You can create a dataset and add rows programmatically using our Python SDK.

If you are using any other language, then you can do so through some simple API requests.

​
Create Dataset via SDK

1. Install the athina package

pip install athina-client

2. Set your API keys

If you are using the python SDK, then can set the API keys like this:

import os
from athina_client.keys import AthinaApiKey

AthinaApiKey.set_key(os.getenv('ATHINA_API_KEY'))

3. Create a dataset and log it to athina

from athina_client.datasets import Dataset

try:
  dataset = Dataset.create(
    name='test_dataset',
    description="Optional description", # optional
    language_model_id="gpt-4", # optional
  )
except Exception as e:
  print(f"Failed to create dataset: {e}")

The name of the dataset must be unique, otherwise the request will throw an exception.

4. Add rows to the dataset

try:
  Dataset.add_rows(
      dataset_id=dataset.id,
      rows=[
          {
              'query': 'What is the capital of France?',
              'context': ['France is a country in Western Europe.', 'Paris is the capital of France.'],
              'response': 'Paris',
              'expected_response': 'Paris'
          },
      ]
  )
except Exception as e:
    print(f"Failed to add rows: {e}")

You can also find the dataset_id from the URL when you open the dataset through https://app.athina.ai/develop.

Currently, a dataset can have a maximum of 1000 rows. If the number of rows > 1000, the API will return an exception with status code 400.

Create a Dataset from a File UploadCreate a Dataset via API request