Create Extract Task
curl --request POST \
--url https://api.chunkr.ai/tasks/extract \
--header 'Authorization: <api-key>' \
--header 'Content-Type: application/json' \
--data '
{
"schema": {},
"file": "<string>",
"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.",
"expires_in": 123,
"file_name": "<string>"
}
'import requests
url = "https://api.chunkr.ai/tasks/extract"
payload = {
"schema": {},
"file": "<string>",
"parse_configuration": {
"chunk_processing": {
"ignore_headers_and_footers": None,
"target_length": 4096,
"tokenizer": { "Enum": "Word" }
},
"error_handling": "Fail",
"ocr_strategy": "All",
"pipeline": "Chunkr",
"segment_processing": {
"Caption": {
"description": None,
"extended_context": None,
"llm": "<string>"
},
"Footnote": {
"description": None,
"extended_context": None,
"llm": "<string>"
},
"FormRegion": {
"description": None,
"extended_context": None,
"llm": "<string>"
},
"Formula": {
"description": None,
"extended_context": None,
"llm": "<string>"
},
"GraphicalItem": {
"description": None,
"extended_context": None,
"llm": "<string>"
},
"Legend": {
"description": None,
"extended_context": None,
"llm": "<string>"
},
"LineNumber": {
"description": None,
"extended_context": None,
"llm": "<string>"
},
"ListItem": {
"description": None,
"extended_context": None,
"llm": "<string>"
},
"Page": {
"description": None,
"extended_context": None,
"llm": "<string>"
},
"PageFooter": {
"description": None,
"extended_context": None,
"llm": "<string>"
},
"PageHeader": {
"description": None,
"extended_context": None,
"llm": "<string>"
},
"PageNumber": {
"description": None,
"extended_context": None,
"llm": "<string>"
},
"Picture": {
"description": None,
"extended_context": None,
"llm": "<string>"
},
"Table": {
"description": None,
"extended_context": None,
"llm": "<string>"
},
"Text": {
"description": None,
"extended_context": None,
"llm": "<string>"
},
"Title": {
"description": None,
"extended_context": None,
"llm": "<string>"
},
"Unknown": {
"description": None,
"extended_context": None,
"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.",
"expires_in": 123,
"file_name": "<string>"
}
headers = {
"Authorization": "<api-key>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {Authorization: '<api-key>', 'Content-Type': 'application/json'},
body: JSON.stringify({
schema: {},
file: '<string>',
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.',
expires_in: 123,
file_name: '<string>'
})
};
fetch('https://api.chunkr.ai/tasks/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/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 => json_encode([
'schema' => [
],
'file' => '<string>',
'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.',
'expires_in' => 123,
'file_name' => '<string>'
]),
CURLOPT_HTTPHEADER => [
"Authorization: <api-key>",
"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.chunkr.ai/tasks/extract"
payload := strings.NewReader("{\n \"schema\": {},\n \"file\": \"<string>\",\n \"parse_configuration\": {\n \"chunk_processing\": {\n \"ignore_headers_and_footers\": null,\n \"target_length\": 4096,\n \"tokenizer\": {\n \"Enum\": \"Word\"\n }\n },\n \"error_handling\": \"Fail\",\n \"ocr_strategy\": \"All\",\n \"pipeline\": \"Chunkr\",\n \"segment_processing\": {\n \"Caption\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"Footnote\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"FormRegion\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"Formula\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"GraphicalItem\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"Legend\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"LineNumber\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"ListItem\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"Page\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"PageFooter\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"PageHeader\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"PageNumber\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"Picture\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"Table\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"Text\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"Title\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"Unknown\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n }\n },\n \"segmentation_strategy\": \"LayoutAnalysis\"\n },\n \"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.\",\n \"expires_in\": 123,\n \"file_name\": \"<string>\"\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Authorization", "<api-key>")
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.chunkr.ai/tasks/extract")
.header("Authorization", "<api-key>")
.header("Content-Type", "application/json")
.body("{\n \"schema\": {},\n \"file\": \"<string>\",\n \"parse_configuration\": {\n \"chunk_processing\": {\n \"ignore_headers_and_footers\": null,\n \"target_length\": 4096,\n \"tokenizer\": {\n \"Enum\": \"Word\"\n }\n },\n \"error_handling\": \"Fail\",\n \"ocr_strategy\": \"All\",\n \"pipeline\": \"Chunkr\",\n \"segment_processing\": {\n \"Caption\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"Footnote\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"FormRegion\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"Formula\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"GraphicalItem\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"Legend\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"LineNumber\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"ListItem\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"Page\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"PageFooter\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"PageHeader\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"PageNumber\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"Picture\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"Table\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"Text\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"Title\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"Unknown\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n }\n },\n \"segmentation_strategy\": \"LayoutAnalysis\"\n },\n \"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.\",\n \"expires_in\": 123,\n \"file_name\": \"<string>\"\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.chunkr.ai/tasks/extract")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Authorization"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"schema\": {},\n \"file\": \"<string>\",\n \"parse_configuration\": {\n \"chunk_processing\": {\n \"ignore_headers_and_footers\": null,\n \"target_length\": 4096,\n \"tokenizer\": {\n \"Enum\": \"Word\"\n }\n },\n \"error_handling\": \"Fail\",\n \"ocr_strategy\": \"All\",\n \"pipeline\": \"Chunkr\",\n \"segment_processing\": {\n \"Caption\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"Footnote\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"FormRegion\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"Formula\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"GraphicalItem\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"Legend\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"LineNumber\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"ListItem\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"Page\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"PageFooter\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"PageHeader\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"PageNumber\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"Picture\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"Table\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"Text\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"Title\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"Unknown\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n }\n },\n \"segmentation_strategy\": \"LayoutAnalysis\"\n },\n \"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.\",\n \"expires_in\": 123,\n \"file_name\": \"<string>\"\n}"
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>"Tasks
Create Extract Task
Queues a document/parsed task for extraction and returns a TaskResponse with the
assigned task_id, initial configuration, file metadata, and timestamps.
The initial status is Starting.
Creates an extract task and returns its metadata immediately.
POST
/
tasks
/
extract
Create Extract Task
curl --request POST \
--url https://api.chunkr.ai/tasks/extract \
--header 'Authorization: <api-key>' \
--header 'Content-Type: application/json' \
--data '
{
"schema": {},
"file": "<string>",
"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.",
"expires_in": 123,
"file_name": "<string>"
}
'import requests
url = "https://api.chunkr.ai/tasks/extract"
payload = {
"schema": {},
"file": "<string>",
"parse_configuration": {
"chunk_processing": {
"ignore_headers_and_footers": None,
"target_length": 4096,
"tokenizer": { "Enum": "Word" }
},
"error_handling": "Fail",
"ocr_strategy": "All",
"pipeline": "Chunkr",
"segment_processing": {
"Caption": {
"description": None,
"extended_context": None,
"llm": "<string>"
},
"Footnote": {
"description": None,
"extended_context": None,
"llm": "<string>"
},
"FormRegion": {
"description": None,
"extended_context": None,
"llm": "<string>"
},
"Formula": {
"description": None,
"extended_context": None,
"llm": "<string>"
},
"GraphicalItem": {
"description": None,
"extended_context": None,
"llm": "<string>"
},
"Legend": {
"description": None,
"extended_context": None,
"llm": "<string>"
},
"LineNumber": {
"description": None,
"extended_context": None,
"llm": "<string>"
},
"ListItem": {
"description": None,
"extended_context": None,
"llm": "<string>"
},
"Page": {
"description": None,
"extended_context": None,
"llm": "<string>"
},
"PageFooter": {
"description": None,
"extended_context": None,
"llm": "<string>"
},
"PageHeader": {
"description": None,
"extended_context": None,
"llm": "<string>"
},
"PageNumber": {
"description": None,
"extended_context": None,
"llm": "<string>"
},
"Picture": {
"description": None,
"extended_context": None,
"llm": "<string>"
},
"Table": {
"description": None,
"extended_context": None,
"llm": "<string>"
},
"Text": {
"description": None,
"extended_context": None,
"llm": "<string>"
},
"Title": {
"description": None,
"extended_context": None,
"llm": "<string>"
},
"Unknown": {
"description": None,
"extended_context": None,
"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.",
"expires_in": 123,
"file_name": "<string>"
}
headers = {
"Authorization": "<api-key>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {Authorization: '<api-key>', 'Content-Type': 'application/json'},
body: JSON.stringify({
schema: {},
file: '<string>',
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.',
expires_in: 123,
file_name: '<string>'
})
};
fetch('https://api.chunkr.ai/tasks/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/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 => json_encode([
'schema' => [
],
'file' => '<string>',
'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.',
'expires_in' => 123,
'file_name' => '<string>'
]),
CURLOPT_HTTPHEADER => [
"Authorization: <api-key>",
"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.chunkr.ai/tasks/extract"
payload := strings.NewReader("{\n \"schema\": {},\n \"file\": \"<string>\",\n \"parse_configuration\": {\n \"chunk_processing\": {\n \"ignore_headers_and_footers\": null,\n \"target_length\": 4096,\n \"tokenizer\": {\n \"Enum\": \"Word\"\n }\n },\n \"error_handling\": \"Fail\",\n \"ocr_strategy\": \"All\",\n \"pipeline\": \"Chunkr\",\n \"segment_processing\": {\n \"Caption\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"Footnote\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"FormRegion\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"Formula\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"GraphicalItem\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"Legend\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"LineNumber\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"ListItem\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"Page\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"PageFooter\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"PageHeader\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"PageNumber\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"Picture\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"Table\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"Text\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"Title\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"Unknown\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n }\n },\n \"segmentation_strategy\": \"LayoutAnalysis\"\n },\n \"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.\",\n \"expires_in\": 123,\n \"file_name\": \"<string>\"\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Authorization", "<api-key>")
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.chunkr.ai/tasks/extract")
.header("Authorization", "<api-key>")
.header("Content-Type", "application/json")
.body("{\n \"schema\": {},\n \"file\": \"<string>\",\n \"parse_configuration\": {\n \"chunk_processing\": {\n \"ignore_headers_and_footers\": null,\n \"target_length\": 4096,\n \"tokenizer\": {\n \"Enum\": \"Word\"\n }\n },\n \"error_handling\": \"Fail\",\n \"ocr_strategy\": \"All\",\n \"pipeline\": \"Chunkr\",\n \"segment_processing\": {\n \"Caption\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"Footnote\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"FormRegion\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"Formula\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"GraphicalItem\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"Legend\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"LineNumber\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"ListItem\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"Page\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"PageFooter\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"PageHeader\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"PageNumber\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"Picture\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"Table\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"Text\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"Title\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"Unknown\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n }\n },\n \"segmentation_strategy\": \"LayoutAnalysis\"\n },\n \"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.\",\n \"expires_in\": 123,\n \"file_name\": \"<string>\"\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.chunkr.ai/tasks/extract")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Authorization"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"schema\": {},\n \"file\": \"<string>\",\n \"parse_configuration\": {\n \"chunk_processing\": {\n \"ignore_headers_and_footers\": null,\n \"target_length\": 4096,\n \"tokenizer\": {\n \"Enum\": \"Word\"\n }\n },\n \"error_handling\": \"Fail\",\n \"ocr_strategy\": \"All\",\n \"pipeline\": \"Chunkr\",\n \"segment_processing\": {\n \"Caption\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"Footnote\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"FormRegion\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"Formula\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"GraphicalItem\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"Legend\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"LineNumber\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"ListItem\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"Page\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"PageFooter\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"PageHeader\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"PageNumber\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"Picture\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"Table\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"Text\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"Title\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n },\n \"Unknown\": {\n \"description\": null,\n \"extended_context\": null,\n \"llm\": \"<string>\"\n }\n },\n \"segmentation_strategy\": \"LayoutAnalysis\"\n },\n \"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.\",\n \"expires_in\": 123,\n \"file_name\": \"<string>\"\n}"
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
Body
application/json
JSON request to create an extract task
The schema to be used for the extraction.
The file to be extracted. Supported inputs:
ch://files/{file_id}: Reference to an existing file. Upload via the Files APIhttp(s)://...: Remote URL to fetchdata:*;base64,...or raw base64 stringtask_id: Reference to an existingparsetask.
Optional configuration for the parse task.
Can not be used if file is a task_id.
Show child attributes
Show child attributes
system_prompt
string | null
default: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.
The system prompt to be used for the extraction.
The number of seconds until task is deleted. Expired tasks can not be updated, polled or accessed via web interface.
The name of the file to be extracted. If not set a name will be generated.
Can not be provided if the file is a task_id.
Response
Task created successfully.
True when the task reaches a terminal state i.e. status is Succeeded or Failed or Cancelled
Show child attributes
Show child attributes
The date and time when the task was created and queued.
Information about the input file.
Show child attributes
Show child attributes
A message describing the task's status or any errors that occurred.
The status of the task.
Available options:
Starting, Processing, Succeeded, Failed, Cancelled The unique identifier for the task.
Available options:
Parse, Extract Version information for the task.
Show child attributes
Show child attributes
The date and time when the task will expire.
The date and time when the task was finished.
The presigned URL of the input file.
Deprecated use file_info.url instead.
The processed results of a document extraction task.
Shapes:
results: JSON matching the user-provided schema.citations: mirror ofresults; only leaf positions (primitive or array-of-primitives) contain aVec<Citation>supporting that field.metrics: mirror ofresults; only leaf positions contain aMetricsobject for that field.
Show child attributes
Show child attributes
The ID of the source parse task that was used for extraction
The date and time when the task was started.
The presigned URL of the task.
⌘I