IBM watsonx.ai for IBM Cloud
============================

Requirements
------------
For information on how to start working with IBM watsonx.ai for IBM Cloud, refer to `Getting started with Cloud Pak for Data as a Service <https://dataplatform.cloud.ibm.com/docs/content/wsj/getting-started/get-started-wdp.html?audience=wdp&context=wx>`_.

Supported machine learning frameworks
-------------------------------------
For a list of supported machine learning frameworks (models) on IBM watsonx.ai for IBM Cloud, refer to `Supported frameworks and software specifications <https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/pm_service_supported_frameworks.html?context=wx&audience=wdp&locale=en>`_.

Authentication
--------------
To use watsonx.ai APIs, create an instance of APIClient with authentication details.

**Note:** Depending on the region of your provisioned service instance, use one of the following as your URL:

    * Dallas: ``https://us-south.ml.cloud.ibm.com``
    * London: ``https://eu-gb.ml.cloud.ibm.com``
    * Frankfurt: ``https://eu-de.ml.cloud.ibm.com``
    * Tokyo: ``https://jp-tok.ml.cloud.ibm.com``
    * Sydney: ``https://au-syd.ml.cloud.ibm.com`` (supported in ``1.1.23`` and newer)

**Note:** To determine your `api_key`, refer to `IBM Cloud console API keys <https://cloud.ibm.com/iam/apikeys>`_.

Example of creating the client using an API key:

.. code-block:: python

   from ibm_watsonx_ai import APIClient
   from ibm_watsonx_ai import Credentials

   credentials = Credentials(
                      url = "https://us-south.ml.cloud.ibm.com",
                      api_key = IAM_API_KEY
                     )

   client = APIClient(credentials)




Example of creating the client using a token:

.. code-block:: python

   from ibm_watsonx_ai import APIClient
   from ibm_watsonx_ai import Credentials

   credentials = Credentials(
                      url = "https://us-south.ml.cloud.ibm.com",
                      token = "***********",
                     )

   client = APIClient(credentials)

**Note:** Setting a default space ID or project ID is mandatory. For details, refer to the ``client.set.default_space()`` API in this document.

.. hint::
    You can copy the project_id from the Project's Manage tab (Project -> Manage -> General -> Details).

Firewall settings
-----------------
Although the above setup is sufficient for most environments, environments behind a firewall may need an additional adjustment.
The following endpoints are used by ``ibm-watsonx-ai`` and need to be whitelisted to ensure correct functioning of the module:

.. code-block::

    https://jp-tok.ml.cloud.ibm.com
    https://eu-gb.ml.cloud.ibm.com
    https://eu-de.ml.cloud.ibm.com
    https://us-south.ml.cloud.ibm.com
    https://au-syd.ml.cloud.ibm.com

    https://api.jp-tok.dataplatform.cloud.ibm.com
    https://api.eu-gb.dataplatform.cloud.ibm.com
    https://api.eu-de.dataplatform.cloud.ibm.com
    https://api.dataplatform.cloud.ibm.com
    https://api.jp-tok.dataplatform.cloud.ibm.com
    https://api.au-syd.dai.cloud.ibm.com

    https://iam.cloud.ibm.com