Create File

POST

apps

{app_id}

files

Create File

curl --request POST \
  --url https://api.example.com/apps/{app_id}/files \
  --header 'Content-Type: application/json' \
  --data '
{
  "file": "<string>",
  "file_url": "https://example.com/files/document.pdf",
  "allowed_types": [
    "*/*"
  ],
  "document_extract_contents": false,
  "document_extract_images": false,
  "document_extract_pages": false,
  "document_pages": [
    1,
    2,
    3
  ],
  "document_max_pages": 10,
  "storage": "PERSISTENT",
  "visibility": "PRIVATE",
  "bucket": "cortex-eu",
  "region": "cortex-eu"
}
'

import requests

url = "https://api.example.com/apps/{app_id}/files"

payload = {
    "file": "<string>",
    "file_url": "https://example.com/files/document.pdf",
    "allowed_types": ["*/*"],
    "document_extract_contents": False,
    "document_extract_images": False,
    "document_extract_pages": False,
    "document_pages": [1, 2, 3],
    "document_max_pages": 10,
    "storage": "PERSISTENT",
    "visibility": "PRIVATE",
    "bucket": "cortex-eu",
    "region": "cortex-eu"
}
headers = {"Content-Type": "application/json"}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {'Content-Type': 'application/json'},
  body: JSON.stringify({
    file: '<string>',
    file_url: 'https://example.com/files/document.pdf',
    allowed_types: ['*/*'],
    document_extract_contents: false,
    document_extract_images: false,
    document_extract_pages: false,
    document_pages: [1, 2, 3],
    document_max_pages: 10,
    storage: 'PERSISTENT',
    visibility: 'PRIVATE',
    bucket: 'cortex-eu',
    region: 'cortex-eu'
  })
};

fetch('https://api.example.com/apps/{app_id}/files', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.example.com/apps/{app_id}/files",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'file' => '<string>',
    'file_url' => 'https://example.com/files/document.pdf',
    'allowed_types' => [
        '*/*'
    ],
    'document_extract_contents' => false,
    'document_extract_images' => false,
    'document_extract_pages' => false,
    'document_pages' => [
        1,
        2,
        3
    ],
    'document_max_pages' => 10,
    'storage' => 'PERSISTENT',
    'visibility' => 'PRIVATE',
    'bucket' => 'cortex-eu',
    'region' => 'cortex-eu'
  ]),
  CURLOPT_HTTPHEADER => [
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.example.com/apps/{app_id}/files"

	payload := strings.NewReader("{\n  \"file\": \"<string>\",\n  \"file_url\": \"https://example.com/files/document.pdf\",\n  \"allowed_types\": [\n    \"*/*\"\n  ],\n  \"document_extract_contents\": false,\n  \"document_extract_images\": false,\n  \"document_extract_pages\": false,\n  \"document_pages\": [\n    1,\n    2,\n    3\n  ],\n  \"document_max_pages\": 10,\n  \"storage\": \"PERSISTENT\",\n  \"visibility\": \"PRIVATE\",\n  \"bucket\": \"cortex-eu\",\n  \"region\": \"cortex-eu\"\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.example.com/apps/{app_id}/files")
  .header("Content-Type", "application/json")
  .body("{\n  \"file\": \"<string>\",\n  \"file_url\": \"https://example.com/files/document.pdf\",\n  \"allowed_types\": [\n    \"*/*\"\n  ],\n  \"document_extract_contents\": false,\n  \"document_extract_images\": false,\n  \"document_extract_pages\": false,\n  \"document_pages\": [\n    1,\n    2,\n    3\n  ],\n  \"document_max_pages\": 10,\n  \"storage\": \"PERSISTENT\",\n  \"visibility\": \"PRIVATE\",\n  \"bucket\": \"cortex-eu\",\n  \"region\": \"cortex-eu\"\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.example.com/apps/{app_id}/files")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Content-Type"] = 'application/json'
request.body = "{\n  \"file\": \"<string>\",\n  \"file_url\": \"https://example.com/files/document.pdf\",\n  \"allowed_types\": [\n    \"*/*\"\n  ],\n  \"document_extract_contents\": false,\n  \"document_extract_images\": false,\n  \"document_extract_pages\": false,\n  \"document_pages\": [\n    1,\n    2,\n    3\n  ],\n  \"document_max_pages\": 10,\n  \"storage\": \"PERSISTENT\",\n  \"visibility\": \"PRIVATE\",\n  \"bucket\": \"cortex-eu\",\n  \"region\": \"cortex-eu\"\n}"

response = http.request(request)
puts response.read_body

{
  "id": "<string>",
  "file_id": "<string>",
  "file_filename": "document.pdf",
  "file_size": 1024,
  "file_mimetype": "application/pdf",
  "file_url": "<string>",
  "created_at": "2023-12-25",
  "file_format": "DOCUMENT",
  "file_status": "PROCESSED",
  "file_status_message": "<string>",
  "document": {
    "filename": "<string>",
    "filetype": "<string>",
    "contents": [
      {
        "id": 123,
        "content": "<string>",
        "page": 123,
        "content_as_html": "<string>",
        "parent": 123
      }
    ],
    "images": [
      {
        "id": "<string>",
        "file_id": "<string>",
        "image_url": "<string>",
        "type": "<string>",
        "page": 123,
        "height": 123,
        "width": 123
      }
    ],
    "extracted_pages": "<string>",
    "time": 123
  },
  "document_extract_contents": true,
  "document_extract_images": true,
  "document_extract_pages": true,
  "document_pages": [
    1,
    2,
    3
  ],
  "document_progress": 123,
  "storage": "PERSISTENT"
}

Path Parameters

app_id

string

required

The ID of the app

Query Parameters

bucket

string

Optional bucket name for storage operations

Example:

"cortex-eu"

Body

File data and options for upload

file

File to be uploaded. It can be a file object, a base64 encoded string, or a file data object containing base64 data, name, and type.

file_url

string

URL of the file to be uploaded

Example:

"https://example.com/files/document.pdf"

allowed_types

string[] | null

The allowed mime types for the file field (e.g. image/*, application/pdf)

Maximum array length: 255

Maximum string length: 255

document_extract_contents

boolean

Flag indicating whether to extract contents from the document

Example:

false

document_extract_images

boolean

Flag indicating whether to extract images from the document

Example:

false

document_extract_pages

boolean

Flag indicating whether to extract pages from the document

Example:

false

document_pages

number[]

Array of page numbers to extract from the document

Maximum array length: 1024

Example:

[1, 2, 3]

document_max_pages

number

Maximum number of pages to extract from the document

Required range: x >= 1

Example:

10

storage

enum<string>

default:PERSISTENT

Whether the file is stored permanently or temporarily, indicating the storage type

Available options:

PERSISTENT,

TEMPORARY

Example:

"PERSISTENT"

visibility

enum<string>

Whether the file is private or public, private files URLs are signed with a token and can be accessed temporarily

Available options:

PUBLIC,

PRIVATE

Example:

"PRIVATE"

bucket

string

Storage bucket for the file

Example:

"cortex-eu"

region

string

Region on R2/cloudflare

Example:

"cortex-eu"

Response

200 - application/json

Detailed information about a file

string

required

Unique identifier for the file

file_id

string

required

File identifier used in the storage system

file_filename

string

required

Name of the file

Example:

"document.pdf"

file_size

number

required

Size of the file in bytes

Example:

1024

file_mimetype

string

required

MIME type of the file

Example:

"application/pdf"

file_url

string

required

URL to access the file

created_at

string<date> | null

required

Timestamp when the file was created

file_format

enum<string>

Format of the file

Available options:

DOCUMENT

Example:

"DOCUMENT"

file_status

enum<string>

Current status of the file

Available options:

PROCESSING,

PROCESSED,

FAILED

Example:

"PROCESSED"

file_status_message

string

Status message providing additional information about the file status

document

object

Document data associated with the file

Show child attributes

document_extract_contents

boolean

Flag indicating whether to extract contents from the document

document_extract_images

boolean

Flag indicating whether to extract images from the document

document_extract_pages

boolean

Flag indicating whether to extract pages from the document

document_pages

number[]

Array of page numbers to extract from the document

Maximum array length: 1024

Example:

[1, 2, 3]

document_progress

number

Progress of the document extraction process

storage

enum<string>

default:PERSISTENT

Whether the file is stored permanently or temporarily, indicating the storage type

Available options:

PERSISTENT,

TEMPORARY

Example:

"PERSISTENT"

Get FileRetrieve details of a specific file.

Create File

curl --request POST \
  --url https://api.example.com/apps/{app_id}/files \
  --header 'Content-Type: application/json' \
  --data '
{
  "file": "<string>",
  "file_url": "https://example.com/files/document.pdf",
  "allowed_types": [
    "*/*"
  ],
  "document_extract_contents": false,
  "document_extract_images": false,
  "document_extract_pages": false,
  "document_pages": [
    1,
    2,
    3
  ],
  "document_max_pages": 10,
  "storage": "PERSISTENT",
  "visibility": "PRIVATE",
  "bucket": "cortex-eu",
  "region": "cortex-eu"
}
'

import requests

url = "https://api.example.com/apps/{app_id}/files"

payload = {
    "file": "<string>",
    "file_url": "https://example.com/files/document.pdf",
    "allowed_types": ["*/*"],
    "document_extract_contents": False,
    "document_extract_images": False,
    "document_extract_pages": False,
    "document_pages": [1, 2, 3],
    "document_max_pages": 10,
    "storage": "PERSISTENT",
    "visibility": "PRIVATE",
    "bucket": "cortex-eu",
    "region": "cortex-eu"
}
headers = {"Content-Type": "application/json"}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {'Content-Type': 'application/json'},
  body: JSON.stringify({
    file: '<string>',
    file_url: 'https://example.com/files/document.pdf',
    allowed_types: ['*/*'],
    document_extract_contents: false,
    document_extract_images: false,
    document_extract_pages: false,
    document_pages: [1, 2, 3],
    document_max_pages: 10,
    storage: 'PERSISTENT',
    visibility: 'PRIVATE',
    bucket: 'cortex-eu',
    region: 'cortex-eu'
  })
};

fetch('https://api.example.com/apps/{app_id}/files', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.example.com/apps/{app_id}/files",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'file' => '<string>',
    'file_url' => 'https://example.com/files/document.pdf',
    'allowed_types' => [
        '*/*'
    ],
    'document_extract_contents' => false,
    'document_extract_images' => false,
    'document_extract_pages' => false,
    'document_pages' => [
        1,
        2,
        3
    ],
    'document_max_pages' => 10,
    'storage' => 'PERSISTENT',
    'visibility' => 'PRIVATE',
    'bucket' => 'cortex-eu',
    'region' => 'cortex-eu'
  ]),
  CURLOPT_HTTPHEADER => [
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.example.com/apps/{app_id}/files"

	payload := strings.NewReader("{\n  \"file\": \"<string>\",\n  \"file_url\": \"https://example.com/files/document.pdf\",\n  \"allowed_types\": [\n    \"*/*\"\n  ],\n  \"document_extract_contents\": false,\n  \"document_extract_images\": false,\n  \"document_extract_pages\": false,\n  \"document_pages\": [\n    1,\n    2,\n    3\n  ],\n  \"document_max_pages\": 10,\n  \"storage\": \"PERSISTENT\",\n  \"visibility\": \"PRIVATE\",\n  \"bucket\": \"cortex-eu\",\n  \"region\": \"cortex-eu\"\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.example.com/apps/{app_id}/files")
  .header("Content-Type", "application/json")
  .body("{\n  \"file\": \"<string>\",\n  \"file_url\": \"https://example.com/files/document.pdf\",\n  \"allowed_types\": [\n    \"*/*\"\n  ],\n  \"document_extract_contents\": false,\n  \"document_extract_images\": false,\n  \"document_extract_pages\": false,\n  \"document_pages\": [\n    1,\n    2,\n    3\n  ],\n  \"document_max_pages\": 10,\n  \"storage\": \"PERSISTENT\",\n  \"visibility\": \"PRIVATE\",\n  \"bucket\": \"cortex-eu\",\n  \"region\": \"cortex-eu\"\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.example.com/apps/{app_id}/files")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Content-Type"] = 'application/json'
request.body = "{\n  \"file\": \"<string>\",\n  \"file_url\": \"https://example.com/files/document.pdf\",\n  \"allowed_types\": [\n    \"*/*\"\n  ],\n  \"document_extract_contents\": false,\n  \"document_extract_images\": false,\n  \"document_extract_pages\": false,\n  \"document_pages\": [\n    1,\n    2,\n    3\n  ],\n  \"document_max_pages\": 10,\n  \"storage\": \"PERSISTENT\",\n  \"visibility\": \"PRIVATE\",\n  \"bucket\": \"cortex-eu\",\n  \"region\": \"cortex-eu\"\n}"

response = http.request(request)
puts response.read_body

{
  "id": "<string>",
  "file_id": "<string>",
  "file_filename": "document.pdf",
  "file_size": 1024,
  "file_mimetype": "application/pdf",
  "file_url": "<string>",
  "created_at": "2023-12-25",
  "file_format": "DOCUMENT",
  "file_status": "PROCESSED",
  "file_status_message": "<string>",
  "document": {
    "filename": "<string>",
    "filetype": "<string>",
    "contents": [
      {
        "id": 123,
        "content": "<string>",
        "page": 123,
        "content_as_html": "<string>",
        "parent": 123
      }
    ],
    "images": [
      {
        "id": "<string>",
        "file_id": "<string>",
        "image_url": "<string>",
        "type": "<string>",
        "page": 123,
        "height": 123,
        "width": 123
      }
    ],
    "extracted_pages": "<string>",
    "time": 123
  },
  "document_extract_contents": true,
  "document_extract_images": true,
  "document_extract_pages": true,
  "document_pages": [
    1,
    2,
    3
  ],
  "document_progress": 123,
  "storage": "PERSISTENT"
}

Getting Started

Collections

Records

Workflows

Tests

Variables

Files

Webhooks

Path Parameters

Query Parameters

Body

Response