Working with AI Space
This documentation is for Kyvos 2026.6.x. To view documentation for other Kyvos versions, click here. |
|---|
Overview
This section details how to use the AI Space in Kyvos to interact with data using natural-language queries and automatically generate insights, visualizations, and analyses.
AI Space in Kyvos enables conversational analytics across multiple data sources within a unified business context. It acts as a container that consolidates relevant entities for semantic models.
By organizing these entities within a single AI Space, Kyvos supports seamless conversational Q&A across multiple semantic models, enriched with external data sources. AI Spaces provide centralized AI settings, including shared business context, tool definitions, and business rules, ensuring accurate query interpretation, consistent SQL generation, and insights beyond simple “what” questions.
Creating an AI Space
To create an AI Space, perform the following steps.
From the Toolbox, select AI Space.
Click the three dots (…) actions menu > Add Space. The AI Space panel is shown, displaying a list of semantic models.
In the Space Assets pane, drag and drop the semantic model to the Space Objects pane in the right.
Setting up context for Space instructions
Space instructions
In the Context section, click Space Instructions and specify the business, querying instructions, summary instructions, verified questions for the AI Space.
Verified Queries
You can add Natural Language Queries (NLQ) in Kyvos to allow users to ask questions about their data in plain business language and automatically generate relevant queries or insights. This feature enables users to define commonly used business questions in natural language and map them to corresponding SQL queries, store them at different access levels, and leverage them both as suggested prompts in chat sessions and as reference examples for RAG-based SQL generation. These verified questions help improve SQL generation accuracy by providing contextual guidance during conversational analytics experience with Kyvos Dialogs.
Set the context for Natural Language Queries (NLQ) on the Managed Verified Queries dialog box. This improves query interpretation and generate more accurate insights based on the user’s business terminology and data context. You can add a new query, export query, and import query.
To add a new query, perform the following steps.
Navigate to Verified Queries under the Context section.
Click Add Queries. The Manage Verified Queries dialog is displayed.
In the Queries panel, click the + icon to add a new query, or select an existing query from the list.
In the Natural Language Query text box, enter the business question in plain language (for example, “What is sum sales for 2025?”).
In the SQL Query editor, enter the corresponding SQL statement using Spark SQL syntax.
(Optional) Click Execute Query to validate and test the SQL query.
In the Additional Context field, provide additional context to clarify the intent or usage of the query.
In the Applicable For field, select the relevant users for whom this query should be available.
Enable Show as suggested questions in Dialogs if you want this query to appear as a suggested question in Kyvos Dialogs.
Repeat the above steps to add more natural language queries as required.
Click Apply to save the configuration. The query has been added. You can now edit or delete the query as needed.
Edit: You can edit natural language queries by clicking the pencil edit icon. The Manage Verified Queries dialog is displayed. Make the necessary changes and click Apply.
Delete: You can delete natural language queries by clicking the delete icon. The query will be deleted.
Revert: You can also click back to previous changes without saving changes.
Importing sample queries
You can import sample queries in CSV format and use them to query the semantic model.
To import sample queries, perform the following steps.
From the Toolbox, click Semantic Models.
Select a semantic model from the list.
Click the Settings tab and then select the Verified Queries tab under the Context section.
Click Import Queries. The Import Verified Queries dialog is displayed.
Select the Choose file option to upload the file. The file will be uploaded.
Specify the settings as: line separator, field separator, and enclosed as needed.
Click Import. The CSV file will be imported.
Exporting sample queries
This section details how to export sample queries in CSV format.
To export sample queries, perform the following steps.
From the Toolbox, click AI Space.
Select an AI Space from the list.
Click the AI Settings tab and then select the Verified Queries tab under the Context section.
Click Export Queries at the bottom of the page. The Export Verified Queries dialog is displayed.
Specify the settings as: line separator, field separator, and enclosed as needed.
Click Download. The CSV file will be downloaded.
Advanced settings
In the Advanced section, you can define the global LLM connections for the AI Space. Specify the LLM connection and Embedding connection for metadata, query, and summary generation.
To configure global LLM connections for this space, perform the following steps.
Navigate to the Settings option.
In the Settings pane, enter the following details.
Area | Parameter | Description |
|---|---|---|
Query Generation | LLM Connection | Select the LLM connection used by Kyvos Dialogs and Kyvos Viz. for interactions with this semantic model. |
| Embedding Connection | Select the embedding connection to generate embeddings of AI Space metadata for semantic search and retrieval. Helps the system understand context, match similar queries, and improve result accuracy. |
Summary Generation | LLM Connection | Select the LLM connection used for natural language generation on this semantic model. |
Max Data Points for Summary | This property configures the maximum number of data points involved in generating the summary. | |
Metadata Generation | LLM Connection | Select the LLM connection from the list. This connection automatically generates metadata such as descriptions, tags, and business context for data models. |
More Actions
Click the Actions menu (…) and do the following:
Validate the space
Share the space via link or grant access.
Refresh the space to get the updates.
Add Note or Tag for the space.
Click Save. The Space will be added and displayed to the AI Space panel.
Collaborative editing support
From Kyvos 2026.5 onwards, Kyvos supports collaborative editing by allowing multiple users to work on the same AI space model simultaneously without enforcing edit locks. It provides visibility into active users, detects concurrent modifications, and offers conflict resolution and merge capabilities to help users manage and reconcile changes efficiently.