Upload dataset from JSON, JSONL, CSV, or PyArrow

POST /v1/datasets/upload

Upload dataset from JSON, JSONL, CSV, or PyArrow

cURL

curl --request POST \
  --url https://api.example.com/v1/datasets/upload \
  --header 'Content-Type: application/json' \
  --data '
{
  "name": "<string>",
  "inputs": [
    {}
  ],
  "description": "<string>",
  "outputs": [
    {}
  ],
  "metadata": [
    {}
  ],
  "splits": [
    "<string>"
  ],
  "span_ids": [
    "<string>"
  ],
  "example_ids": [
    "<string>"
  ]
}
'

import requests

url = "https://api.example.com/v1/datasets/upload"

payload = {
    "name": "<string>",
    "inputs": [{}],
    "description": "<string>",
    "outputs": [{}],
    "metadata": [{}],
    "splits": ["<string>"],
    "span_ids": ["<string>"],
    "example_ids": ["<string>"]
}
headers = {"Content-Type": "application/json"}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {'Content-Type': 'application/json'},
  body: JSON.stringify({
    name: '<string>',
    inputs: [{}],
    description: '<string>',
    outputs: [{}],
    metadata: [{}],
    splits: ['<string>'],
    span_ids: ['<string>'],
    example_ids: ['<string>']
  })
};

fetch('https://api.example.com/v1/datasets/upload', 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.example.com/v1/datasets/upload",
  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([
    'name' => '<string>',
    'inputs' => [
        [
                
        ]
    ],
    'description' => '<string>',
    'outputs' => [
        [
                
        ]
    ],
    'metadata' => [
        [
                
        ]
    ],
    'splits' => [
        '<string>'
    ],
    'span_ids' => [
        '<string>'
    ],
    'example_ids' => [
        '<string>'
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "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.example.com/v1/datasets/upload"

	payload := strings.NewReader("{\n  \"name\": \"<string>\",\n  \"inputs\": [\n    {}\n  ],\n  \"description\": \"<string>\",\n  \"outputs\": [\n    {}\n  ],\n  \"metadata\": [\n    {}\n  ],\n  \"splits\": [\n    \"<string>\"\n  ],\n  \"span_ids\": [\n    \"<string>\"\n  ],\n  \"example_ids\": [\n    \"<string>\"\n  ]\n}")

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

	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.example.com/v1/datasets/upload")
  .header("Content-Type", "application/json")
  .body("{\n  \"name\": \"<string>\",\n  \"inputs\": [\n    {}\n  ],\n  \"description\": \"<string>\",\n  \"outputs\": [\n    {}\n  ],\n  \"metadata\": [\n    {}\n  ],\n  \"splits\": [\n    \"<string>\"\n  ],\n  \"span_ids\": [\n    \"<string>\"\n  ],\n  \"example_ids\": [\n    \"<string>\"\n  ]\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.example.com/v1/datasets/upload")

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

request = Net::HTTP::Post.new(url)
request["Content-Type"] = 'application/json'
request.body = "{\n  \"name\": \"<string>\",\n  \"inputs\": [\n    {}\n  ],\n  \"description\": \"<string>\",\n  \"outputs\": [\n    {}\n  ],\n  \"metadata\": [\n    {}\n  ],\n  \"splits\": [\n    \"<string>\"\n  ],\n  \"span_ids\": [\n    \"<string>\"\n  ],\n  \"example_ids\": [\n    \"<string>\"\n  ]\n}"

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

200

{
  "data": {
    "dataset_id": "<string>",
    "version_id": "<string>",
    "num_created_examples": 123,
    "num_updated_examples": 123,
    "num_deleted_examples": 123
  }
}

"<string>"

"<string>"

"<string>"

Query Parameters

sync · boolean · default: false

If true, fulfill request synchronously and return JSON containing dataset_id.

Body

application/jsonmultipart/form-data

name · string · required

inputs · object[] · required

action · enum<string>

Available options: create, append, update

description · string

outputs · object[]

metadata · object[]

splits · (string | string[] | null)[]

Split per example: string, string array, or null

span_ids · (string | null)[]

Span IDs to link examples back to spans

example_ids · (string | null)[]

Optional example ID per example. If provided, it is used as the example's stable public ID.

Response

200

application/json

UploadDatasetResponseBody · object | null

Successful Response

data · UploadDatasetData · object · required

Show child attributes