Extract File Async (Deprecated)

Submit an asynchronous extraction job

curl --request POST \
  --url https://api.runpulse.com/extract_async \
  --header 'Content-Type: multipart/form-data' \
  --header 'x-api-key: <api-key>' \
  --form file='@example-file' \
  --form 'fileUrl=<string>' \
  --form detectSelections=true \
  --form extractionConfigId=3c90c3cc-0d44-4b50-8888-8dd25736052a \
  --form 'pages=<string>' \
  --form forceUrl=false \
  --form 'figureProcessing={
  "description": false,
  "showImages": false
}' \
  --form 'extensions={
  "footnoteReferences": false,
  "document_metadata": false,
  "chunking": {
    "chunkTypes": [],
    "chunkSize": 2
  },
  "altOutputs": {
    "wlbb": false,
    "returnHtml": false,
    "returnXml": false
  }
}' \
  --form 'spreadsheet={
  "includeHiddenRows": false,
  "includeHiddenCols": false,
  "includeHiddenSheets": false,
  "useRawValues": false,
  "onlyDataRows": false,
  "onlyDataCols": false,
  "cellData": true
}' \
  --form 'storage={
  "enabled": true,
  "folderName": "<string>",
  "folderId": "3c90c3cc-0d44-4b50-8888-8dd25736052a"
}' \
  --form async=false \
  --form 'structuredOutput={
  "schema": {},
  "schemaPrompt": "<string>",
  "effort": false
}' \
  --form 'schema={}' \
  --form 'schemaPrompt=<string>' \
  --form 'customPrompt=<string>' \
  --form 'chunking=<string>' \
  --form chunkSize=2 \
  --form extractFigure=false \
  --form figureDescription=false \
  --form showImages=false \
  --form returnHtml=false \
  --form thinking=false

import requests

url = "https://api.runpulse.com/extract_async"

files = { "file": ("example-file", open("example-file", "rb")) }
payload = {
    "fileUrl": "<string>",
    "detectSelections": "true",
    "extractionConfigId": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
    "pages": "<string>",
    "forceUrl": "false",
    "figureProcessing": "{
  \"description\": false,
  \"showImages\": false
}",
    "extensions": "{
  \"footnoteReferences\": false,
  \"document_metadata\": false,
  \"chunking\": {
    \"chunkTypes\": [],
    \"chunkSize\": 2
  },
  \"altOutputs\": {
    \"wlbb\": false,
    \"returnHtml\": false,
    \"returnXml\": false
  }
}",
    "spreadsheet": "{
  \"includeHiddenRows\": false,
  \"includeHiddenCols\": false,
  \"includeHiddenSheets\": false,
  \"useRawValues\": false,
  \"onlyDataRows\": false,
  \"onlyDataCols\": false,
  \"cellData\": true
}",
    "storage": "{
  \"enabled\": true,
  \"folderName\": \"<string>\",
  \"folderId\": \"3c90c3cc-0d44-4b50-8888-8dd25736052a\"
}",
    "async": "false",
    "structuredOutput": "{
  \"schema\": {},
  \"schemaPrompt\": \"<string>\",
  \"effort\": false
}",
    "schema": "{}",
    "schemaPrompt": "<string>",
    "customPrompt": "<string>",
    "chunking": "<string>",
    "chunkSize": "2",
    "extractFigure": "false",
    "figureDescription": "false",
    "showImages": "false",
    "returnHtml": "false",
    "thinking": "false"
}
headers = {"x-api-key": "<api-key>"}

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

print(response.text)

const form = new FormData();
form.append('file', '<string>');
form.append('fileUrl', '<string>');
form.append('detectSelections', 'true');
form.append('extractionConfigId', '3c90c3cc-0d44-4b50-8888-8dd25736052a');
form.append('pages', '<string>');
form.append('forceUrl', 'false');
form.append('figureProcessing', '{
  "description": false,
  "showImages": false
}');
form.append('extensions', '{
  "footnoteReferences": false,
  "document_metadata": false,
  "chunking": {
    "chunkTypes": [],
    "chunkSize": 2
  },
  "altOutputs": {
    "wlbb": false,
    "returnHtml": false,
    "returnXml": false
  }
}');
form.append('spreadsheet', '{
  "includeHiddenRows": false,
  "includeHiddenCols": false,
  "includeHiddenSheets": false,
  "useRawValues": false,
  "onlyDataRows": false,
  "onlyDataCols": false,
  "cellData": true
}');
form.append('storage', '{
  "enabled": true,
  "folderName": "<string>",
  "folderId": "3c90c3cc-0d44-4b50-8888-8dd25736052a"
}');
form.append('async', 'false');
form.append('structuredOutput', '{
  "schema": {},
  "schemaPrompt": "<string>",
  "effort": false
}');
form.append('schema', '{}');
form.append('schemaPrompt', '<string>');
form.append('customPrompt', '<string>');
form.append('chunking', '<string>');
form.append('chunkSize', '2');
form.append('extractFigure', 'false');
form.append('figureDescription', 'false');
form.append('showImages', 'false');
form.append('returnHtml', 'false');
form.append('thinking', 'false');

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

options.body = form;

fetch('https://api.runpulse.com/extract_async', 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.runpulse.com/extract_async",
  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\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"fileUrl\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"detectSelections\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"extractionConfigId\"\r\n\r\n3c90c3cc-0d44-4b50-8888-8dd25736052a\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"pages\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"forceUrl\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"figureProcessing\"\r\n\r\n{\r\n  \"description\": false,\r\n  \"showImages\": false\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"extensions\"\r\n\r\n{\r\n  \"footnoteReferences\": false,\r\n  \"document_metadata\": false,\r\n  \"chunking\": {\r\n    \"chunkTypes\": [],\r\n    \"chunkSize\": 2\r\n  },\r\n  \"altOutputs\": {\r\n    \"wlbb\": false,\r\n    \"returnHtml\": false,\r\n    \"returnXml\": false\r\n  }\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"spreadsheet\"\r\n\r\n{\r\n  \"includeHiddenRows\": false,\r\n  \"includeHiddenCols\": false,\r\n  \"includeHiddenSheets\": false,\r\n  \"useRawValues\": false,\r\n  \"onlyDataRows\": false,\r\n  \"onlyDataCols\": false,\r\n  \"cellData\": true\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"storage\"\r\n\r\n{\r\n  \"enabled\": true,\r\n  \"folderName\": \"<string>\",\r\n  \"folderId\": \"3c90c3cc-0d44-4b50-8888-8dd25736052a\"\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"async\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"structuredOutput\"\r\n\r\n{\r\n  \"schema\": {},\r\n  \"schemaPrompt\": \"<string>\",\r\n  \"effort\": false\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"schema\"\r\n\r\n{}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"schemaPrompt\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"customPrompt\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"chunking\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"chunkSize\"\r\n\r\n2\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"extractFigure\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"figureDescription\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"showImages\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"returnHtml\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"thinking\"\r\n\r\nfalse\r\n-----011000010111000001101001--",
  CURLOPT_HTTPHEADER => [
    "Content-Type: multipart/form-data",
    "x-api-key: <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"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.runpulse.com/extract_async"

	payload := strings.NewReader("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"fileUrl\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"detectSelections\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"extractionConfigId\"\r\n\r\n3c90c3cc-0d44-4b50-8888-8dd25736052a\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"pages\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"forceUrl\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"figureProcessing\"\r\n\r\n{\r\n  \"description\": false,\r\n  \"showImages\": false\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"extensions\"\r\n\r\n{\r\n  \"footnoteReferences\": false,\r\n  \"document_metadata\": false,\r\n  \"chunking\": {\r\n    \"chunkTypes\": [],\r\n    \"chunkSize\": 2\r\n  },\r\n  \"altOutputs\": {\r\n    \"wlbb\": false,\r\n    \"returnHtml\": false,\r\n    \"returnXml\": false\r\n  }\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"spreadsheet\"\r\n\r\n{\r\n  \"includeHiddenRows\": false,\r\n  \"includeHiddenCols\": false,\r\n  \"includeHiddenSheets\": false,\r\n  \"useRawValues\": false,\r\n  \"onlyDataRows\": false,\r\n  \"onlyDataCols\": false,\r\n  \"cellData\": true\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"storage\"\r\n\r\n{\r\n  \"enabled\": true,\r\n  \"folderName\": \"<string>\",\r\n  \"folderId\": \"3c90c3cc-0d44-4b50-8888-8dd25736052a\"\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"async\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"structuredOutput\"\r\n\r\n{\r\n  \"schema\": {},\r\n  \"schemaPrompt\": \"<string>\",\r\n  \"effort\": false\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"schema\"\r\n\r\n{}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"schemaPrompt\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"customPrompt\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"chunking\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"chunkSize\"\r\n\r\n2\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"extractFigure\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"figureDescription\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"showImages\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"returnHtml\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"thinking\"\r\n\r\nfalse\r\n-----011000010111000001101001--")

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

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

	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.runpulse.com/extract_async")
  .header("x-api-key", "<api-key>")
  .body("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"fileUrl\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"detectSelections\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"extractionConfigId\"\r\n\r\n3c90c3cc-0d44-4b50-8888-8dd25736052a\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"pages\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"forceUrl\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"figureProcessing\"\r\n\r\n{\r\n  \"description\": false,\r\n  \"showImages\": false\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"extensions\"\r\n\r\n{\r\n  \"footnoteReferences\": false,\r\n  \"document_metadata\": false,\r\n  \"chunking\": {\r\n    \"chunkTypes\": [],\r\n    \"chunkSize\": 2\r\n  },\r\n  \"altOutputs\": {\r\n    \"wlbb\": false,\r\n    \"returnHtml\": false,\r\n    \"returnXml\": false\r\n  }\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"spreadsheet\"\r\n\r\n{\r\n  \"includeHiddenRows\": false,\r\n  \"includeHiddenCols\": false,\r\n  \"includeHiddenSheets\": false,\r\n  \"useRawValues\": false,\r\n  \"onlyDataRows\": false,\r\n  \"onlyDataCols\": false,\r\n  \"cellData\": true\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"storage\"\r\n\r\n{\r\n  \"enabled\": true,\r\n  \"folderName\": \"<string>\",\r\n  \"folderId\": \"3c90c3cc-0d44-4b50-8888-8dd25736052a\"\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"async\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"structuredOutput\"\r\n\r\n{\r\n  \"schema\": {},\r\n  \"schemaPrompt\": \"<string>\",\r\n  \"effort\": false\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"schema\"\r\n\r\n{}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"schemaPrompt\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"customPrompt\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"chunking\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"chunkSize\"\r\n\r\n2\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"extractFigure\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"figureDescription\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"showImages\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"returnHtml\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"thinking\"\r\n\r\nfalse\r\n-----011000010111000001101001--")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.runpulse.com/extract_async")

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

request = Net::HTTP::Post.new(url)
request["x-api-key"] = '<api-key>'
request.body = "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"fileUrl\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"detectSelections\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"extractionConfigId\"\r\n\r\n3c90c3cc-0d44-4b50-8888-8dd25736052a\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"pages\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"forceUrl\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"figureProcessing\"\r\n\r\n{\r\n  \"description\": false,\r\n  \"showImages\": false\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"extensions\"\r\n\r\n{\r\n  \"footnoteReferences\": false,\r\n  \"document_metadata\": false,\r\n  \"chunking\": {\r\n    \"chunkTypes\": [],\r\n    \"chunkSize\": 2\r\n  },\r\n  \"altOutputs\": {\r\n    \"wlbb\": false,\r\n    \"returnHtml\": false,\r\n    \"returnXml\": false\r\n  }\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"spreadsheet\"\r\n\r\n{\r\n  \"includeHiddenRows\": false,\r\n  \"includeHiddenCols\": false,\r\n  \"includeHiddenSheets\": false,\r\n  \"useRawValues\": false,\r\n  \"onlyDataRows\": false,\r\n  \"onlyDataCols\": false,\r\n  \"cellData\": true\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"storage\"\r\n\r\n{\r\n  \"enabled\": true,\r\n  \"folderName\": \"<string>\",\r\n  \"folderId\": \"3c90c3cc-0d44-4b50-8888-8dd25736052a\"\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"async\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"structuredOutput\"\r\n\r\n{\r\n  \"schema\": {},\r\n  \"schemaPrompt\": \"<string>\",\r\n  \"effort\": false\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"schema\"\r\n\r\n{}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"schemaPrompt\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"customPrompt\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"chunking\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"chunkSize\"\r\n\r\n2\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"extractFigure\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"figureDescription\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"showImages\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"returnHtml\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"thinking\"\r\n\r\nfalse\r\n-----011000010111000001101001--"

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

{
  "job_id": "<string>",
  "status": "pending",
  "message": "<string>",
  "queuedAt": "2023-11-07T05:31:56Z",
  "credits_used": 123
}

POST

extract_async

Submit an asynchronous extraction job

curl --request POST \
  --url https://api.runpulse.com/extract_async \
  --header 'Content-Type: multipart/form-data' \
  --header 'x-api-key: <api-key>' \
  --form file='@example-file' \
  --form 'fileUrl=<string>' \
  --form detectSelections=true \
  --form extractionConfigId=3c90c3cc-0d44-4b50-8888-8dd25736052a \
  --form 'pages=<string>' \
  --form forceUrl=false \
  --form 'figureProcessing={
  "description": false,
  "showImages": false
}' \
  --form 'extensions={
  "footnoteReferences": false,
  "document_metadata": false,
  "chunking": {
    "chunkTypes": [],
    "chunkSize": 2
  },
  "altOutputs": {
    "wlbb": false,
    "returnHtml": false,
    "returnXml": false
  }
}' \
  --form 'spreadsheet={
  "includeHiddenRows": false,
  "includeHiddenCols": false,
  "includeHiddenSheets": false,
  "useRawValues": false,
  "onlyDataRows": false,
  "onlyDataCols": false,
  "cellData": true
}' \
  --form 'storage={
  "enabled": true,
  "folderName": "<string>",
  "folderId": "3c90c3cc-0d44-4b50-8888-8dd25736052a"
}' \
  --form async=false \
  --form 'structuredOutput={
  "schema": {},
  "schemaPrompt": "<string>",
  "effort": false
}' \
  --form 'schema={}' \
  --form 'schemaPrompt=<string>' \
  --form 'customPrompt=<string>' \
  --form 'chunking=<string>' \
  --form chunkSize=2 \
  --form extractFigure=false \
  --form figureDescription=false \
  --form showImages=false \
  --form returnHtml=false \
  --form thinking=false

import requests

url = "https://api.runpulse.com/extract_async"

files = { "file": ("example-file", open("example-file", "rb")) }
payload = {
    "fileUrl": "<string>",
    "detectSelections": "true",
    "extractionConfigId": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
    "pages": "<string>",
    "forceUrl": "false",
    "figureProcessing": "{
  \"description\": false,
  \"showImages\": false
}",
    "extensions": "{
  \"footnoteReferences\": false,
  \"document_metadata\": false,
  \"chunking\": {
    \"chunkTypes\": [],
    \"chunkSize\": 2
  },
  \"altOutputs\": {
    \"wlbb\": false,
    \"returnHtml\": false,
    \"returnXml\": false
  }
}",
    "spreadsheet": "{
  \"includeHiddenRows\": false,
  \"includeHiddenCols\": false,
  \"includeHiddenSheets\": false,
  \"useRawValues\": false,
  \"onlyDataRows\": false,
  \"onlyDataCols\": false,
  \"cellData\": true
}",
    "storage": "{
  \"enabled\": true,
  \"folderName\": \"<string>\",
  \"folderId\": \"3c90c3cc-0d44-4b50-8888-8dd25736052a\"
}",
    "async": "false",
    "structuredOutput": "{
  \"schema\": {},
  \"schemaPrompt\": \"<string>\",
  \"effort\": false
}",
    "schema": "{}",
    "schemaPrompt": "<string>",
    "customPrompt": "<string>",
    "chunking": "<string>",
    "chunkSize": "2",
    "extractFigure": "false",
    "figureDescription": "false",
    "showImages": "false",
    "returnHtml": "false",
    "thinking": "false"
}
headers = {"x-api-key": "<api-key>"}

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

print(response.text)

const form = new FormData();
form.append('file', '<string>');
form.append('fileUrl', '<string>');
form.append('detectSelections', 'true');
form.append('extractionConfigId', '3c90c3cc-0d44-4b50-8888-8dd25736052a');
form.append('pages', '<string>');
form.append('forceUrl', 'false');
form.append('figureProcessing', '{
  "description": false,
  "showImages": false
}');
form.append('extensions', '{
  "footnoteReferences": false,
  "document_metadata": false,
  "chunking": {
    "chunkTypes": [],
    "chunkSize": 2
  },
  "altOutputs": {
    "wlbb": false,
    "returnHtml": false,
    "returnXml": false
  }
}');
form.append('spreadsheet', '{
  "includeHiddenRows": false,
  "includeHiddenCols": false,
  "includeHiddenSheets": false,
  "useRawValues": false,
  "onlyDataRows": false,
  "onlyDataCols": false,
  "cellData": true
}');
form.append('storage', '{
  "enabled": true,
  "folderName": "<string>",
  "folderId": "3c90c3cc-0d44-4b50-8888-8dd25736052a"
}');
form.append('async', 'false');
form.append('structuredOutput', '{
  "schema": {},
  "schemaPrompt": "<string>",
  "effort": false
}');
form.append('schema', '{}');
form.append('schemaPrompt', '<string>');
form.append('customPrompt', '<string>');
form.append('chunking', '<string>');
form.append('chunkSize', '2');
form.append('extractFigure', 'false');
form.append('figureDescription', 'false');
form.append('showImages', 'false');
form.append('returnHtml', 'false');
form.append('thinking', 'false');

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

options.body = form;

fetch('https://api.runpulse.com/extract_async', 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.runpulse.com/extract_async",
  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\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"fileUrl\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"detectSelections\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"extractionConfigId\"\r\n\r\n3c90c3cc-0d44-4b50-8888-8dd25736052a\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"pages\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"forceUrl\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"figureProcessing\"\r\n\r\n{\r\n  \"description\": false,\r\n  \"showImages\": false\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"extensions\"\r\n\r\n{\r\n  \"footnoteReferences\": false,\r\n  \"document_metadata\": false,\r\n  \"chunking\": {\r\n    \"chunkTypes\": [],\r\n    \"chunkSize\": 2\r\n  },\r\n  \"altOutputs\": {\r\n    \"wlbb\": false,\r\n    \"returnHtml\": false,\r\n    \"returnXml\": false\r\n  }\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"spreadsheet\"\r\n\r\n{\r\n  \"includeHiddenRows\": false,\r\n  \"includeHiddenCols\": false,\r\n  \"includeHiddenSheets\": false,\r\n  \"useRawValues\": false,\r\n  \"onlyDataRows\": false,\r\n  \"onlyDataCols\": false,\r\n  \"cellData\": true\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"storage\"\r\n\r\n{\r\n  \"enabled\": true,\r\n  \"folderName\": \"<string>\",\r\n  \"folderId\": \"3c90c3cc-0d44-4b50-8888-8dd25736052a\"\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"async\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"structuredOutput\"\r\n\r\n{\r\n  \"schema\": {},\r\n  \"schemaPrompt\": \"<string>\",\r\n  \"effort\": false\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"schema\"\r\n\r\n{}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"schemaPrompt\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"customPrompt\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"chunking\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"chunkSize\"\r\n\r\n2\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"extractFigure\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"figureDescription\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"showImages\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"returnHtml\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"thinking\"\r\n\r\nfalse\r\n-----011000010111000001101001--",
  CURLOPT_HTTPHEADER => [
    "Content-Type: multipart/form-data",
    "x-api-key: <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"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.runpulse.com/extract_async"

	payload := strings.NewReader("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"fileUrl\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"detectSelections\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"extractionConfigId\"\r\n\r\n3c90c3cc-0d44-4b50-8888-8dd25736052a\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"pages\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"forceUrl\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"figureProcessing\"\r\n\r\n{\r\n  \"description\": false,\r\n  \"showImages\": false\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"extensions\"\r\n\r\n{\r\n  \"footnoteReferences\": false,\r\n  \"document_metadata\": false,\r\n  \"chunking\": {\r\n    \"chunkTypes\": [],\r\n    \"chunkSize\": 2\r\n  },\r\n  \"altOutputs\": {\r\n    \"wlbb\": false,\r\n    \"returnHtml\": false,\r\n    \"returnXml\": false\r\n  }\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"spreadsheet\"\r\n\r\n{\r\n  \"includeHiddenRows\": false,\r\n  \"includeHiddenCols\": false,\r\n  \"includeHiddenSheets\": false,\r\n  \"useRawValues\": false,\r\n  \"onlyDataRows\": false,\r\n  \"onlyDataCols\": false,\r\n  \"cellData\": true\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"storage\"\r\n\r\n{\r\n  \"enabled\": true,\r\n  \"folderName\": \"<string>\",\r\n  \"folderId\": \"3c90c3cc-0d44-4b50-8888-8dd25736052a\"\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"async\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"structuredOutput\"\r\n\r\n{\r\n  \"schema\": {},\r\n  \"schemaPrompt\": \"<string>\",\r\n  \"effort\": false\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"schema\"\r\n\r\n{}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"schemaPrompt\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"customPrompt\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"chunking\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"chunkSize\"\r\n\r\n2\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"extractFigure\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"figureDescription\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"showImages\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"returnHtml\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"thinking\"\r\n\r\nfalse\r\n-----011000010111000001101001--")

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

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

	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.runpulse.com/extract_async")
  .header("x-api-key", "<api-key>")
  .body("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"fileUrl\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"detectSelections\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"extractionConfigId\"\r\n\r\n3c90c3cc-0d44-4b50-8888-8dd25736052a\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"pages\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"forceUrl\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"figureProcessing\"\r\n\r\n{\r\n  \"description\": false,\r\n  \"showImages\": false\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"extensions\"\r\n\r\n{\r\n  \"footnoteReferences\": false,\r\n  \"document_metadata\": false,\r\n  \"chunking\": {\r\n    \"chunkTypes\": [],\r\n    \"chunkSize\": 2\r\n  },\r\n  \"altOutputs\": {\r\n    \"wlbb\": false,\r\n    \"returnHtml\": false,\r\n    \"returnXml\": false\r\n  }\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"spreadsheet\"\r\n\r\n{\r\n  \"includeHiddenRows\": false,\r\n  \"includeHiddenCols\": false,\r\n  \"includeHiddenSheets\": false,\r\n  \"useRawValues\": false,\r\n  \"onlyDataRows\": false,\r\n  \"onlyDataCols\": false,\r\n  \"cellData\": true\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"storage\"\r\n\r\n{\r\n  \"enabled\": true,\r\n  \"folderName\": \"<string>\",\r\n  \"folderId\": \"3c90c3cc-0d44-4b50-8888-8dd25736052a\"\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"async\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"structuredOutput\"\r\n\r\n{\r\n  \"schema\": {},\r\n  \"schemaPrompt\": \"<string>\",\r\n  \"effort\": false\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"schema\"\r\n\r\n{}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"schemaPrompt\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"customPrompt\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"chunking\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"chunkSize\"\r\n\r\n2\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"extractFigure\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"figureDescription\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"showImages\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"returnHtml\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"thinking\"\r\n\r\nfalse\r\n-----011000010111000001101001--")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.runpulse.com/extract_async")

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

request = Net::HTTP::Post.new(url)
request["x-api-key"] = '<api-key>'
request.body = "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"fileUrl\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"detectSelections\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"extractionConfigId\"\r\n\r\n3c90c3cc-0d44-4b50-8888-8dd25736052a\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"pages\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"forceUrl\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"figureProcessing\"\r\n\r\n{\r\n  \"description\": false,\r\n  \"showImages\": false\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"extensions\"\r\n\r\n{\r\n  \"footnoteReferences\": false,\r\n  \"document_metadata\": false,\r\n  \"chunking\": {\r\n    \"chunkTypes\": [],\r\n    \"chunkSize\": 2\r\n  },\r\n  \"altOutputs\": {\r\n    \"wlbb\": false,\r\n    \"returnHtml\": false,\r\n    \"returnXml\": false\r\n  }\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"spreadsheet\"\r\n\r\n{\r\n  \"includeHiddenRows\": false,\r\n  \"includeHiddenCols\": false,\r\n  \"includeHiddenSheets\": false,\r\n  \"useRawValues\": false,\r\n  \"onlyDataRows\": false,\r\n  \"onlyDataCols\": false,\r\n  \"cellData\": true\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"storage\"\r\n\r\n{\r\n  \"enabled\": true,\r\n  \"folderName\": \"<string>\",\r\n  \"folderId\": \"3c90c3cc-0d44-4b50-8888-8dd25736052a\"\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"async\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"structuredOutput\"\r\n\r\n{\r\n  \"schema\": {},\r\n  \"schemaPrompt\": \"<string>\",\r\n  \"effort\": false\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"schema\"\r\n\r\n{}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"schemaPrompt\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"customPrompt\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"chunking\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"chunkSize\"\r\n\r\n2\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"extractFigure\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"figureDescription\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"showImages\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"returnHtml\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"thinking\"\r\n\r\nfalse\r\n-----011000010111000001101001--"

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

{
  "job_id": "<string>",
  "status": "pending",
  "message": "<string>",
  "queuedAt": "2023-11-07T05:31:56Z",
  "credits_used": 123
}

Deprecated: This endpoint is deprecated. Use /extract with async: true instead.

Overview

The asynchronous extraction endpoint accepts the same input parameters as the synchronous /extract endpoint but returns immediately with a job identifier. Use this endpoint for:

Large documents that may take longer to process
Batch processing workflows
Non-blocking integrations

Migration

Replace calls to /extract_async with /extract and add async: true:

- POST /extract_async
- {"file_url": "https://example.com/doc.pdf"}

+ POST /extract
+ {"file_url": "https://example.com/doc.pdf", "async": true}

The response format is identical.

Request

Document Source

Provide the document using one of these methods:

Field	Type	Description
`file`	binary	Document file to upload directly (multipart/form-data).
`file_url`	string	Public or pre-signed URL that Pulse will download and extract.

Extraction Options

Field	Type	Default	Description
`model`	string (enum)	`default`	Extraction model to use. One of `default` or `pulse-ultra-2`. `pulse-ultra-2` uses Pulse’s vision-language model with built-in refinement, figure/chart extraction, and word-level bounding boxes.
`pages`	string	-	Page range filter (1-indexed). Supports segments like `1-2` or mixed ranges like `1-2,5`. Page 1 is the first page.
`figure_processing`	object	-	Settings that control how figures in the document are processed. These affect the markdown output directly and do not produce additional output fields. See Figure Processing.
`extensions`	object	-	Settings that enable additional processing or alternate output formats. Each enabled extension produces a corresponding result under `response.extensions.*`. See Extensions.
`spreadsheet`	object	-	Settings for Excel/spreadsheet extraction. Controls hidden rows, columns, sheets, raw values, phantom-cell trimming, and whether table `cell_data` is included. Applies to `.xlsx`, `.xlsm`, and `.xls` files. See Spreadsheet Options.
`storage`	object	-	Options for persisting extraction artifacts. See Storage Options.
`async`	boolean	`false`	If `true`, returns immediately with a `job_id` for polling via `GET /job/{jobId}`.
`force_url`	boolean	`false`	When `true`, return the complete extraction result as a URL even if it is small. Spreadsheet responses are URL-backed by default; set `force_url: false` to request inline spreadsheet output. URL delivery changes only the transport, not the result shape.
`structured_output`	object	-	⚠️ Deprecated — Use the `/schema` endpoint after extraction instead. Still works for backward compatibility.

Figure Processing

Settings under figure_processing control how figures (images, charts, diagrams) and embedded visuals are processed. Applies to both PDFs/images (figures detected from layout) and spreadsheets (charts and embedded images read directly from the workbook). Affects the markdown output and the bounding_boxes.Images[] array.

Field	Type	Default	Description
`figure_processing.description`	boolean	`false`	Generate descriptive captions for extracted visuals. Captions appear under `bounding_boxes.Images[].description` and inline in the markdown output. Applies to both detected charts and non-chart images.
`figure_processing.show_images`	boolean	`false`	Return image URLs for extracted visuals. URLs appear under `bounding_boxes.Images[].image_url` and resolve to a Pulse-hosted PNG/JPEG served from `GET /results/{jobId}/images/{filename}`. Applies to both detected charts and non-chart images.

For spreadsheets specifically, show_images: true collects every embedded chart and image in the workbook and emits one entry per visual under bounding_boxes.Images, with chart-specific fields like chart_type, chart_title, and source_ranges populated. See Bounding Boxes for the full field list.

Spreadsheet Options

Settings under spreadsheet control how Excel workbooks (.xlsx, .xlsm, .xls) are processed. By default, hidden rows, columns, and sheets are excluded from extraction output, cell values are rendered the way Excel displays them, and table cell metadata is included. Phantom-cell trimming is opt-in. Spreadsheet responses are returned as full-result URLs by default because workbook cell_data can make the payload large even for modest .xlsx files.

Field	Type	Default	Description
`spreadsheet.include_hidden_rows`	boolean	`false`	Include rows that are hidden in the Excel workbook.
`spreadsheet.include_hidden_cols`	boolean	`false`	Include columns that are hidden in the Excel workbook.
`spreadsheet.include_hidden_sheets`	boolean	`false`	Include sheets that are hidden in the Excel workbook.
`spreadsheet.use_raw_values`	boolean	`false`	Emit the underlying numeric value for number cells instead of the Excel display-formatted text — e.g. `1201.67` rather than `$1,202` when the cell uses a rounded currency format. Useful when downstream processing needs exact amounts (cent-level precision) rather than what the workbook shows visually. Percent-formatted cells and dates keep their display rendering. Does not apply to legacy `.xls` files.
`spreadsheet.only_data_rows`	boolean	`false`	When `true`, trim trailing empty rows past the last cell carrying a value or formula. See Phantom-cell trimming below.
`spreadsheet.only_data_cols`	boolean	`false`	When `true`, trim trailing empty columns past the last cell carrying a value or formula. Same rationale as `only_data_rows`.
`spreadsheet.cell_data`	boolean	`true`	Include cell-level table metadata under `bounding_boxes.Tables[].cell_data`. Set to `false` to omit this metadata and reduce output size.

These settings accept both camelCase (includeHiddenRows, onlyDataRows, cellData) and snake_case (include_hidden_rows, only_data_rows, cell_data) formats.

Phantom-cell trimming (`only_data_rows` / `only_data_cols`)

Excel files exported from claims systems, ERPs, and other automated pipelines routinely declare a “used range” that extends hundreds of thousands of rows past where the data actually ends. A typical case: a 57 MB workbook with only ~500 rows of real data, where the other ~1,000,000 rows are empty cells that exist only because they were once selected and styled. These phantom cells inflate file size by orders of magnitude and can exhaust parser memory on the extraction pipeline. Set only_data_rows: true and only_data_cols: true to have Pulse scan each sheet once before parsing, find the largest row and column containing a value or formula, and ignore everything beyond that extent. Surviving cells keep their original A1 coordinates (e.g., a value at B7 in the source is still B7 in the output), so any citation or bounding box that references a specific cell remains stable. The trim only kicks in on large sheets (≥5 MB of XML per sheet), so small, well-formed workbooks pay no overhead either way. Both flags default to false.

Pulse Ultra 2 Options

These options are available only when model: pulse-ultra-2 is set. Passing any of them with the default model returns a 400 error listing the offending fields.

Field	Type	Default	Description
`refine`	boolean	`false`	Run a full-page OCR and formatting correction pass after extraction. Improves accuracy on dense layouts, numerical values, and table structure. Adds ~1–2s per page. Overridden by `refine_options` if both are provided.
`refine_options`	object	-	Granular refinement targets. Takes precedence over the boolean `refine` flag. See below.
`refine_options.tables`	boolean	`false`	Fix table cell values, structure, and headers against the source image.
`refine_options.text`	boolean	`false`	Fix OCR errors, missing or extra content, and numerical accuracy (tables untouched).
`refine_options.formatting`	boolean	`false`	Add strikethrough, italic, bold, super/subscript, and LaTeX formatting (tables untouched).
`extract_figure`	boolean	`false`	Convert charts and data visualizations into HTML `<table>` blocks, wrapped in `<figure-table>` tags. Useful for financial decks, dashboards, and scientific charts.
`figure_description`	boolean	`false`	Generate a 1–2 paragraph natural-language description of each picture, wrapped in `<figure-description>` tags. Combines well with `extract_figure`.
`detect_selections`	boolean	`true`	Detect selected and unselected marks with a specialized selection-mark model. Improves accuracy on forms, checkboxes, radio buttons, handwritten checkmarks, X marks, and similar controls. Enabled by default for `pulse-ultra-2`; set to `false` to skip this pass.
`additional_prompt`	string	`""`	Extra context injected into the extraction prompt. Use to steer extraction toward a specific domain or attention focus. Max 4000 characters.
`custom_image_prompt`	string	`""`	Extra context appended to the prompt used by `figure_description` and `extract_figure`. Tunes image and chart interpretation. Max 2000 characters.
`custom_refine_prompt`	string	`""`	Extra context appended to the refinement prompt. Only applies when `refine: true` or `refine_options` is set. Max 2000 characters.

Selection mark detection

Use detect_selections: true with model: pulse-ultra-2 when a document contains forms, checkboxes, radio buttons, handwritten selection marks, or other marked-choice controls. Pulse runs a specialized detection pass for these marks so selected/unselected states are less likely to be missed or confused with nearby text, boxes, or handwriting. When available, the detected state is returned on the relevant bounding-box items as selected.

Markdown output additions

When extract_figure or figure_description is enabled, figures in response.markdown include additional tags:

<figure data-page="1">
  <figure-table>...HTML table for the chart...</figure-table>
  <figure-description>...1–2 paragraph description...</figure-description>
</figure>

When refine (or refine_options) is set, markdown content is post-processed page-by-page; output is cleaner but typically grows ~1.5–3x in size for dense documents. No new tags are introduced.

Extensions

Settings under extensions enable additional processing passes or alternate output formats. Each enabled extension produces a corresponding output field under response.extensions.*. For example, enabling extensions.chunking produces response.extensions.chunking, and enabling extensions.alt_outputs.return_html produces response.extensions.alt_outputs.html.

Field	Type	Default	Description
`extensions.document_metadata`	boolean	`false`	Extract native properties and deterministic structure from the original file. Results appear under `response.extensions.document_metadata`.
`extensions.footnote_references`	boolean	`false`	Link footnote markers to their corresponding footnote text.
`extensions.chunking`	object	-	Chunking configuration. See below.
`extensions.chunking.chunk_types`	string[]	-	List of chunking strategies: `semantic`, `header`, `page`, `recursive`.
`extensions.chunking.chunk_size`	integer	-	Maximum characters per chunk.
`extensions.alt_outputs`	object	-	Alternate output formats. See below.
`extensions.alt_outputs.wlbb`	boolean	`false`	Enable word-level bounding boxes (PDF only). Results in `response.extensions.alt_outputs.wlbb`.
`extensions.alt_outputs.return_html`	boolean	`false`	Include HTML representation. `response.markdown` is still present; HTML is at `response.extensions.alt_outputs.html`.
`extensions.alt_outputs.return_xml`	boolean	`false`	Include XML representation (work in progress).

Storage Options

Control whether extractions are saved to your extraction library:

Field	Type	Default	Description
`storage.enabled`	boolean	`true`	Whether to persist extraction artifacts. Set to `false` for temporary extractions.
`storage.folder_name`	string	-	Target folder name to save the extraction to. Creates the folder if it doesn’t exist.
`storage.folder_id`	string (uuid)	-	Target folder ID to save the extraction to. Takes precedence over `folder_name`.

Deprecated Fields

The following input fields are deprecated and will be removed in a future version. They are still accepted for backward compatibility.

Field	Replacement
`show_images`	Use `figure_processing.show_images`
`chunking`	Use `extensions.chunking.chunk_types` (array instead of comma-separated string)
`chunk_size`	Use `extensions.chunking.chunk_size`
`return_html`	Use `extensions.alt_outputs.return_html`
`structured_output`	Use `/schema` endpoint after extraction. Pass `extraction_id` + `schema_config`. Accepts `schema`, `schema_prompt`, and `effort`.
`schema`	Use `/schema` endpoint after extraction
`schema_prompt`	Use `/schema` endpoint with `schema_config.schema_prompt`
`custom_prompt`	No replacement
`thinking`	No replacement

When legacy input fields are used, the API returns a deprecation warning in the warnings array directing you to the updated field names. See the latest documentation for details.

Response

When you submit a document for async extraction, you’ll receive a response containing the job metadata:

{
  "job_id": "abc123-def456-ghi789",
  "status": "pending",
  "queuedAt": "2025-01-15T10:30:00Z"
}

Response Fields

Field	Type	Description
`job_id`	string	Unique identifier for the extraction job. Use this to poll for results with the Poll Job endpoint.
`status`	string	Initial job status. Typically `pending` when first submitted.
`queuedAt`	string	ISO 8601 timestamp indicating when the job was accepted.

Retrieving Results

After submitting an async extraction, poll the job status endpoint to retrieve results:

GET /job/{job_id}

The job status endpoint will return the extraction results once the job is completed. See the Poll Job documentation for details on the response structure.

For detailed information on the extraction output format (markdown, bounding boxes, chunks, etc.), see the Extract documentation.

Example Usage

Submit Async Extraction

import time
from pulse import Pulse

client = Pulse(api_key="YOUR_API_KEY")

# Submit async extraction
submission = client.extract_async(
    file_url="https://platform.runpulse.com/api/examples/637e5678-30b1-45fa-acc4-877f2d636419/pdf"
)

print(f"Job ID: {submission.job_id}")
print(f"Status: {submission.status}")

# Poll for completion
job_id = submission.job_id
while True:
    job_status = client.jobs.get_job(job_id=job_id)
    print(f"Status: {job_status.status}")
    
    if job_status.status == "completed":
        print("Extraction complete!")
        print(f"Result: {job_status.result}")
        break
    elif job_status.status in ["failed", "canceled"]:
        print(f"Job ended: {job_status.status}")
        if job_status.error:
            print(f"Error: {job_status.error}")
        break
    
    time.sleep(2)

import { PulseClient } from 'pulse-ts-sdk';

const client = new PulseClient({ 
    apiKey: 'YOUR_API_KEY'
});

// Submit async extraction
const submission = await client.extract({
    fileUrl: "https://platform.runpulse.com/api/examples/637e5678-30b1-45fa-acc4-877f2d636419/pdf",
    async: true
});

console.log(`Job ID: ${submission.job_id}`);
console.log(`Status: ${submission.status}`);

// Poll for completion
const jobId = submission.job_id;
while (true) {
    const jobStatus = await client.jobs.getJob({ jobId });
    console.log(`Status: ${jobStatus.status}`);
    
    if (jobStatus.status === 'completed') {
        console.log('Extraction complete!');
        console.log(`Result: ${JSON.stringify(jobStatus.result)}`);
        break;
    } else if (jobStatus.status === 'failed' || jobStatus.status === 'canceled') {
        console.log(`Job ended: ${jobStatus.status}`);
        if (jobStatus.error) {
            console.log(`Error: ${jobStatus.error}`);
        }
        break;
    }
    
    await new Promise(resolve => setTimeout(resolve, 2000));
}

# Submit async extraction with file upload
curl -X POST https://api.runpulse.com/extract_async \
  -H "x-api-key: YOUR_API_KEY" \
  -F "file=@document.pdf"

# Submit async extraction with URL
curl -X POST https://api.runpulse.com/extract_async \
  -H "x-api-key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"file_url": "https://platform.runpulse.com/api/examples/637e5678-30b1-45fa-acc4-877f2d636419/pdf"}'

# Response
# {"job_id": "abc123", "status": "pending", "queuedAt": "2025-01-15T10:30:00Z"}

# Poll for results
curl https://api.runpulse.com/job/abc123 \
  -H "x-api-key: YOUR_API_KEY"

With Structured Output

schema = {
    "type": "object",
    "properties": {
        "total": {"type": "number"},
        "vendor": {"type": "string"}
    }
}

submission = client.extract_async(
    file_url="https://platform.runpulse.com/api/examples/637e5678-30b1-45fa-acc4-877f2d636419/pdf",
    structured_output={
        "schema": schema,
        "schema_prompt": "Extract the invoice total"
    }
)

const submission = await client.extract({
    fileUrl: "https://platform.runpulse.com/api/examples/637e5678-30b1-45fa-acc4-877f2d636419/pdf",
    async: true,
    structuredOutput: {
        schema: {
            type: "object",
            properties: {
                total: { type: "number" },
                vendor: { type: "string" }
            }
        },
        schemaPrompt: "Extract the invoice total"
    }
});

curl -X POST https://api.runpulse.com/extract_async \
  -H "x-api-key: YOUR_API_KEY" \
  -F "file=@invoice.pdf" \
  -F 'structured_output={"schema": {"type": "object", "properties": {"total": {"type": "number"}}}, "schema_prompt": "Extract the invoice total"}'

Cancel a Job

# Cancel a running job
cancellation = client.jobs.cancel_job(job_id=job_id)
print(f"Cancelled: {cancellation.message}")

# Verify cancellation
status = client.jobs.get_job(job_id=job_id)
print(f"Status: {status.status}")  # Should be "canceled"

// Cancel a running job
const cancellation = await client.jobs.cancelJob({ jobId });
console.log(`Cancelled: ${cancellation.message}`);

// Verify cancellation
const status = await client.jobs.getJob({ jobId });
console.log(`Status: ${status.status}`);  // Should be "canceled"

# Cancel a job
curl -X DELETE https://api.runpulse.com/job/abc123 \
  -H "x-api-key: YOUR_API_KEY"

Authorizations

x-api-key

string

header

required

Body

multipart/form-data

Input schema for extraction requests. Provide either file (direct upload) or fileUrl (remote URL).

file

Document to upload directly. Required unless fileUrl is provided.

fileUrl

string<uri>

Public or pre-signed URL that Pulse will download and extract. Required unless file is provided.

model

enum<string>

Extraction model to use. When set to pulse-ultra-2, routes the request through Pulse Ultra 2 (self-hosted VPC model) instead of the default cloud-based service. If omitted or set to default, the default model is used.

Available options:

default,

pulse-ultra-2

detectSelections

boolean

Pulse Ultra 2 only. Enables a specialized selection-mark detection pass that improves selected/unselected state accuracy for forms, checkboxes, radio buttons, handwritten checkmarks, X marks, and similar controls. Enabled by default when model is pulse-ultra-2; set to false to skip this pass. Passing true without model: pulse-ultra-2 returns a validation error.

extractionConfigId

string<uuid>

UUID of a saved extraction configuration (a "preset"). When provided, the server loads the saved configuration and applies its options on top of any inline parameters supplied in this request. Inline parameters always take precedence over preset values for the same field. Saved configs are managed via the platform UI or the input_extractions admin endpoints.

pages

string

Page range filter supporting segments such as 1-2 or mixed ranges like 1-2,5.

Pattern: ^[0-9]+(-[0-9]+)?(,[0-9]+(-[0-9]+)?)*$

forceUrl

boolean

default:false

When true, return the complete extraction result as a URL even if it is small. Spreadsheet extractions use URL delivery by default; set force_url: false to request inline spreadsheet output. URL delivery changes only the transport, not the result shape.

figureProcessing

object

Settings that control how figures and embedded visuals are processed. Applies to both PDFs/images (where figures are detected from layout) and spreadsheets (where charts and embedded images are read directly from the workbook). These options affect the markdown output and the bounding_boxes.Images[] array; they do not produce additional output fields elsewhere in the response.

Show child attributes

extensions

object

Settings that enable additional processing passes or alternate output formats. Each enabled extension produces a corresponding output field under response.extensions.*.

Show child attributes

spreadsheet

object

Settings for Excel/spreadsheet extraction. Controls handling of hidden rows, columns, and sheets, whether numeric cells are rendered using their display format or underlying raw value, whether table cell metadata is captured, and optional trimming of empty phantom rows/columns past the last data-bearing cell. Applies to .xlsx, .xlsm, and .xls files. Accepts both camelCase and snake_case field names.

Show child attributes

storage

object

Options for persisting extraction artifacts. When enabled (default), artifacts are saved to storage and a database record is created.

Show child attributes

async

boolean

default:false

If true, returns immediately with a job_id for polling via GET /job/{jobId}. Otherwise processes synchronously.

structuredOutput

object

deprecated

⚠️ DEPRECATED — Use the /schema endpoint after extraction instead. Pass the extraction_id from the extract response to /schema with your schema_config. This parameter still works for backward compatibility but will be removed in a future version.

Show child attributes

schema

deprecated

(Deprecated) JSON schema describing structured data to extract. Use structuredOutput instead. Accepts either a JSON object or a stringified JSON representation.

schemaPrompt

string

deprecated

(Deprecated) Natural language prompt for schema-guided extraction. Use structuredOutput.schemaPrompt instead.

customPrompt

string

deprecated

(Deprecated) Custom instructions that augment the default extraction behaviour. Use figureProcessing or extensions instead.

chunking

string

deprecated

⚠️ DEPRECATED — Use extensions.chunking.chunkTypes instead. Comma-separated list of chunking strategies to apply (for example semantic,header,page,recursive). Still accepted for backward compatibility.

chunkSize

integer

deprecated

⚠️ DEPRECATED — Use extensions.chunking.chunkSize instead. Override for maximum characters per chunk when chunking is enabled.

Required range: x >= 1

extractFigure

boolean

default:false

deprecated

⚠️ DEPRECATED — Toggle to enable figure extraction in results.

figureDescription

boolean

default:false

deprecated

⚠️ DEPRECATED — Use figureProcessing.description instead. Toggle to generate descriptive captions for extracted figures.

showImages

boolean

default:false

deprecated

⚠️ DEPRECATED — Use figureProcessing.showImages instead. Embed base64-encoded images inline in figure tags in the output. Increases response size.

returnHtml

boolean

default:false

deprecated

⚠️ DEPRECATED — Use extensions.altOutputs.returnHtml instead. Whether to include HTML representation alongside markdown in the response.

thinking

boolean

default:false

deprecated

(Deprecated) Enables expanded rationale output for debugging.

Response

Asynchronous extraction job accepted

Acknowledgement returned when a request is submitted for asynchronous processing. Poll GET /job/{job_id} to check status and retrieve results.

job_id

string

required

Identifier assigned to the asynchronous job.

status

enum<string>

required

Initial status reported by the server.

Available options:

pending,

processing,

completed,

failed,

canceled

message

string

Human-readable description of the accepted job.

queuedAt

string<date-time>

deprecated

Deprecated — Timestamp indicating when the job was accepted. Retained for backward compatibility. Use GET /job/{jobId} for timing details.

credits_used

number<float> | null

Number of credits consumed by this request. Only present when the organization has the credit billing system enabled.

API Reference

Pipeline Steps

Batch & Pipelines

Forms

Jobs, Results & Webhooks

Account & Usage

Legacy Support

Extract File Async (Deprecated)

Overview

Migration

Request

Document Source

Extraction Options

Figure Processing

Spreadsheet Options

Phantom-cell trimming (`only_data_rows` / `only_data_cols`)

Pulse Ultra 2 Options

Selection mark detection

Markdown output additions

Extensions

Storage Options

Deprecated Fields

Response

Response Fields

Retrieving Results

Example Usage

Submit Async Extraction

With Structured Output

Cancel a Job

Authorizations

Body

Response

​Overview

​Migration

​Request

​Document Source

​Extraction Options

​Figure Processing

​Spreadsheet Options

​Phantom-cell trimming (only_data_rows / only_data_cols)

​Pulse Ultra 2 Options

​Selection mark detection

​Markdown output additions

​Extensions

​Storage Options

​Deprecated Fields

​Response

​Response Fields

​Retrieving Results

​Example Usage

​Submit Async Extraction

​With Structured Output

​Cancel a Job

Authorizations

Body

Response

Overview

Migration

Request

Document Source

Extraction Options

Figure Processing

Spreadsheet Options

Phantom-cell trimming (`only_data_rows` / `only_data_cols`)

Pulse Ultra 2 Options

Selection mark detection

Markdown output additions

Extensions

Storage Options

Deprecated Fields

Response

Response Fields

Retrieving Results

Example Usage

Submit Async Extraction

With Structured Output

Cancel a Job