On Quotient, datasets are collections of structured data that enable you to store, manage, and organize rows of information for evaluation or reference within QuotientAI. Each dataset consists of rows, where each row includes fields for input, context, expected output, and optional metadata for annotations.

​
Creating a New Dataset

To create a new dataset, use the create() method. You can specify a name, an optional description, and optional list of rows.

new_dataset = quotient.datasets.create(
    name="Sample Dataset",
    description="My first dataset",
    rows=[
        {"input": "Sample input", "expected": "Sample output"},
        {"input": "Another input", "expected": "Another output"}
    ]
)

print(new_dataset)

​
Listing Datasets

To list all available datasets, use the list() method. This method returns a collection of Dataset objects, each containing details like id, name, description, and timestamps.

from quotientai import QuotientAI

quotient = QuotientAI()

datasets = quotient.datasets.list()

for dataset in datasets:
    print(dataset)

​
Retrieving a Specific Dataset

To get the details of a specific dataset by its ID along with its rows, use the get() method.

dataset_id = quotient.datasets.list()[0].id
dataset = quotient.datasets.get(dataset_id)

print(dataset)

​
Updating an Existing Dataset

To update a dataset, use the update() method. This can modify the dataset’s metadata.

updated_dataset = quotient.datasets.update(
    dataset=new_dataset,
    name="my new dataset name",
    description="a different description",
)

print(updated_dataset)

​
Appending Rows to an Existing Dataset

To add rows to an existing dataset, use the append() method. This allows you to extend the dataset by adding new rows.

extended_dataset = quotient.datasets.append(
    dataset=new_dataset,
    rows=[{"input": "New input", "expected": "New output"}]
)

print(extended_dataset)

​
Deleting a Dataset

To delete a dataset, use the delete() method. Pass in the Dataset object you intend to delete.

quotient.datasets.delete(new_dataset)

print("dataset deleted successfully!")
PromptsPython SDK