Manage Datasets

You can manage datasets from the Dashboard UI, the SDK (TypeScript, Python, Java), or the REST API.

From the Dashboard

View Datasets

Datasets list in the dashboard

Navigate to Datasets in the left sidebar.

The dataset list shows one row per dataset with these columns:

Column	Description
Name	Dataset name (click to open detail page)
Items	Number of items in the dataset
Runs	Number of dataset runs
Created	Creation date
Last Run	Date of the most recent run

Use the search bar to filter datasets by name. Pagination defaults to 50 rows per page.

To filter with SQL expressions, click Filters, then switch to the SQL tab. See SQL Filter Mode below.

SQL Filter Mode

The Datasets table supports a SQL filter tab that accepts SQL WHERE-clause expressions for filtering by name, item count, run count, and dates.

The Datasets SQL filter supports AND conditions only. Top-level OR (e.g. name = 'a' OR name = 'b') is not supported on this table.

Available columns:

Column	Type	Notes
`name`	string	Dataset name
`items`	number	Number of items
`runs`	number	Number of runs
`created_at`	datetime	Creation timestamp
`last_run`	datetime	Most recent run timestamp

Example expressions:

-- Filter by name
name = 'qa-golden-set'

-- Recently created datasets
created_at > '2025-01-01'

-- Datasets with items
items > 0

-- Name AND item count
name LIKE '%golden%' AND items > 10

To use the SQL filter:

SQL filter for the Datasets list

Click Filters at the top of the Datasets list.

Select the SQL tab in the filter popover.

Type your expression and click Apply. The filtered URL is shareable.

Create a Dataset

Click New Dataset in the top-right of the Datasets page.

Fill in the form:

Name (required) — unique dataset name
Description (optional) — free-form notes about the dataset
Metadata (optional) — JSON key-value pairs for custom metadata

Click Create dataset. You'll be taken to the new dataset's detail page.

Dataset Detail Page

Click any dataset name to open its detail page. The page has three tabs:

Items — view, add, import, and manage dataset items (see Dataset Items)
Runs — view and create dataset runs (see Dataset Runs)
Linked Experiments — experiments that reference this dataset

Dataset Actions

Click the more menu (three dots) on the dataset detail page for:

Rename — update the dataset name and description
Duplicate Dataset — create a copy of the entire dataset with all items
Delete — permanently remove the dataset and all its items

From the SDK

Setup

import { AISDK } from '@browserstack/ai-sdk';

const testOps = new AISDK({
  publicKey: process.env.AISDK_PUBLIC_KEY,
  secretKey: process.env.AISDK_SECRET_KEY,
});

const datasets = testOps.datasets;       // DatasetsClient
const datasetRuns = testOps.datasetRuns; // DatasetRuns

import os
from browserstack_ai_sdk import AISDK

client = AISDK(
    public_key=os.environ["AISDK_PUBLIC_KEY"],
    secret_key=os.environ["AISDK_SECRET_KEY"],
)

datasets = testOps.datasets;       # datasets client

import com.browserstack.aisdk.AISDK;
import com.browserstack.aisdk.eval.DatasetsClient;
import com.browserstack.aisdk.eval.model.*;

AISDK sdk = AISDK.fromEnv();
DatasetsClient datasets = sdk.datasets();

Create a Dataset

const dataset = await datasets.create(
  'qa-golden-set',
  'Golden set for QA evaluation',
  { owner: 'ml-team', version: '1.0' } // optional metadata
);

console.log(dataset.id);   // dataset ID
console.log(dataset.name); // 'qa-golden-set'

dataset = client.datasets.create(
    name="qa-dataset-v1",
    description="Question-answer pairs for RAG evaluation",
    metadata='{"domain": "customer-support"}',
)
print(dataset)

// Name only
DatasetResponse ds = datasets.create("my-dataset");

// With description
DatasetResponse ds = datasets.create("my-dataset", "Questions about Northern Lights");

// With metadata
DatasetResponse ds = datasets.create(
    "my-dataset",
    "Questions about Northern Lights",
    Map.of("team", "nlp", "domain", "science")
);

System.out.println("Created: " + ds.getId() + " — " + ds.getName());

List Datasets

const result = await datasets.list(
  1,           // page (1-indexed)
  20,          // limit per page
  'qa'         // optional name filter
);

for (const ds of result.data) {
  console.log(ds.id, ds.name);
}

result = client.datasets.list(page=1, limit=20)

for dataset in result["data"]:
    print(f"{dataset.get('name')}: {dataset.get('id')}")

Filter by name:

datasets = client.datasets.list(name="qa-dataset-v1")

// Default (page 1, limit 50)
ListDatasetsResponse list = datasets.list();

// With pagination
ListDatasetsResponse list = datasets.list(1, 20);

// Filtered by name
ListDatasetsResponse list = datasets.list(1, 20, "my-dataset");

list.getData().forEach(d -> System.out.println(d.getId() + " " + d.getName()));

Get Dataset Tags

const tagsResult = await datasets.getTags('qa-golden-set');
console.log(tagsResult.tags); // string[]

tags = client.datasets.get_tags("qa-dataset-v1")
print(tags)

List<String> tags = datasets.getTags("my-dataset");
System.out.println("Tags: " + tags);

Manage Datasets

On this page