Conversational search

Before you begin

You must configure the search integration to enable the conversational search feature. For more information about configuring IBM Watson® Discovery search integration, see Discovery search integration setup. For more information about configuring Elasticsearch integration, see Elasticsearch search integration setup.

Enabling conversational search

You can enable conversational search to give accurate responses to the customer query. In addition, you can enable citations by putting a citation title, which gives the list of references of the source content from where the assistant pulled the responses. You can see the citation title in between the conversational response and the citations.

To enable conversational search, do the following steps:

1. Go to Search Integration window.

2. Set the Conversational search toggle to On.

3. Choose the type of conversational search based on the context using contextual awareness.

   • Single-turn conversational search

   For contexts that require only current input to retrieve search results and to generate answers, choose Single-turn.

   • Conversational search using entire conversation

   For context-dependent questions, which might take previous inputs into account, choose Entire conversation.

   Entire conversation uses the whole session to continue the conversation. It might bring back subjects that are no longer in the scope of the conversation.

4. In the Define the text for the citation title, type How do we know?.

   The Define the text for the citation title is enabled only when Conversational search toggle is switched to On.

   The web chat integration does not support the citation title feature.

5. In the Tendency to say I don’t know, select the tendency to use. By default, Less often is selected.

6. Click Save.

   

Tuning conversational search’s tendency to say “I don’t know"

You can tune the tendency of your assistant to say “I don’t know” in conversational search by selecting one of the following options in the Tendency to say I don’t know section:

• Rarely
• Less often
• More often
• Most often

When your assistant generates a conversational search response, it evaluates the response and calculates a response confidence score. The assistant compares the response confidence score against your selection in the Tendency to say I don’t know section. If the response confidence score is comparatively high, the assistant responds to the user query with the generated response. If the response confidence score is comparatively low, the assistant does one of the following actions:

• Responds with an “I don’t know” message.
• Falls back to the “No matches” action per the Search routing configuration in your assistant.

'Table 1. Tendency to say “I don’t know” options' shows the options available in the Tendency to say “I don’t know” section.

Tuning the generated response length in conversational search

The generated response-length feature in IBM Watson Assistant customizes response lengths to best meet your needs.

You can choose from three response lengths: concise, moderate, and verbose. This feature adjusts the length of the responses that your assistant gives to better fit your needs in conversational search. The default setting is moderate, but you can change it as needed:

The response-length feature affects the average length of responses that watsonx Assistant generates. Although it aims to match the specified length, actual responses vary because of the complexity of user input and the inherent limitations of the large language model (LLM).

Configuring your assistant to use the conversational search

After you enable Conversational search, you must configure the Search routing setting to route your assistant responses to conversational search when no action matches the user response. For more information about the Search routing configuration, see the Configuring the search routing when no action matches topic. To configure your assistant to route to conversational search for specific topics or actions, you can add search as a step in a new or existing action.

When your assistant receives no search results from Elasticsearch or Discovery in response to a user query or when its connection to Elasticsearch or Discovery fails, your assistant responds to the user with a failure message. You can configure the failure messages for no search results and a failed connection in the Search integration settings.

Testing conversational search

You can test the conversational search in actions preview, the preview page, or by using the preview link.

In this example, the user asks, Tell me about a custom extension. Search results are pulled from your knowledge base when the conversational search is Off. In this case, the answer is returned as a list of cards that are relevant to custom extensions.

When the conversational search is On, the same search results are pulled from your knowledge base. The results are passed to an IBM watsonx generative AI model. This model produces a conversational reply to the user's question, in the form of a text response about custom extensions.

The web chat integration does not support the citation title feature. Hence, the preceding image does not display the default text in the citation title.

If you encounter bugs in conversational search, you can troubleshoot the errors by clicking Inspect. When you click Inspect, you see two options:

Streaming response for conversational search

Streaming response for the conversational search uses watsonx.ai capabilities to provide continuous, real-time responses in your assistant. By default, the streaming response is disabled for the web chat and the assistant preview panels.

By using the streaming response support feature, you can reduce the wait time for the response.

To enable streaming response, do the following:

1. Go to Home > Preview > Customize web chat.
2. Click the Styles tab.
3. Set the Streaming toggle button to On.
4. Click Save and exit.