> ## Documentation Index
> Fetch the complete documentation index at: https://docs.galtea.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Dataset Service

> Dataset Service API methods in the Galtea SDK

> [!WARNING]
>
> You are reading the docs of Galtea 5.15. [Read this page in the latest version](https://docs.galtea.ai/sdk/api/dataset/service.md).

The Dataset Service in the Galtea SDK allows you to manage [datasets](https://docs.galtea.ai/v5.15/concepts/product/dataset.md) for evaluating your products.
This Service is exposed by the `galtea.datasets` object.

> [!NOTE]
>
> Remember that we will be using the `galtea` object. More information [here](https://docs.galtea.ai/v5.15/sdk/api/galtea.md).

## Quick Example

First, initialize the Galtea SDK:

```python theme={"system"}
galtea = Galtea(api_key="YOUR_API_KEY")
```

Create a dataset:

```python theme={"system"}
dataset = galtea.datasets.create(
    name=dataset_name,
    type="ACCURACY",
    product_id=product_id,
    ground_truth_file_path="path/to/knowledge.md",
    language="english",
    max_test_cases=5,
)
```

List datasets for a product:

```python theme={"system"}
datasets = galtea.datasets.list(product_id=product_id, limit=10)
```

Get a dataset by ID:

```python theme={"system"}
dataset = galtea.datasets.get(dataset_id=dataset_id)
```

## Service Methods

* [Create Dataset](https://docs.galtea.ai/v5.15/sdk/api/dataset/create.md)
* [Listing Datasets](https://docs.galtea.ai/v5.15/sdk/api/dataset/list.md)
* [Retrieving Dataset](https://docs.galtea.ai/v5.15/sdk/api/dataset/get.md)
* [Retrieving Dataset By Name](https://docs.galtea.ai/v5.15/sdk/api/dataset/get-by-name.md)
* [Updating Dataset](https://docs.galtea.ai/v5.15/sdk/api/dataset/update.md)
* [Deleting Dataset](https://docs.galtea.ai/v5.15/sdk/api/dataset/delete.md)
* [Downloading Dataset](https://docs.galtea.ai/v5.15/sdk/api/dataset/download.md)

## Related

> [card] [Dataset](https://docs.galtea.ai/v5.15/concepts/product/dataset.md)
>
> A dataset of test cases for evaluating product performance


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.