Manage Datasets

Datasets can be used to track test cases you would like to evaluate your LLM on. Each dataset is made up of dictionary with any key value pairs. When getting started, we recommend having an input and optional expected_output fields for example. These datasets can be created from:

• Python SDK: You can use the Python SDK to create an dataset and add items to it.
• Traces table: You can add existing logged traces (from a production application for example) to a dataset.
• The Opik UI: You can manually create a dataset and add items to it.

Once a dataset has been created, you can run Experiments on it. Each Experiment will evaluate an LLM application based on the test cases in the dataset using an evaluation metric and report the results back to the dataset.

Creating a dataset using the SDK

You can create a dataset and log items to it using the get_or_create_dataset method:

from opik import Opik

# Create a dataset
client = Opik()
dataset = client.get_or_create_dataset(name="My dataset")

If a dataset with the given name already exists, the existing dataset will be returned.

Insert items

Inserting dictionary items

You can insert items to a dataset using the insert method:

from opik import Opik

# Get or create a dataset
client = Opik()
dataset = client.get_or_create_dataset(name="My dataset")

# Add dataset items to it
dataset.insert([
    {"user_question": "Hello, world!", "expected_output": {"assistant_answer": "Hello, world!"}},
    {"user_question": "What is the capital of France?", "expected_output": {"assistant_answer": "Paris"}},
])

tip

Opik automatically deduplicates items that are inserted into a dataset when using the Python SDK. This means that you can insert the same item multiple times without duplicating it in the dataset. This combined with the get_or_create_dataset method means that you can use the SDK to manage your datasets in a "fire and forget" manner.

Once the items have been inserted, you can view them them in the Opik UI:

Inserting items from a JSONL file

You can also insert items from a JSONL file:

dataset.read_jsonl_from_file("path/to/file.jsonl")

The format of the JSONL file should be a JSON object per line. For example:

{"user_question": "Hello, world!"}
{"user_question": "What is the capital of France?", "expected_output": {"assistant_answer": "Paris"}}

Inserting items from a Pandas DataFrame

You can also insert items from a Pandas DataFrame:

dataset.insert_from_pandas(dataframe=df, keys_mapping={"Expected output": "expected_output"})

The keys_mapping parameter maps the column names in the DataFrame to the keys in the dataset items, if you want to insert the columns Expected output as an expected and user_question to the input:

dataset.insert_from_pandas(dataframe=df, keys_mapping={"Expected output": "expected_output", "user_question": "input"})

Deleting items

You can delete items in a dataset by using the delete method:

from opik import Opik

# Get or create a dataset
client = Opik()
dataset = client.get_dataset(name="My dataset")

dataset.delete(items_ids=["123", "456"])

tip

You can also remove all the items in a dataset by using the clear method:

from opik import Opik

# Get or create a dataset
client = Opik()
dataset = client.get_dataset(name="My dataset")

dataset.clear()

Downloading a dataset from Opik

You can download a dataset from Opik using the get_dataset method:

from opik import Opik

client = Opik()
dataset = client.get_dataset(name="My dataset")

Once the dataset has been retrieved, you can access it's items using the to_pandas() or to_json methods:

from opik import Opik

client = Opik()
dataset = client.get_dataset(name="My dataset")

# Convert to a Pandas DataFrame
dataset.to_pandas()

# Convert to a JSON array
dataset.to_json()