP containing file formats see above

RAR containing file formats see above

7ZIP containing file formats see above

Set content_type parameter according to HTTP header field Content-Type:

File format Content type

PDF application/pdf

JPEG image/jpeg

PNG image/png

TIFF image/tiff

ZIP application/zip

RAR application/x-rar

7ZIP application/x-7z-compressed

Please check example request body to see required structure.

Following attributes are mandatory:

Attribute Required Type, Example Description

filename true String invoice.pdf File name

content_type true String, application/pdf MIME type of document

agenda_id true String, 143 Agenda ID where document belongs to

type true String, PurchaseInvoice Type of document. Allowed values: PurchaseInvoice, SalesInvoice

content true String, JVBERi0xLjQgZGVt..(omitted)) url safe base64 encoded string of file content. File content needs to use url safe variant of base64 encoding/decoding (common pitfall).

file_split false Boolean,true true,false. In case of false automatic splitting is disabled. One file = one document. Number of pages for split is limited to 200.

Optional file duplicates check

If you add additional parameter check_file_duplicates=1 to create document url you will get response message “File duplicate” with additional meta data in case the check is positive. You can use the provided metadata either to let you user know that the file is duplicate or to obtain extracted data from original. Just be aware that there can be multiple processed docs from single upload (archives, multi page scans).

Query parameters

Name	Example	Description
`check_file_duplicates`	1	[object Object]

Headers

Name	Example	Description
`Accept-Encoding`	application/json	—
`Content-Type`	application/json	—

Request body

{
  "documents": [
    {
      "files": [
        {
          "filename": "demo-supplier-invoice.pdf",
          "content_type": "application/pdf",
          "content": "JVBERi0xLjQgZGF0YW1vbGluby1kZW1v"
        }
      ],
      "agenda_id": 12345,
      "file_split": false,
      "type": "PurchaseInvoice"
    }
  ]
}

Code examples

curl --request POST 'https://app.datamolino.com/api/v1_2/documents?check_file_duplicates=1' \
  --header 'Accept-Encoding: application/json' \
  --header 'Content-Type: application/json' \
  --header 'Authorization: Bearer demo_access_token' \
  --data '{
  "documents": [
    {
      "files": [
        {
          "filename": "demo-supplier-invoice.pdf",
          "content_type": "application/pdf",
          "content": "JVBERi0xLjQgZGF0YW1vbGluby1kZW1v"
        }
      ],
      "agenda_id": 12345,
      "file_split": false,
      "type": "PurchaseInvoice"
    }
  ]
}'

POST /api/v1_2/documents?check_file_duplicates=1 HTTP/1.1
Host: app.datamolino.com
Accept-Encoding: application/json
Content-Type: application/json
Authorization: Bearer demo_access_token

{
  "documents": [
    {
      "files": [
        {
          "filename": "demo-supplier-invoice.pdf",
          "content_type": "application/pdf",
          "content": "JVBERi0xLjQgZGF0YW1vbGluby1kZW1v"
        }
      ],
      "agenda_id": 12345,
      "file_split": false,
      "type": "PurchaseInvoice"
    }
  ]
}

const response = await fetch("https://app.datamolino.com/api/v1_2/documents?check_file_duplicates=1", {
  method: "POST",
  headers: {
    "Accept-Encoding": "application/json",
    "Content-Type": "application/json",
    "Authorization": "Bearer demo_access_token"
  },
  body: JSON.stringify({
    "documents": [
      {
        "files": [
          {
            "filename": "demo-supplier-invoice.pdf",
            "content_type": "application/pdf",
            "content": "JVBERi0xLjQgZGF0YW1vbGluby1kZW1v"
          }
        ],
        "agenda_id": 12345,
        "file_split": false,
        "type": "PurchaseInvoice"
      }
    ]
  }),
});

const data = await response.json();

import axios from "axios";

const response = await axios({
  method: "post",
  url: "https://app.datamolino.com/api/v1_2/documents?check_file_duplicates=1",
  headers: {
    "Accept-Encoding": "application/json",
    "Content-Type": "application/json",
    "Authorization": "Bearer demo_access_token"
  },
  data: {
    "documents": [
      {
        "files": [
          {
            "filename": "demo-supplier-invoice.pdf",
            "content_type": "application/pdf",
            "content": "JVBERi0xLjQgZGF0YW1vbGluby1kZW1v"
          }
        ],
        "agenda_id": 12345,
        "file_split": false,
        "type": "PurchaseInvoice"
      }
    ]
  }
});

console.log(response.data);

import requests

url = "https://app.datamolino.com/api/v1_2/documents?check_file_duplicates=1"
headers = {
  "Accept-Encoding": "application/json",
  "Content-Type": "application/json",
  "Authorization": "Bearer demo_access_token"
}
payload = {
  "documents": [
    {
      "files": [
        {
          "filename": "demo-supplier-invoice.pdf",
          "content_type": "application/pdf",
          "content": "JVBERi0xLjQgZGF0YW1vbGluby1kZW1v"
        }
      ],
      "agenda_id": 12345,
      "file_split": False,
      "type": "PurchaseInvoice"
    }
  ]
}

response = requests.request("POST", url, headers=headers, json=payload)
response.raise_for_status()
print(response.json())

require 'json'
require 'net/http'

uri = URI("https://app.datamolino.com/api/v1_2/documents?check_file_duplicates=1")
request = Net::HTTP::Post.new(uri)
request["Accept-Encoding"] = "application/json"
request["Content-Type"] = "application/json"
request["Authorization"] = "Bearer demo_access_token"
request.body = <<~JSON
{
  "documents": [
    {
      "files": [
        {
          "filename": "demo-supplier-invoice.pdf",
          "content_type": "application/pdf",
          "content": "JVBERi0xLjQgZGF0YW1vbGluby1kZW1v"
        }
      ],
      "agenda_id": 12345,
      "file_split": false,
      "type": "PurchaseInvoice"
    }
  ]
}
JSON

response = Net::HTTP.start(uri.hostname, uri.port, use_ssl: uri.scheme == "https") do |http|
  http.request(request)
end

puts JSON.parse(response.body)

# app/services/datamolino_client.rb
require 'json'
require 'net/http'

class DatamolinoClient
  BASE_URL = "https://app.datamolino.com"

  def initialize(access_token: Rails.application.credentials.dig(:datamolino, :access_token))
    @access_token = access_token
  end

  def request_create_document
    uri = URI("#{BASE_URL}/api/v1_2/documents?check_file_duplicates=1")
    request = Net::HTTP::Post.new(uri)
    request["Accept-Encoding"] = "application/json"
    request["Content-Type"] = "application/json"
    request["Authorization"] = "Bearer #{@access_token}"
    request.body = <<~JSON
      {
        "documents": [
          {
            "files": [
              {
                "filename": "demo-supplier-invoice.pdf",
                "content_type": "application/pdf",
                "content": "JVBERi0xLjQgZGF0YW1vbGluby1kZW1v"
              }
            ],
            "agenda_id": 12345,
            "file_split": false,
            "type": "PurchaseInvoice"
          }
        ]
      }
    JSON

    response = Net::HTTP.start(uri.hostname, uri.port, use_ssl: true) do |http|
      http.request(request)
    end

    JSON.parse(response.body)
  end
end

<?php

use GuzzleHttp\Client;

$client = new Client();
$response = $client->request('POST', 'https://app.datamolino.com/api/v1_2/documents?check_file_duplicates=1', [
    'headers' => json_decode('{"Accept-Encoding":"application/json","Content-Type":"application/json","Authorization":"Bearer demo_access_token"}', true),
    'json' => json_decode('{"documents":[{"files":[{"filename":"demo-supplier-invoice.pdf","content_type":"application/pdf","content":"JVBERi0xLjQgZGF0YW1vbGluby1kZW1v"}],"agenda_id":12345,"file_split":false,"type":"PurchaseInvoice"}]}', true)
]);

echo $response->getBody();

OkHttpClient client = new OkHttpClient();

RequestBody body = RequestBody.create("{\n  \"documents\": [\n    {\n      \"files\": [\n        {\n          \"filename\": \"demo-supplier-invoice.pdf\",\n          \"content_type\": \"application/pdf\",\n          \"content\": \"JVBERi0xLjQgZGF0YW1vbGluby1kZW1v\"\n        }\n      ],\n      \"agenda_id\": 12345,\n      \"file_split\": false,\n      \"type\": \"PurchaseInvoice\"\n    }\n  ]\n}", MediaType.parse("application/json"));
Request request = new Request.Builder()
    .url("https://app.datamolino.com/api/v1_2/documents?check_file_duplicates=1")
    .addHeader("Accept-Encoding", "application/json")
    .addHeader("Content-Type", "application/json")
    .addHeader("Authorization", "Bearer demo_access_token")
    .method("POST", body)
    .build();

Response response = client.newCall(request).execute();

using var client = new HttpClient();
using var request = new HttpRequestMessage(HttpMethod.Post, "https://app.datamolino.com/api/v1_2/documents?check_file_duplicates=1");
request.Headers.Add("Accept-Encoding", "application/json");
request.Headers.Add("Authorization", "Bearer demo_access_token");
request.Content = new StringContent("{\n  \"documents\": [\n    {\n      \"files\": [\n        {\n          \"filename\": \"demo-supplier-invoice.pdf\",\n          \"content_type\": \"application/pdf\",\n          \"content\": \"JVBERi0xLjQgZGF0YW1vbGluby1kZW1v\"\n        }\n      ],\n      \"agenda_id\": 12345,\n      \"file_split\": false,\n      \"type\": \"PurchaseInvoice\"\n    }\n  ]\n}", Encoding.UTF8, "application/json");

using var response = await client.SendAsync(request);
response.EnsureSuccessStatusCode();
Console.WriteLine(await response.Content.ReadAsStringAsync());

client := &http.Client{}
req, err := http.NewRequest("POST", "https://app.datamolino.com/api/v1_2/documents?check_file_duplicates=1", strings.NewReader("{\n  \"documents\": [\n    {\n      \"files\": [\n        {\n          \"filename\": \"demo-supplier-invoice.pdf\",\n          \"content_type\": \"application/pdf\",\n          \"content\": \"JVBERi0xLjQgZGF0YW1vbGluby1kZW1v\"\n        }\n      ],\n      \"agenda_id\": 12345,\n      \"file_split\": false,\n      \"type\": \"PurchaseInvoice\"\n    }\n  ]\n}"))
if err != nil { panic(err) }
req.Header.Add("Accept-Encoding", "application/json")
req.Header.Add("Content-Type", "application/json")
req.Header.Add("Authorization", "Bearer demo_access_token")

res, err := client.Do(req)
if err != nil { panic(err) }
defer res.Body.Close()

body, err := io.ReadAll(res.Body)
if err != nil { panic(err) }
fmt.Println(string(body))

import Foundation

var request = URLRequest(url: URL(string: "https://app.datamolino.com/api/v1_2/documents?check_file_duplicates=1")!)
request.httpMethod = "POST"
request.setValue("application/json", forHTTPHeaderField: "Accept-Encoding")
request.setValue("application/json", forHTTPHeaderField: "Content-Type")
request.setValue("Bearer demo_access_token", forHTTPHeaderField: "Authorization")
request.httpBody = "{\n  \"documents\": [\n    {\n      \"files\": [\n        {\n          \"filename\": \"demo-supplier-invoice.pdf\",\n          \"content_type\": \"application/pdf\",\n          \"content\": \"JVBERi0xLjQgZGF0YW1vbGluby1kZW1v\"\n        }\n      ],\n      \"agenda_id\": 12345,\n      \"file_split\": false,\n      \"type\": \"PurchaseInvoice\"\n    }\n  ]\n}".data(using: .utf8)

let (data, _) = try await URLSession.shared.data(for: request)
print(String(data: data, encoding: .utf8)!)

Query parameters

Headers

Request body

Code examples

Responses

Response Create Document - with duplicate file

Response Create Document - real pdf sample