Extract structured data from a document

curl --request POST \
  --url https://api.lighton.ai/api/v3/extract \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: multipart/form-data' \
  --form 'file=(binary)' \
  --form 'schema={
  "type": "object",
  "properties": {
    "invoice_number": {
      "type": "string"
    }
  }
}'

import requests

url = "https://api.lighton.ai/api/v3/extract"

payload = "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"\r\n\r\n(binary)\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"schema\"\r\n\r\n{\r\n  \"type\": \"object\",\r\n  \"properties\": {\r\n    \"invoice_number\": {\r\n      \"type\": \"string\"\r\n    }\r\n  }\r\n}\r\n-----011000010111000001101001--"
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "multipart/form-data"
}

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

print(response.text)

const form = new FormData();
form.append('file', '(binary)');
form.append('schema', '{
  "type": "object",
  "properties": {
    "invoice_number": {
      "type": "string"
    }
  }
}');

const options = {method: 'POST', headers: {Authorization: 'Bearer <token>'}};

options.body = form;

fetch('https://api.lighton.ai/api/v3/extract', 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.lighton.ai/api/v3/extract",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"\r\n\r\n(binary)\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"schema\"\r\n\r\n{\r\n  \"type\": \"object\",\r\n  \"properties\": {\r\n    \"invoice_number\": {\r\n      \"type\": \"string\"\r\n    }\r\n  }\r\n}\r\n-----011000010111000001101001--",
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: multipart/form-data"
  ],
]);

$response = curl_exec($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.lighton.ai/api/v3/extract"

	payload := strings.NewReader("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"\r\n\r\n(binary)\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"schema\"\r\n\r\n{\r\n  \"type\": \"object\",\r\n  \"properties\": {\r\n    \"invoice_number\": {\r\n      \"type\": \"string\"\r\n    }\r\n  }\r\n}\r\n-----011000010111000001101001--")

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

	req.Header.Add("Authorization", "Bearer <token>")

	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.lighton.ai/api/v3/extract")
  .header("Authorization", "Bearer <token>")
  .body("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"\r\n\r\n(binary)\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"schema\"\r\n\r\n{\r\n  \"type\": \"object\",\r\n  \"properties\": {\r\n    \"invoice_number\": {\r\n      \"type\": \"string\"\r\n    }\r\n  }\r\n}\r\n-----011000010111000001101001--")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.lighton.ai/api/v3/extract")

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request.body = "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"\r\n\r\n(binary)\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"schema\"\r\n\r\n{\r\n  \"type\": \"object\",\r\n  \"properties\": {\r\n    \"invoice_number\": {\r\n      \"type\": \"string\"\r\n    }\r\n  }\r\n}\r\n-----011000010111000001101001--"

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

{
  "id": "ext_0196e4b2a3c14d5e8f7a9b2c1d0e3f4a",
  "status": "completed",
  "created_at": "2026-03-31T10:00:00+00:00",
  "completed_at": "2026-03-31T10:00:04+00:00",
  "processing_time_ms": 3200,
  "document": {
    "filename": "invoice.pdf",
    "page_count": 3,
    "file_size_bytes": 245120,
    "mime_type": "application/pdf"
  },
  "result": {
    "data": [
      {
        "invoice_number": "INV-2026-001",
        "total": null,
        "line_items": null
      },
      {
        "invoice_number": null,
        "total": 1250,
        "line_items": [
          {
            "description": "Widget A",
            "quantity": 10,
            "unit_price": 50
          },
          {
            "description": "Widget B",
            "quantity": 5,
            "unit_price": 150
          }
        ]
      },
      {
        "invoice_number": null,
        "total": null,
        "line_items": null
      }
    ],
    "pagination": {
      "page": 1,
      "page_size": 15,
      "total_items": 3,
      "total_pages": 1,
      "has_next": false,
      "has_prev": false
    }
  },
  "usage": {
    "pages_processed": 3
  },
  "progress": {
    "percentage": 100,
    "pages_processed": 3
  }
}

Extract

Extract structured data from a document

Pull specific fields from a document into a typed schema.

Accepts exactly one of: a file upload (multipart/form-data), a document URL (JSON body), or a file_id referencing an already-ingested document (from POST /v3/files), plus a JSON Schema (the schema field) describing what to extract.

Sync mode (default)

Blocks until extraction completes and returns 200 with the full result.

curl -X POST https://api.lighton.ai/api/v3/extract \
  -H 'Authorization: Bearer $TOKEN' \
  -F file=@invoice.pdf \
  -F 'schema={"type":"object","properties":{"invoice_number":{"type":"string"}}}'

Async mode (`options.async = true`)

Returns 202 immediately with an ext_<token> job id. Poll GET /api/v3/extract/{id} with that same id until status is completed or failed.

curl -X POST https://api.lighton.ai/api/v3/extract \
  -H 'Authorization: Bearer $TOKEN' \
  -H 'Content-Type: application/json' \
  -d '{"document": "https://example.com/report.pdf", "schema": {"type": "object", "properties": {"title": {"type": "string"}}}, "options": {"async": true}}'

For multipart uploads, pass options as a JSON-encoded form field: -F 'options={"async":true}'.

Supported file types: .pdf, .png, .jpg, .jpeg, .pptx, .ppt, .odp, .docx, .odt, .doc, .html

Sync limits: 20 MB file size, 15 pages.

Async limits: 100 MB file size, 1000 pages.

POST

api

extract

Extract structured data from a document

curl --request POST \
  --url https://api.lighton.ai/api/v3/extract \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: multipart/form-data' \
  --form 'file=(binary)' \
  --form 'schema={
  "type": "object",
  "properties": {
    "invoice_number": {
      "type": "string"
    }
  }
}'

import requests

url = "https://api.lighton.ai/api/v3/extract"

payload = "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"\r\n\r\n(binary)\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"schema\"\r\n\r\n{\r\n  \"type\": \"object\",\r\n  \"properties\": {\r\n    \"invoice_number\": {\r\n      \"type\": \"string\"\r\n    }\r\n  }\r\n}\r\n-----011000010111000001101001--"
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "multipart/form-data"
}

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

print(response.text)

const form = new FormData();
form.append('file', '(binary)');
form.append('schema', '{
  "type": "object",
  "properties": {
    "invoice_number": {
      "type": "string"
    }
  }
}');

const options = {method: 'POST', headers: {Authorization: 'Bearer <token>'}};

options.body = form;

fetch('https://api.lighton.ai/api/v3/extract', 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.lighton.ai/api/v3/extract",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"\r\n\r\n(binary)\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"schema\"\r\n\r\n{\r\n  \"type\": \"object\",\r\n  \"properties\": {\r\n    \"invoice_number\": {\r\n      \"type\": \"string\"\r\n    }\r\n  }\r\n}\r\n-----011000010111000001101001--",
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: multipart/form-data"
  ],
]);

$response = curl_exec($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.lighton.ai/api/v3/extract"

	payload := strings.NewReader("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"\r\n\r\n(binary)\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"schema\"\r\n\r\n{\r\n  \"type\": \"object\",\r\n  \"properties\": {\r\n    \"invoice_number\": {\r\n      \"type\": \"string\"\r\n    }\r\n  }\r\n}\r\n-----011000010111000001101001--")

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

	req.Header.Add("Authorization", "Bearer <token>")

	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.lighton.ai/api/v3/extract")
  .header("Authorization", "Bearer <token>")
  .body("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"\r\n\r\n(binary)\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"schema\"\r\n\r\n{\r\n  \"type\": \"object\",\r\n  \"properties\": {\r\n    \"invoice_number\": {\r\n      \"type\": \"string\"\r\n    }\r\n  }\r\n}\r\n-----011000010111000001101001--")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.lighton.ai/api/v3/extract")

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request.body = "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"\r\n\r\n(binary)\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"schema\"\r\n\r\n{\r\n  \"type\": \"object\",\r\n  \"properties\": {\r\n    \"invoice_number\": {\r\n      \"type\": \"string\"\r\n    }\r\n  }\r\n}\r\n-----011000010111000001101001--"

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

{
  "id": "ext_0196e4b2a3c14d5e8f7a9b2c1d0e3f4a",
  "status": "completed",
  "created_at": "2026-03-31T10:00:00+00:00",
  "completed_at": "2026-03-31T10:00:04+00:00",
  "processing_time_ms": 3200,
  "document": {
    "filename": "invoice.pdf",
    "page_count": 3,
    "file_size_bytes": 245120,
    "mime_type": "application/pdf"
  },
  "result": {
    "data": [
      {
        "invoice_number": "INV-2026-001",
        "total": null,
        "line_items": null
      },
      {
        "invoice_number": null,
        "total": 1250,
        "line_items": [
          {
            "description": "Widget A",
            "quantity": 10,
            "unit_price": 50
          },
          {
            "description": "Widget B",
            "quantity": 5,
            "unit_price": 150
          }
        ]
      },
      {
        "invoice_number": null,
        "total": null,
        "line_items": null
      }
    ],
    "pagination": {
      "page": 1,
      "page_size": 15,
      "total_items": 3,
      "total_pages": 1,
      "has_next": false,
      "has_prev": false
    }
  },
  "usage": {
    "pages_processed": 3
  },
  "progress": {
    "percentage": 100,
    "pages_processed": 3
  }
}

Authorizations

Authorization

string

header

required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

Body for POST /api/v3/extract.

schema is the JSON Schema that drives extraction. It arrives as a dict on JSON requests and as a JSON-encoded string on multipart requests — both are coerced to dict.

options is a free-form dict; currently supports {"async": bool}.

schema

Schema · object

required

document

string | null

file_id

integer | null

options

Options · object

Response

Extraction completed (sync mode).

string

required

status

string

required

created_at

string<date-time> | null

completed_at

string<date-time> | null

processing_time_ms

integer | null

document

ExtractDocument · object | null

Show child attributes

result

ExtractResult · object | null

Show child attributes

usage

ExtractUsage · object | null

Show child attributes

progress

JobProgress · object | null

Live progress of a long-running async job while it is in flight.

Shared by the parse (GET /api/v3/parse/<id>) and extract (GET /api/v3/extract/<id>) polling envelopes: pages_processed is the count of pages done so far and percentage is the completion percentage [0, 100] derived from it.

Show child attributes

⌘I

Overview

Intelligence

Document Processing

Administration

Extract structured data from a document

Sync mode (default)

Async mode (`options.async = true`)

Authorizations

Body

Response