Integrate Label Studio, a leading open-source annotation platform, with ZenML to seamlessly incorporate data annotation into your ML workflows. This integration enables efficient labeling of diverse data types, including images, audio, text, and time series, directly within ZenML pipelines.
# Setup Label Studio integration
# 1. Create a secret with your Label Studio API key:
# zenml secret create label_studio_secrets --api_key="<your_label_studio_api_key>"
# 2. Register the Label Studio annotator:
# zenml annotator register label_studio --flavor label_studio --authentication_secret="label_studio_secrets"
# 3. Update your stack with the Label Studio annotator:
# zenml stack update -an label_studio
from zenml import pipeline, step
from typing import Dict, Any
from zenml.client import Client
@step
def data_loader() -> Dict[str, Any]:
"""Load labeled data from the active annotator."""
client = Client()
annotator = client.active_stack.annotator
return annotator.get_labeled_data(dataset_name="my_dataset")
@pipeline
def my_pipeline():
"""Define the pipeline using the data loader step."""
data = data_loader()
# Process the labeled data here
if __name__ == "__main__":
my_pipeline()
# Additional CLI commands for working with Label Studio:
# - List all datasets:
# zenml annotator dataset list
# - Get statistics for a specific dataset:
# zenml annotator dataset stats <dataset_id>
Expand your ML pipelines with more than 50 ZenML Integrations
