Tungsten AI knowledge base provider

Tungsten AI knowledge base provider is an out-of-the-box AI provider for use with an AI knowledge base. You cannot delete the Tungsten AI knowledge base provider.

Property	Description
Display name	Name of the Tungsten knowledge base provider. (Read-only)
Indexes	Add indexes by defining dimensions and index fields. If using a shared license, you can only view indexes created on this instance of TotalAgility, as these indexes are saved in the database. Once you save the AI knowledge base configuration, all specified indexes are created automatically in Azure AI Search. Any existing indexes are validated to ensure they contain the same internal fields as required by TotalAgility. If using a shared license, you cannot create new indexes but only view indexes from the current instance of TotalAgility, as they are stored in the database. In a TotalAgility on-premise multi-tenant environment, a tenant can only view indexes created specifically for that tenant, as these are stored in the tenant's dedicated database. However, the index names must be unique because the indexing service is shared across all tenants. An error message is displayed if a tenant attempts to create an index with an already existing name, indicating the conflict.
Query type	The query type, based on which TotalAgility specifies the default Semantic configuration created previously for the Azure AI Search index. The following query types are available: Simple (default), Semantic, Vector, Vector simple hybrid, and Vector semantic hybrid. See the preceding table for a description of these query types.
Enable query type override	If selected, allows you to override the integration-level query type by selecting a different query type while configuring the Generative AI chat control (using AI knowledge base), AI knowledge base insight type, or Search knowledge base activity . At runtime, the query type defined at the activity or control level takes precedence over the query type set at the integration level. The "Override query type" setting becomes available in an activity or form only if "Enable query type override" setting is enabled in the AI knowledge base integration.
Max number of matches	The maximum number of documents configured for the query. (Default: 5, Minimum: 3, and Maximum: 20)
Strictness	The strictness level for search relevance filtering. A higher strictness means higher precision but lower recall. (Default: 3, Minimum: 1, and Maximum: 5)
Timeout in seconds	The timeout period (in seconds) for each provider. (Default: 300, Minimum: 120, and Maximum: 3600)
Retry count	The number of times a system retries a failed operation for each provider before giving up and returning a failure response. (Default: 5, Minimum: 0, and Maximum: 100).