Create dataset from CSV

curl --request POST \
  --url https://catchall.newscatcherapi.com/catchAll/datasets/upload \
  --header 'Content-Type: multipart/form-data' \
  --header 'x-api-key: <api-key>' \
  --form file='@example-file' \
  --form 'name=My Portfolio' \
  --form 'description=Companies from Q1 2026 watchlist'

import requests

url = "https://catchall.newscatcherapi.com/catchAll/datasets/upload"

files = { "file": ("example-file", open("example-file", "rb")) }
payload = {
    "name": "My Portfolio",
    "description": "Companies from Q1 2026 watchlist"
}
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('name', 'My Portfolio');
form.append('description', 'Companies from Q1 2026 watchlist');

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

options.body = form;

fetch('https://catchall.newscatcherapi.com/catchAll/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://catchall.newscatcherapi.com/catchAll/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 => "-----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=\"name\"\r\n\r\nMy Portfolio\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"description\"\r\n\r\nCompanies from Q1 2026 watchlist\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://catchall.newscatcherapi.com/catchAll/datasets/upload"

	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=\"name\"\r\n\r\nMy Portfolio\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"description\"\r\n\r\nCompanies from Q1 2026 watchlist\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://catchall.newscatcherapi.com/catchAll/datasets/upload")
  .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=\"name\"\r\n\r\nMy Portfolio\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"description\"\r\n\r\nCompanies from Q1 2026 watchlist\r\n-----011000010111000001101001--")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://catchall.newscatcherapi.com/catchAll/datasets/upload")

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=\"name\"\r\n\r\nMy Portfolio\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"description\"\r\n\r\nCompanies from Q1 2026 watchlist\r\n-----011000010111000001101001--"

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

{
  "dataset_id": "ccabb755-afc2-4047-b84c-78d1f23d49b2",
  "dataset_name": "My Portfolio",
  "entities_created": 3,
  "validation_report": {
    "total_rows": 4,
    "valid_rows": 3,
    "skipped_count": 1,
    "skipped_rows": [
      {
        "row": 3,
        "reason": "missing required field: name"
      }
    ]
  }
}

{
  "detail": "Invalid API key"
}

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

Datasets

Create dataset from CSV

Creates a new dataset by uploading a CSV file. Each row in the CSV becomes an entity. Each row requires a name plus at least one of: a description or a domain; all other columns are optional. Note: description in the CSV is the entity’s matching description — it is separate from the dataset-level description field in the form data.

CSV format:

name,description,domain,alternative_names,key_persons
NewsCatcher,"NewsCatcher is a data-as-a-service company providing news intelligence APIs including the CatchAll Web Search API (2B+ web pages indexed) and News API (140,000+ sources, 100+ countries).",newscatcherapi.com,"NewsCatcher CatchAll;NewsCatcher API","Artem Bugara;Maksym Sugonyaka"
OpenAI,"Artificial intelligence research company",openai.com,"Open AI","Sam Altman"

Use semicolons (;) to separate multiple values in alternative_names and key_persons. Rows with empty name are skipped and reported in validation_report.

Note: The response shape differs from the JSON dataset creation endpoint: it returns dataset_id (not id) and includes a validation_report with details on skipped rows.

POST

catchAll

datasets

upload

Create dataset from CSV

curl --request POST \
  --url https://catchall.newscatcherapi.com/catchAll/datasets/upload \
  --header 'Content-Type: multipart/form-data' \
  --header 'x-api-key: <api-key>' \
  --form file='@example-file' \
  --form 'name=My Portfolio' \
  --form 'description=Companies from Q1 2026 watchlist'

import requests

url = "https://catchall.newscatcherapi.com/catchAll/datasets/upload"

files = { "file": ("example-file", open("example-file", "rb")) }
payload = {
    "name": "My Portfolio",
    "description": "Companies from Q1 2026 watchlist"
}
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('name', 'My Portfolio');
form.append('description', 'Companies from Q1 2026 watchlist');

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

options.body = form;

fetch('https://catchall.newscatcherapi.com/catchAll/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://catchall.newscatcherapi.com/catchAll/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 => "-----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=\"name\"\r\n\r\nMy Portfolio\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"description\"\r\n\r\nCompanies from Q1 2026 watchlist\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://catchall.newscatcherapi.com/catchAll/datasets/upload"

	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=\"name\"\r\n\r\nMy Portfolio\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"description\"\r\n\r\nCompanies from Q1 2026 watchlist\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://catchall.newscatcherapi.com/catchAll/datasets/upload")
  .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=\"name\"\r\n\r\nMy Portfolio\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"description\"\r\n\r\nCompanies from Q1 2026 watchlist\r\n-----011000010111000001101001--")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://catchall.newscatcherapi.com/catchAll/datasets/upload")

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=\"name\"\r\n\r\nMy Portfolio\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"description\"\r\n\r\nCompanies from Q1 2026 watchlist\r\n-----011000010111000001101001--"

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

{
  "dataset_id": "ccabb755-afc2-4047-b84c-78d1f23d49b2",
  "dataset_name": "My Portfolio",
  "entities_created": 3,
  "validation_report": {
    "total_rows": 4,
    "valid_rows": 3,
    "skipped_count": 1,
    "skipped_rows": [
      {
        "row": 3,
        "reason": "missing required field: name"
      }
    ]
  }
}

{
  "detail": "Invalid API key"
}

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

Authorizations

x-api-key

string

header

required

API key for authentication.

Body

multipart/form-data

file

required

The CSV file to upload.

name

string

required

Name for the new dataset.

Example:

"My Portfolio"

description

string

Optional description for the dataset.

Example:

"Companies from Q1 2026 watchlist"

Response

Dataset created from CSV successfully.

dataset_id

string<uuid>

required

Unique identifier of the created dataset.

Example:

"ccabb755-afc2-4047-b84c-78d1f23d49b2"

dataset_name

string

required

Name of the created dataset.

Example:

"My Portfolio"

entities_created

integer

required

Number of entities successfully created from the CSV.

Example:

3

validation_report

object

required

Summary of CSV processing results.

Show child attributes

Create dataset Get dataset

⌘I