🪄Embedding Kaiya

Embed Kaiya conversational AI into your applications using iFrame and postMessage API

Kaiya, the conversational AI assistant in Tellius, can be embedded into external applications to enable natural language querying and interaction with data directly within your app via iFrame. This allows users to ask natural language questions, receive data-driven answers, and view visualizations in a chat-like interface, without leaving your application.

Steps to obtain the embed URL

1. Under Settings → Embed → Kaiya, click on Generate Embed URL to view the embedding URL window.

1. Once you click on Generate Embed URL, the following window will be displayed.

Generating embed URL

1. Direct Access URL (toggle): When enabled, users accessing the embedded URL are taken directly to the embedded Kaiya conversations interface (no login prompt). This only works when the token (passed via utm_source) has valid session context. When disabled, users will be redirected to the Tellius login screen before reaching the embedded component. Use this when you want user-level authentication to be enforced on access.

2. Expiry time of URL: Controls how long the generated embedding URL remains valid. Specify the duration in hours, days, or months. After the set time, the token (utm_source or similar context ID) expires, and the link becomes invalid.

3. Once you click on Generate URL, the Embed URL will be generated.

4. Click on the Copy icon to copy the URL.

5. An embedding URL looks like the following: https://domain/kaiya/chat/conversation/new?utm_source=ID

6. Once you embed the URL, the Kaiya conversations page will be loaded.