IBM Watsonx AI Integration

Overview

IBM Watson Studio is a toolset for exploring data to build, train, and deploy machine learning models. It integrates various tools, including Jupyter Notebooks, Anaconda, and Apache Spark, and supports both graphical drag-and-drop interfaces and command-line interactions. Watson.ai provides several generative AI services including vector embeddings and text completions. More information can be found at https://developer.ibm.com/learningpaths/get-started-watson-studio/introduction-watson-studio/

Configuration an AI Assistant

The following are needed in order to use the Watson AI embedding and completion services:

Watson Studio project ID,

API key and

an associated service with an Editor role.

The details on using these IBM Watsonx AI values are in the “AI Assistant Configuration” document here.

A URL for Watsonx AI Studio is
https://cloud.ibm.com/catalog/services/watsonxai-studio?catalog_query=aHR0cHM6Ly9jbG91ZC5pYm0uY29tL2NhdGFsb2c%2Fc2VhcmNoPXdhdHNvbiNzZWFyY2hfcmVzdWx0cw%3D%3D

Two URLs to access your Watson projects are
https://dataplatform.cloud.ibm.com/projects

https://cloud.ibm.com/projects

Click the right hand “Create Project” button.
Enter a name.

Click

Click the Manage tab

Copy the project ID

Click Access Control

Click

Start typing a filter.

Checkmark the service

Choose “Editor” from the drop down.

This role avoids this potential downstream error

message: 'Unauthorized user iam-ServiceId-1c415 in project_id 5c283 with Role editor due to: User iam-ServiceId-1c415 not authorized with role editor'

Click

Next the Watson ML service needs to be associated with the project. To avoid “project_id XXX is not associated with a WML instance”, navigate to