Administering Watson Assistant
After you install Watson™ Assistant, there are several options for customizing your instance of the Watson Assistant service on top of IBM® Cloud Pak for Data.
About Watson Assistant
- CLU Embeddings
- Manages word embeddings for CLU.
- Dialog
- Dialog runtime, or user-chat capability.
- ed-mm
- Manages contextual entity capabilities.
- Master
- Controls the lifecycle of underlying intent and entity models.
- NLU (Natural Language Understanding)
- Interface for store to communicate with the back-end to initiate ML training.
- Recommends
- Supports recommendations from Watson, such as dictionary-based entity synonyms and intent conflicts.
- SIREG
- Manages tokenization and system entity capabilities.
- skill-search
- Manages search skills.
- SLAD
- Manages service training capabilities.
- Spellchecker
- Corrects spelling mistakes in user input.
- Store
- API endpoints.
- TAS
- Manages services model inferencing.
- UI
- Provides the developer user interface.
- etcd
- Manages service registration and discovery.
- Minio
- Stores CLU models.
- MongoDB
- Stores word vectors.
- PostgreSQL
- Stores training data. Includes the components keeper, sentinel, and proxy.
- Redis
- Used by the Watson Assistant tool to store web session-related data.
Provisioning an instance
You can provision up to 30 instances of Watson Assistant per deployment of Watson Assistant.
- From the Cloud Pak for Data web client, go to the Services page.
- Find the Watson Assistant service tile and then click to open it.
- Click the overflow menu icon, and then click Provision instance.
- Name the instance.
This is the instance you will share with the users in your organization. They will see this instance name from the product's main page. Choose a unique name that represents the instance's purpose.
- Click Create.
Giving users access to an instance
After you provision an instance, you can share the URL for the product user interface with other users. However, those users can only log into the product user interface if you give them access.
- From the web client menu, click .
- Click New user, and specify the user’s full name, user name, and email address. Set the user’s permissions, and then click Save.
- From the web client menu, select My Instances.
- Find your Watson Assistant instance, hover over the last column to find and click the menu, and then choose Manage Access.
- Click Add user.
- Click the user name field to see a list of the people you can add. The users you added in the previous steps are listed. Select a name, choose User or Admin as their access role, and then click Add. If you aren’t connecting to an existing user registry and enabling single sign-on, then temporary passwords are created for the users you add and are sent to them by way of the email addresses you specified.
Before people can create search skills in Watson Assistant, they need to have access to a Watson Discovery instance. Add to the Watson Discovery instance those people who need to be able to add new data collections to or query from existing collections by using a search skill.