Embedding Conversational Analytics

You can embed the Conversational Analytics interface in a website or an application by using an HTML iframe tag just as you can with other Looker content types. The Conversational Analytics interface includes the dashboard data agent conversation pane and the Conversations page, where you can chat with data agents that are connected to multiple Looker Explores or chat with a standalone Explore.

Conversational Analytics supports both private embedding, where users are authenticated using their Looker login, and signed embedding, where users are authenticated through your own application.

This page describes how to embed the Conversational Analytics interface into an iframe.

Learn how and when Gemini for Google Cloud uses your data.

As an early-stage technology, Gemini for Google Cloud products can generate output that seems plausible but is factually incorrect. We recommend that you validate all output from Gemini for Google Cloud products before you use it. For more information, see Gemini for Google Cloud and responsible AI.

Before you begin

To embed Conversational Analytics, keep in mind the following requirements and limitations:

• Your instance must be Looker-hosted.
• Users will need the same permissions that are required to use non-embedded Conversational Analytics.
• Embedded themes are partially supported when you're embedding Conversational Analytics. The General options themes apply to Conversational Analytics interfaces. No other theming options are supported. Embedded themes are supported in the data agent conversation experience in an embedded dashboard.

Creating the Conversational Analytics embed URL

The process to create an embed URL for Conversational Analytics is the same as for embedding other content types, such as dashboards or Looks, where you add /embed/ after the instance name and before the content folder and content ID.

To embed a conversation with an Explore data agent or with a standalone Explore, find the non-embedded URL of the conversation or agent, and add /embed/ before the conversations or agents folder. For example:

• For the Conversations page, the embed URL will look like https://my_looker_instance.looker.com/embed/conversations.
• For the Agents page, the embed URL will look like https://my_looker_instance.looker.com/embed/agents.
• For a specific conversation, the embed URL will look like https://my_looker_instance.looker.com/embed/conversations/c9f370ac830b4669aeb494396422004c. In this example, c9f370ac830b4669aeb494396422004c is the conversation ID.

Private embedding of Conversational Analytics

For private embedding, create an iframe and use the Conversational Analytics embed URL as your iframe source, as shown in the following example:

  <iframe
      src="https://my_looker_instance.looker.com/embed/conversations/c9f370ac830b4669aeb494396422004c"
      width="1000"
      height="2000"
      frameborder="0">
  </iframe>

Then embed the iframe in your web page or application.

Signed embedding of Conversational Analytics

The process for signed embedding of Conversational Analytics is the same as for other content types. Use the Conversational Analytics embed URL when coding the signed embed URL.

Embed users will need the proper permissions to use Conversational Analytics, such as chat_with_explore or chat_with_agent. As a result, you will have to add those permissions to the signed embed URL.

You can add a URL parameter to make the Gemini spark that opens the data agent conversation pane from a dashboard visible or hidden to users.