Use a Python SDK to Interact with deepset Cloud

Use your local environment to interact with deepset Cloud. You can also use Jupyter Notebooks from deepset Cloud.


You must be an Admin user to perform this task.

About This Task

You can use Python methods to work with pipelines, manage your data, and run experiments in deepset Cloud from your local environment.

You can also work in Jupyter notebooks directly from deepset Cloud, just click Notebooks on the dashboard. Once you're done, you can easily share your work by dragging your notebook to your organization shared folder in Jupyter Lab called your organization - shared.


Server restart

If the Notebooks server closes while you're still working, all the files you saved are still there. When you restart the server, you'll be able to work on them again.


  • If you work from your local SDK, you must have Haystack installed. For more information, see Haystack Installation. If you use Jupyter Notebooks in deepset Cloud, you don't have to worry about that.
  • Add API endpoint and API key to the environment variables. The API endpoint is <>. See Generate an API Key.

SDK Methods

See the Reference documentation for available methods: