Configure AI features for your organization

Several features in Sigma use AI to accelerate insights and tasks that you might perform in Sigma:

• Ask Sigma is a natural language query (NLQ) interface that allows you to ask questions about your data and interact with AI-generated responses. See Ask natural language queries with Ask Sigma.
• The formula assistant uses AI to write new formulas, correct formula errors, and explain existing formulas. See Use AI with formulas.
• Explain this chart uses AI to instantly generate a description of any chart. See Explain charts with AI.

To use AI-enabled features in Sigma, do the following:

1. Set up an AI provider
2. Manage access to AI features
3. Review data access for AI features

User requirements

You must be assigned the Admin account type.

Set up an AI provider

When you set up an AI provider in Sigma, you connect Sigma to either an external AI service or a data platform with access to specific AI models that Sigma can use.

• To connect to an AI model hosted by your data platform, see Configure a warehouse-hosted model as AI provider.

  When you choose the option to configure a warehouse-hosted model, your data is managed fully in your data platform.

• To connect to an externally hosted model, see Configure an external AI provider.

Manage access to AI features

You can control who can access different AI features by enabling feature permissions on different account types assigned to users. See Configure permissions for AI features.

You can also manage whether to show generated data collections in Ask Sigma. See Configure Ask discovery.

Configure permissions for AI features

To control which Sigma users can access specific AI-powered features, enable or disable the relevant permissions for specific account types:

For more details, including details on which license tiers have access to these permissions, see License and account type overview.

Configure Ask discovery

Ask discovery generates data collections when a user accesses Ask Sigma. If a user opens a generated data collection, they can review a text description and links to data sources and documents that use those sources. Both options are turned on by default when you add an AI provider.

You can choose to stop showing data collections, or exclude links to documents from the generated data collections:

1. Go to Administration > AI Settings:

   1. In the Sigma header, click your user avatar to open the user menu.
   2. Select Administration to open the Administration portal.
   3. In the side panel, select AI Settings.

2. In the Ask discovery section, turn off the relevant features:

   • To stop showing data collections in Ask Sigma, turn off the Show Ask discovery toggle. Turning off this toggle also turns off the Show Ask discovery assets toggle.
   • To exclude links to documents from the generated data collections, turn off the Show Ask discovery assets toggle. If you turn off this option, the generated data collections only display text descriptions.

   Your changes save automatically.

Review data access for AI features

AI features such as Ask Sigma respect the access granted to users for data sources. Each user can see and query only the data sources that they have access to. If you want to restrict what Ask Sigma uses as a data source for answers for a specific user or team, restrict user or team access to the data source at the data source, schema, or table level.

To manage user access to data, review the access set on a specific data connection or data model:

• Manage access to data and connections.
• Manage document access.
• Within a data model, you can also control visibility of a source: Enable or disable an element as a data source.

To manage what data sources Ask Sigma uses when answering questions, review How Ask Sigma selects data sources when answering user questions and follow the steps to highlight data sources.

How Ask Sigma selects data sources when answering user questions

When using Ask Sigma, users can choose a specific data source that they have access to, or Ask Sigma can choose a highlighted data source to use in the conversation.

If a source is not specified, the data source that Ask Sigma selects from the highlighted data sources is based on the following factors:

• The user's access to the data source. Ask Sigma respects the access granted to the user asking the question and does not expose data they are not authorized to use.
• The relevance of the data to the question. Ask Sigma uses any metadata that exists to describe data sources and data columns, such as data model descriptions or column descriptions. If no other metadata has been defined, Ask Sigma can infer relevancy from column names.
• The known validity of the data. If a data model has an "endorsed" badge applied, for example, Ask Sigma is more likely to use that data source. Similarly, if someone in your organization has created and shared metrics, data models, or datasets, Ask Sigma is more likely to select one of those when answering rather than using a table directly from your connected data platform.
• The frequency of usage of the data source. Ask Sigma is more likely to reference frequently used data sources in its answers.

📘

You do not need to add any metadata to your data sources in order for Ask Sigma to determine which ones to use. Ask Sigma uses any existing available metadata, such as certification badges, source descriptions, and column descriptions, to determine relevancy to a user's question, but can also determine relevancy using column names alone. If no metadata is defined, Ask Sigma automatically generates AI summaries for each data source that it uses. If you want to add badges and other metadata, see Annotate tables with metadata.

Select data sources to highlight in Ask Sigma

When you highlight a data source, you make it available by default for conversations in Ask Sigma. Users can also choose specific data sources that they have access to when asking natural language queries, even if they are not highlighted. When highlighting a table in a data model, consider highlighting any tables that are visible as a source. Ask Sigma can use relationships to non-highlighted tables to perform joins when answering questions as needed.

Choose the data sources to highlight in Ask Sigma. Select popular data sources to improve the relevance of typical results for your users.

1. Go to Administration > AI Settings:

   1. In the Sigma header, click your user avatar to open the user menu.
   2. Select Administration to open the Administration portal.
   3. In the side panel, select AI Settings.

2. In the Ask Sigma data sources section, enter terms in the search bar to find the tables, data model elements, semantic views, and datasets that you want to highlight for use in responses to user questions in Ask Sigma. The data sources in the results are listed in order of usage. When searching for data sources:

   • Search for tables from your data platform.
   • Search for the view name for a Snowflake semantic view.
   • Search for individual tables in a data model. Searching for the data model name produces no results.

   🚧

   You cannot highlight the tagged version of a data model. When you highlight a data model element, only the published version of the data model is highlighted.

3. Select the checkboxes next to the sources that you want to highlight in Ask Sigma.

   To see a list of all data sources that are either already available or that you have selected to highlight, clear any text from the search bar. The Pending column indicates the status of a data source.

   

4. After selecting all relevant data sources, click Sync.

If you change any data sources or metadata in your data platform after you highlight those data sources, return to this page and manually re-sync your data sources to ensure Ask Sigma has access to those changes.