Async parsing — Submit Task

import json
import requests

url = "https://somark.ai/api/v1/parse/async"

data = {
    "output_formats": ["markdown", "json"],
    "api_key": "sk-***",
    "element_formats": json.dumps({
        "image": "url",
        "formula": "latex",
        "table": "html",
        "cs": "image",
    }),
    "feature_config": json.dumps({
        "enable_text_cross_page": False,
        "enable_table_cross_page": False,
        "enable_title_level_recognition": False,
        "enable_inline_image": False,
        "enable_table_image": True,
        "enable_image_understanding": True,
        "keep_header_footer": False,
    }),
}

files = {"file": ("example.pdf", open("example.pdf", "rb"))}

response = requests.post(url, data=data, files=files)
task_id = response.json()["data"]["task_id"]
print(f"任务已提交，task_id: {task_id}")

curl -X POST https://somark.ai/api/v1/parse/async \
  -F "file=@example.pdf" \
  -F "output_formats=markdown" \
  -F "output_formats=json" \
  -F "api_key=sk-***" \
  -F 'element_formats={"image":"url","formula":"latex","table":"html","cs":"image"}' \
  -F 'feature_config={"enable_text_cross_page":false,"enable_table_cross_page":false,"enable_title_level_recognition":false,"enable_inline_image":false,"enable_table_image":true,"enable_image_understanding":true,"keep_header_footer":false}'

const form = new FormData();
form.append('api_key', '<string>');
form.append('file', '<string>');
form.append('file_url', '<string>');
form.append('output_formats[0]', 'markdown');
form.append('output_formats[1]', 'json');
form.append('element_formats', '{
  "image": "url",
  "formula": "latex",
  "table": "html",
  "cs": "image"
}');
form.append('feature_config', '{
  "enable_text_cross_page": false,
  "enable_table_cross_page": false,
  "enable_title_level_recognition": false,
  "enable_inline_image": false,
  "enable_table_image": true,
  "enable_image_understanding": true,
  "keep_header_footer": false
}');

const options = {method: 'POST'};

options.body = form;

fetch('https://somark.ai/api/v1/parse/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://somark.ai/api/v1/parse/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=\"api_key\"\r\n\r\n<string>\r\n-----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=\"file_url\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"output_formats%5B0%5D\"\r\n\r\nmarkdown\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"output_formats%5B1%5D\"\r\n\r\njson\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"element_formats\"\r\n\r\n{\r\n  \"image\": \"url\",\r\n  \"formula\": \"latex\",\r\n  \"table\": \"html\",\r\n  \"cs\": \"image\"\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"feature_config\"\r\n\r\n{\r\n  \"enable_text_cross_page\": false,\r\n  \"enable_table_cross_page\": false,\r\n  \"enable_title_level_recognition\": false,\r\n  \"enable_inline_image\": false,\r\n  \"enable_table_image\": true,\r\n  \"enable_image_understanding\": true,\r\n  \"keep_header_footer\": false\r\n}\r\n-----011000010111000001101001--",
  CURLOPT_HTTPHEADER => [
    "Content-Type: multipart/form-data; boundary=---011000010111000001101001"
  ],
]);

$response = curl_exec($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://somark.ai/api/v1/parse/async"

	payload := strings.NewReader("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"api_key\"\r\n\r\n<string>\r\n-----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=\"file_url\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"output_formats%5B0%5D\"\r\n\r\nmarkdown\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"output_formats%5B1%5D\"\r\n\r\njson\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"element_formats\"\r\n\r\n{\r\n  \"image\": \"url\",\r\n  \"formula\": \"latex\",\r\n  \"table\": \"html\",\r\n  \"cs\": \"image\"\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"feature_config\"\r\n\r\n{\r\n  \"enable_text_cross_page\": false,\r\n  \"enable_table_cross_page\": false,\r\n  \"enable_title_level_recognition\": false,\r\n  \"enable_inline_image\": false,\r\n  \"enable_table_image\": true,\r\n  \"enable_image_understanding\": true,\r\n  \"keep_header_footer\": false\r\n}\r\n-----011000010111000001101001--")

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

	req.Header.Add("Content-Type", "multipart/form-data; boundary=---011000010111000001101001")

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

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

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://somark.ai/api/v1/parse/async")
  .header("Content-Type", "multipart/form-data; boundary=---011000010111000001101001")
  .body("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"api_key\"\r\n\r\n<string>\r\n-----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=\"file_url\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"output_formats%5B0%5D\"\r\n\r\nmarkdown\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"output_formats%5B1%5D\"\r\n\r\njson\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"element_formats\"\r\n\r\n{\r\n  \"image\": \"url\",\r\n  \"formula\": \"latex\",\r\n  \"table\": \"html\",\r\n  \"cs\": \"image\"\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"feature_config\"\r\n\r\n{\r\n  \"enable_text_cross_page\": false,\r\n  \"enable_table_cross_page\": false,\r\n  \"enable_title_level_recognition\": false,\r\n  \"enable_inline_image\": false,\r\n  \"enable_table_image\": true,\r\n  \"enable_image_understanding\": true,\r\n  \"keep_header_footer\": false\r\n}\r\n-----011000010111000001101001--")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://somark.ai/api/v1/parse/async")

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

request = Net::HTTP::Post.new(url)
request["Content-Type"] = 'multipart/form-data; boundary=---011000010111000001101001'
request.body = "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"api_key\"\r\n\r\n<string>\r\n-----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=\"file_url\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"output_formats%5B0%5D\"\r\n\r\nmarkdown\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"output_formats%5B1%5D\"\r\n\r\njson\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"element_formats\"\r\n\r\n{\r\n  \"image\": \"url\",\r\n  \"formula\": \"latex\",\r\n  \"table\": \"html\",\r\n  \"cs\": \"image\"\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"feature_config\"\r\n\r\n{\r\n  \"enable_text_cross_page\": false,\r\n  \"enable_table_cross_page\": false,\r\n  \"enable_title_level_recognition\": false,\r\n  \"enable_inline_image\": false,\r\n  \"enable_table_image\": true,\r\n  \"enable_image_understanding\": true,\r\n  \"keep_header_footer\": false\r\n}\r\n-----011000010111000001101001--"

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

{
  "code": 0,
  "message": "任务已提交",
  "data": {
    "task_id": "c5e6c983f28a4e6eb5d6c061343a8642",
    "status": "queuing"
  }
}