You can use Openlayer in or in .

Select the tab below that best describes your use case to get started.

Prerequisites

To follow along with the quickstart, you’ll need an:

  • Development

  • Monitoring

1. Install

pip install openlayer

2. Create or load a project

import openlayer
from openlayer.tasks import TaskType

client = openlayer.OpenlayerClient("YOUR_API_KEY_HERE")

project = client.create_project(
    name="Your project name here",
    task_type=TaskType.TabularClassification, # Refer to the API reference for other task types
)

# Or load an existing project
# project = client.load_project(name="Your project name here")

3. Add datasets to the project’s staging area

# Training dataset
project.add_dataframe(
    dataset_df=training_df,
    dataset_config=traininig_dataset_config
)

# Validation dataset
project.add_dataframe(
    dataset_df=training_df,
    dataset_config=traininig_dataset_config
)

Refer to the dataset config guides for the task of interest for more information about the dataset configs in the code snipped above.

4. Add a model to the project’s staging area

project.add_model(
    model_config=model_config,
)

Refer to the model config guides for the task of interest for more information about the model_config in the code snipped above.

5. Write a commit message and push the staging area to the platform

project.commit("Initial commit!")
project.push()

Colab notebook

See the full source code.

🚀 Head to the Openlayer platform

After running the snippets above, your models and data will be available on the Openlayer platform where you can start setting up tests.

For additional sample notebooks, check out our Examples gallery GitHub repository.

To learn more, you can head to the Guided walkthroughs and Knowledge base.