Create Extract Task

import os
from chunkr_ai import Chunkr

client = Chunkr(
    api_key=os.environ.get("CHUNKR_API_KEY"),  # This is the default and can be omitted
)
extract = client.tasks.extract.create(
    file="https://example.com/invoice.pdf",
    schema={
        "type": "object",
        "properties": {
            "invoice_number": {"type": "string"},
            "total": {"type": "number"},
        },
    },
)
print(extract.task_id)

import Chunkr from 'chunkr-ai';

const client = new Chunkr({
  apiKey: process.env['CHUNKR_API_KEY'], // This is the default and can be omitted
});

const extract = await client.tasks.extract.create({
  file: 'https://example.com/invoice.pdf',
  schema: {
    type: 'object',
    properties: {
      invoice_number: { type: 'string' },
      total: { type: 'number' },
    },
  },
});

console.log(extract.task_id);

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>"
}
'

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": {
          "crop_image": "All",
          "description": null,
          "extended_context": null,
          "format": "Html",
          "llm": "<string>",
          "strategy": "LLM"
        },
        "Footnote": {
          "crop_image": "All",
          "description": null,
          "extended_context": null,
          "format": "Html",
          "llm": "<string>",
          "strategy": "LLM"
        },
        "FormRegion": {
          "crop_image": "All",
          "description": null,
          "extended_context": null,
          "format": "Html",
          "llm": "<string>",
          "strategy": "LLM"
        },
        "Formula": {
          "crop_image": "All",
          "description": null,
          "extended_context": null,
          "format": "Html",
          "llm": "<string>",
          "strategy": "LLM"
        },
        "GraphicalItem": {
          "crop_image": "All",
          "description": null,
          "extended_context": null,
          "format": "Html",
          "llm": "<string>",
          "strategy": "LLM"
        },
        "Legend": {
          "crop_image": "All",
          "description": null,
          "extended_context": null,
          "format": "Html",
          "llm": "<string>",
          "strategy": "LLM"
        },
        "LineNumber": {
          "crop_image": "All",
          "description": null,
          "extended_context": null,
          "format": "Html",
          "llm": "<string>",
          "strategy": "LLM"
        },
        "ListItem": {
          "crop_image": "All",
          "description": null,
          "extended_context": null,
          "format": "Html",
          "llm": "<string>",
          "strategy": "LLM"
        },
        "Page": {
          "crop_image": "All",
          "description": null,
          "extended_context": null,
          "format": "Html",
          "llm": "<string>",
          "strategy": "LLM"
        },
        "PageFooter": {
          "crop_image": "All",
          "description": null,
          "extended_context": null,
          "format": "Html",
          "llm": "<string>",
          "strategy": "LLM"
        },
        "PageHeader": {
          "crop_image": "All",
          "description": null,
          "extended_context": null,
          "format": "Html",
          "llm": "<string>",
          "strategy": "LLM"
        },
        "PageNumber": {
          "crop_image": "All",
          "description": null,
          "extended_context": null,
          "format": "Html",
          "llm": "<string>",
          "strategy": "LLM"
        },
        "Picture": {
          "crop_image": "All",
          "description": null,
          "extended_context": null,
          "format": "Html",
          "llm": "<string>",
          "strategy": "LLM"
        },
        "Table": {
          "crop_image": "All",
          "description": null,
          "extended_context": null,
          "format": "Html",
          "llm": "<string>",
          "strategy": "LLM"
        },
        "Text": {
          "crop_image": "All",
          "description": null,
          "extended_context": null,
          "format": "Html",
          "llm": "<string>",
          "strategy": "LLM"
        },
        "Title": {
          "crop_image": "All",
          "description": null,
          "extended_context": null,
          "format": "Html",
          "llm": "<string>",
          "strategy": "LLM"
        },
        "Unknown": {
          "crop_image": "All",
          "description": null,
          "extended_context": null,
          "format": "Html",
          "llm": "<string>",
          "strategy": "LLM"
        }
      },
      "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>",
  "status": "Starting",
  "task_id": "<string>",
  "task_type": "Parse",
  "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>