Get Extract Task

curl --request GET \
  --url https://api.chunkr.ai/tasks/{task_id}/extract \
  --header 'Authorization: <api-key>'

import requests

url = "https://api.chunkr.ai/tasks/{task_id}/extract"

headers = {"Authorization": "<api-key>"}

response = requests.get(url, headers=headers)

print(response.text)

const options = {method: 'GET', headers: {Authorization: '<api-key>'}};

fetch('https://api.chunkr.ai/tasks/{task_id}/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.chunkr.ai/tasks/{task_id}/extract",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "GET",
  CURLOPT_HTTPHEADER => [
    "Authorization: <api-key>"
  ],
]);

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

curl_close($curl);

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

package main

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

func main() {

	url := "https://api.chunkr.ai/tasks/{task_id}/extract"

	req, _ := http.NewRequest("GET", url, nil)

	req.Header.Add("Authorization", "<api-key>")

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

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

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.get("https://api.chunkr.ai/tasks/{task_id}/extract")
  .header("Authorization", "<api-key>")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.chunkr.ai/tasks/{task_id}/extract")

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

request = Net::HTTP::Get.new(url)
request["Authorization"] = '<api-key>'

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

{
  "completed": true,
  "configuration": {
    "schema": {},
    "parse_configuration": {
      "chunk_processing": {
        "ignore_headers_and_footers": null,
        "target_length": 4096,
        "tokenizer": {
          "Enum": "Word"
        }
      },
      "error_handling": "Fail",
      "ocr_strategy": "All",
      "pipeline": "Chunkr",
      "segment_processing": {
        "Caption": {
          "description": null,
          "extended_context": null,
          "llm": "<string>"
        },
        "Footnote": {
          "description": null,
          "extended_context": null,
          "llm": "<string>"
        },
        "FormRegion": {
          "description": null,
          "extended_context": null,
          "llm": "<string>"
        },
        "Formula": {
          "description": null,
          "extended_context": null,
          "llm": "<string>"
        },
        "GraphicalItem": {
          "description": null,
          "extended_context": null,
          "llm": "<string>"
        },
        "Legend": {
          "description": null,
          "extended_context": null,
          "llm": "<string>"
        },
        "LineNumber": {
          "description": null,
          "extended_context": null,
          "llm": "<string>"
        },
        "ListItem": {
          "description": null,
          "extended_context": null,
          "llm": "<string>"
        },
        "Page": {
          "description": null,
          "extended_context": null,
          "llm": "<string>"
        },
        "PageFooter": {
          "description": null,
          "extended_context": null,
          "llm": "<string>"
        },
        "PageHeader": {
          "description": null,
          "extended_context": null,
          "llm": "<string>"
        },
        "PageNumber": {
          "description": null,
          "extended_context": null,
          "llm": "<string>"
        },
        "Picture": {
          "description": null,
          "extended_context": null,
          "llm": "<string>"
        },
        "Table": {
          "description": null,
          "extended_context": null,
          "llm": "<string>"
        },
        "Text": {
          "description": null,
          "extended_context": null,
          "llm": "<string>"
        },
        "Title": {
          "description": null,
          "extended_context": null,
          "llm": "<string>"
        },
        "Unknown": {
          "description": null,
          "extended_context": null,
          "llm": "<string>"
        }
      },
      "segmentation_strategy": "LayoutAnalysis"
    },
    "system_prompt": "You are an expert at structured data extraction. You will be given parsed text from a document and should convert it into the given structure."
  },
  "created_at": "2023-11-07T05:31:56Z",
  "file_info": {
    "url": "<string>",
    "mime_type": "<string>",
    "name": "<string>",
    "page_count": 1,
    "ss_cell_count": 1
  },
  "message": "<string>",
  "task_id": "<string>",
  "version_info": {
    "client_version": "Legacy",
    "server_version": "<string>"
  },
  "expires_at": "2023-11-07T05:31:56Z",
  "finished_at": "2023-11-07T05:31:56Z",
  "input_file_url": "<string>",
  "output": {
    "citations": "<unknown>",
    "metrics": "<unknown>",
    "results": "<unknown>"
  },
  "parse_task_id": "<string>",
  "started_at": "2023-11-07T05:31:56Z",
  "task_url": "<string>"
}

"<string>"

"<string>"

"<string>"

"<string>"

GET

tasks

{task_id}

extract

Get Extract Task

curl --request GET \
  --url https://api.chunkr.ai/tasks/{task_id}/extract \
  --header 'Authorization: <api-key>'

import requests

url = "https://api.chunkr.ai/tasks/{task_id}/extract"

headers = {"Authorization": "<api-key>"}

response = requests.get(url, headers=headers)

print(response.text)

const options = {method: 'GET', headers: {Authorization: '<api-key>'}};

fetch('https://api.chunkr.ai/tasks/{task_id}/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.chunkr.ai/tasks/{task_id}/extract",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "GET",
  CURLOPT_HTTPHEADER => [
    "Authorization: <api-key>"
  ],
]);

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

curl_close($curl);

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

package main

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

func main() {

	url := "https://api.chunkr.ai/tasks/{task_id}/extract"

	req, _ := http.NewRequest("GET", url, nil)

	req.Header.Add("Authorization", "<api-key>")

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

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

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.get("https://api.chunkr.ai/tasks/{task_id}/extract")
  .header("Authorization", "<api-key>")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.chunkr.ai/tasks/{task_id}/extract")

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

request = Net::HTTP::Get.new(url)
request["Authorization"] = '<api-key>'

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

{
  "completed": true,
  "configuration": {
    "schema": {},
    "parse_configuration": {
      "chunk_processing": {
        "ignore_headers_and_footers": null,
        "target_length": 4096,
        "tokenizer": {
          "Enum": "Word"
        }
      },
      "error_handling": "Fail",
      "ocr_strategy": "All",
      "pipeline": "Chunkr",
      "segment_processing": {
        "Caption": {
          "description": null,
          "extended_context": null,
          "llm": "<string>"
        },
        "Footnote": {
          "description": null,
          "extended_context": null,
          "llm": "<string>"
        },
        "FormRegion": {
          "description": null,
          "extended_context": null,
          "llm": "<string>"
        },
        "Formula": {
          "description": null,
          "extended_context": null,
          "llm": "<string>"
        },
        "GraphicalItem": {
          "description": null,
          "extended_context": null,
          "llm": "<string>"
        },
        "Legend": {
          "description": null,
          "extended_context": null,
          "llm": "<string>"
        },
        "LineNumber": {
          "description": null,
          "extended_context": null,
          "llm": "<string>"
        },
        "ListItem": {
          "description": null,
          "extended_context": null,
          "llm": "<string>"
        },
        "Page": {
          "description": null,
          "extended_context": null,
          "llm": "<string>"
        },
        "PageFooter": {
          "description": null,
          "extended_context": null,
          "llm": "<string>"
        },
        "PageHeader": {
          "description": null,
          "extended_context": null,
          "llm": "<string>"
        },
        "PageNumber": {
          "description": null,
          "extended_context": null,
          "llm": "<string>"
        },
        "Picture": {
          "description": null,
          "extended_context": null,
          "llm": "<string>"
        },
        "Table": {
          "description": null,
          "extended_context": null,
          "llm": "<string>"
        },
        "Text": {
          "description": null,
          "extended_context": null,
          "llm": "<string>"
        },
        "Title": {
          "description": null,
          "extended_context": null,
          "llm": "<string>"
        },
        "Unknown": {
          "description": null,
          "extended_context": null,
          "llm": "<string>"
        }
      },
      "segmentation_strategy": "LayoutAnalysis"
    },
    "system_prompt": "You are an expert at structured data extraction. You will be given parsed text from a document and should convert it into the given structure."
  },
  "created_at": "2023-11-07T05:31:56Z",
  "file_info": {
    "url": "<string>",
    "mime_type": "<string>",
    "name": "<string>",
    "page_count": 1,
    "ss_cell_count": 1
  },
  "message": "<string>",
  "task_id": "<string>",
  "version_info": {
    "client_version": "Legacy",
    "server_version": "<string>"
  },
  "expires_at": "2023-11-07T05:31:56Z",
  "finished_at": "2023-11-07T05:31:56Z",
  "input_file_url": "<string>",
  "output": {
    "citations": "<unknown>",
    "metrics": "<unknown>",
    "results": "<unknown>"
  },
  "parse_task_id": "<string>",
  "started_at": "2023-11-07T05:31:56Z",
  "task_url": "<string>"
}

"<string>"

"<string>"

"<string>"

"<string>"

Authorizations

Authorization

string

header

required

Path Parameters

task_id

string | null

required

Id of the task to retrieve

Query Parameters

base64_urls

boolean

Whether to return base64 encoded URLs. If false, the URLs will be returned as presigned URLs.

include_chunks

boolean

Whether to include chunks in the output response

Response

Task details.

completed

boolean

required

True when the task reaches a terminal state i.e. status is Succeeded or Failed or Cancelled

configuration

Extract · object

required

Show child attributes

created_at

string<date-time>

required

The date and time when the task was created and queued.

file_info

object

required

Information about the input file.

Show child attributes

message

string

required

A message describing the task's status or any errors that occurred.

status

enum<string>

required

The status of the task.

Available options:

Starting,

Processing,

Succeeded,

Failed,

Cancelled

task_id

string

required

The unique identifier for the task.

task_type

enum<string>

required

Available options:

Parse,

Extract

version_info

object

required

Version information for the task.

Show child attributes

expires_at

string<date-time> | null

The date and time when the task will expire.

finished_at

string<date-time> | null

The date and time when the task was finished.

input_file_url

string | null

deprecated

The presigned URL of the input file. Deprecated use file_info.url instead.

output

null | Extract · object

The processed results of a document extraction task.

Shapes:

results: JSON matching the user-provided schema.
citations: mirror of results; only leaf positions (primitive or array-of-primitives) contain a Vec<Citation> supporting that field.
metrics: mirror of results; only leaf positions contain a Metrics object for that field.

Show child attributes

parse_task_id

string | null

The ID of the source parse task that was used for extraction

started_at

string<date-time> | null

The date and time when the task was started.

task_url

string | null

The presigned URL of the task.

Cancel Task Get Parse Task

Extras

Files

Health

Tasks

Webhook

API Reference

Get Extract Task

Authorizations

Path Parameters

Query Parameters

Response