Add Model Predictions | API Reference

You can add predictions to existing tasks in Label Studio in your Python script.

If you would prefer to set them directly in the script, see Create a Project for an example.

This demo uses the example project from Create a Project. You would need to adjust this to match your labeling configuration.

For example, sentiment maps to <Choices name="sentiment" toName="text" choice="single"> in the labeling configuration we used earlier.

For information on finding your API key and base URL, see Authenticate and Connect to the API.

1 LABEL_STUDIO_URL = 'YOUR_BASE_URL'
2 LABEL_STUDIO_API_KEY = 'YOUR_API_KEY'
3 PROJECT_ID=1    # replace with your project ID 
4 
5 from label_studio_sdk import LabelStudio
6 from label_studio_sdk.label_interface.objects import PredictionValue
7 
8 client = LabelStudio(base_url=LABEL_STUDIO_URL, api_key=LABEL_STUDIO_API_KEY)
9 
10 project = client.projects.get(id=PROJECT_ID)
11 
12 # Get the parsed labeling interface to build valid prediction payloads
13 li = project.get_label_interface()
14 
15 # Iterate tasks and attach predictions
16 for task in client.tasks.list(project=project.id, include=["id"]):
17     # 'label' must match the control tag name in your labeling config
18     predicted_label = li.get_control('sentiment').label(['Positive'])
19 
20     prediction = PredictionValue(
21         model_version="my-super-ai",
22         score=0.99,  # optional
23         result=[predicted_label]
24     )
25 
26     client.predictions.create(task=task.id, **prediction.model_dump())

For another example, see the Jupyter notebook example of importing pre-annotated data.