Create Dataset

Upload a CSV or Parquet file to create a new dataset or add a new version.

POST /datasets

Create Dataset

cURL

curl --request POST \
  --url https://api.woodwide.ai/datasets \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: multipart/form-data' \
  --form file=train.csv \
  --form dataset_name=my_dataset

import requests

url = "https://api.woodwide.ai/datasets"

payload = "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"\r\n\r\ntrain.csv\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"dataset_name\"\r\n\r\nmy_dataset\r\n-----011000010111000001101001--"
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "multipart/form-data"
}

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

print(response.text)

const form = new FormData();
form.append('file', 'train.csv');
form.append('dataset_name', 'my_dataset');

const options = {method: 'POST', headers: {Authorization: 'Bearer <token>'}};

options.body = form;

fetch('https://api.woodwide.ai/datasets', 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.woodwide.ai/datasets",
  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\"\r\n\r\ntrain.csv\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"dataset_name\"\r\n\r\nmy_dataset\r\n-----011000010111000001101001--",
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: multipart/form-data"
  ],
]);

$response = curl_exec($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.woodwide.ai/datasets"

	payload := strings.NewReader("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"\r\n\r\ntrain.csv\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"dataset_name\"\r\n\r\nmy_dataset\r\n-----011000010111000001101001--")

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

	req.Header.Add("Authorization", "Bearer <token>")

	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.woodwide.ai/datasets")
  .header("Authorization", "Bearer <token>")
  .body("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"\r\n\r\ntrain.csv\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"dataset_name\"\r\n\r\nmy_dataset\r\n-----011000010111000001101001--")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.woodwide.ai/datasets")

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request.body = "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"\r\n\r\ntrain.csv\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"dataset_name\"\r\n\r\nmy_dataset\r\n-----011000010111000001101001--"

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

201

{
  "dataset": {
    "id": "a1b2c3d4-0000-0000-0000-000000000001",
    "version_id": "a1b2c3d4-0000-0000-0000-000000000002",
    "version_number": 1
  },
  "job_id": "a1b2c3d4-0000-0000-0000-000000000003",
  "status": "queued"
}

{
  "detail": "Not authenticated"
}

{
  "detail": "Forbidden"
}

{
  "detail": "Not found"
}

{
  "detail": [
    {
      "loc": [
        "<string>"
      ],
      "msg": "<string>",
      "type": "<string>"
    }
  ]
}

{
  "detail": "Rate limit exceeded. Retry after a short delay."
}

Maximum file size is 30 MB. For larger files, use the signed-URL upload flow.

Authorizations

Authorization · string · header · required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

multipart/form-data

file · string · required

The file to upload. Maximum file size: 30 MB.

dataset_name · string

dataset_id · string<uuid>

description · string | null

override · boolean · default: false

When true, replaces the data in the current version instead of creating a new version. Defaults to false.

Response

201

application/json

Successful Response

Response for dataset creation/ingestion.

dataset · DatasetVersionRef · object

Dataset version reference.

Show child attributes

job_id · string<uuid>

status · enum<string>

Available options: initializing, pending, queued, running, succeeded, failed, canceled, rejected, waiting_for_upload