Defining a knowledge search provider for chatbot
As an administrator you can specify a knowledge provider for a chatbot. If you have multiple chatbots, you can define a different provider for each chatbot.
To learn about the support search providers and their benefits, see Search-providers.
Before you begin
Product | Action |
---|---|
(To use cognitive search in chatbot) BMC Helix Innovation Suite IBM Watson Discovery | |
(To use BMC Helix Knowledge Management search in chatbot) BMC Helix Innovation Studio | If you do not want to include articles from BMC Helix ITSM: Knowledge Management |
If you want to include articles from BMC Helix ITSM: Knowledge Management |
To define BMC Helix Knowledge Management search
- Log in to BMC Helix Innovation Studio.
- On the Workspace tab, select the BMC Helix Virtual Agent application or custom application for which you set up the chatbot instances.
- Click the Chatbots tab and select the chatbot instance for which you want to configure the BMC Helix Knowledge Management search.
- On the Chatbot Configuration page, click the Search Settings tab.
- From the list of locales, click the locale of the chatbot application in which you want to configure BMC Helix Knowledge Management search; for example, English.
- From the Provider list, select ComAround Knowledge.
- Click Save.
The following image shows how to define BMC Helix Knowledge Management search:
You have defined BMC Helix Knowledge Management by ComAround as the default search provider for the chatbot.
End users can view the knowledge articles as shown in the following image:
To define cognitive search
- Log in to BMC Helix Innovation Studio.
- On the Workspace tab, select the BMC Helix Virtual Agent application or custom application for which you set up the chatbot instances.
- Click the Chatbots tab and select the chatbot instance for which you want to configure the cognitive search.
- On the Chatbot Configuration page, click the Search Settings tab.
- From the list of locales, click the locale of the chatbot application in which you want to configure cognitive search; for example, English.
- On the Edit Bot Locale Search Settings page, set the following fields:
- In the Provider list, select Cognitive.
- In the Data Set field, select the external or BMC Helix Innovation Suite data sets or both that you want to include in the cognitive search.
- Click Save.
- From the list of locales, select the locale for which you want to apply the display templates.
The Display Template by Channel section displays two entries for each data set—one for the web channel and the other for the non-web channels.
- From the Display Template by Channel section, do the following:
- Select an entry in the Data Set column.
In this example, Template for Internal DS_Calbro. - Click Upload Template, and browse to the location where you saved the out-of-the-box templates.
- Select the HTML template that you want to apply for displaying knowledge articles of the selected channel, and click Open.
- Repeat the preceding steps for the remaining channels in the Display Template by Channel section to complete the configuration for cognitive search.
- Select an entry in the Data Set column.
You have defined cognitive search provider for the chatbot. The end users can view the knowledge articles as shown in the following image:
Troubleshooting
After configuring cognitive search, if search results are not displayed as expected, use the following checklist to troubleshoot the issues:
Unable to view the search results or irrelevant search results are displayed
- Check if the API key and the IBM Watson Assistant Skill ID is correct.
- Check if the IBM Watson Discovery service credentials are correct.
- Check if the IBM Watson Discovery Collection IDs are correct.
- Check if you have selected Cognitive as the Provider in the Bot Locale Search Settings.
- Check if you have selected data sets in the Bot Locale Search Settings.
- On the Chatbot Configuration page > Search Settings tab, check if you have uploaded the correct templates.
If irrelevant search results are displayed, in IBM Watson Discovery, improve the search result relevance.