Ai Search

Activate your preferred embedding model so that your AI Search RAG application knows which model to use for generating embeddings.

Activate indexing of searchable content from variables on Catalog Item records. Configure the set of Catalog Items eligible for catalog variable indexing and the set of variables to index.

Request activation of the External Content for AI Search plugin (com.glide.ais.external_content) to enable indexing of searchable content and metadata from records in external data sources.

Activate fuzzy numeric search to let users find indexed records by their Number field values without needing to enter alphabetic prefixes or leading zeroes.

Generate descriptive captions for images, tables, charts, and other visual elements in attachments from records in an indexed source table. You can find these attachments by searching for terms from their generated captions.

Enable AI Search's People default Genius Result configuration for use in your search profiles.

Enable automatic generation of searchable descriptive captions for images, tables, charts, and other visual elements found in indexed attachments.

Enable Unified Navigation search for newly installed workspaces in AI Search for Next Experience.

Learn how AI Search features and behavior affect indexing and search. Gain insight into AI Search behavior by reviewing log messages, ingestion history for indexed sources, and session debugging messages.

Domain separation is supported for AI Search Assist. Domain separation enables you to separate data, processes, and administrative tasks into logical groupings called domains. You can control several aspects of this separation, including which users can see and access data.

The AI Search Assist properties determine when searching begins based on characters entered and the time that has elapsed. These properties reduce the impact of searches for systems with many Catalog Items or Knowledge articles.

AI Search Assist includes the following roles.

AI Search Assist is a Service Portal widget that uses AI Search to improve incident deflection by displaying the most relevant set of related Catalog Item and knowledge article search results within a record producer. You can use AI Search Assist instead of Contextual Search.

Search administrators configure AI Search indexing and search settings in indexed sources, search sources, search profiles, and search application configurations.

Domain separation is unsupported for the AI Search application tables, but user search queries respect domain restrictions from indexed ServiceNow AI Platform table records. Domain separation enables you to separate data, processes, and administrative tasks into logical groupings called domains. You can control several aspects of this separation, including which users can see and access data.

A system property allows you to control whether facets are shown when no source is selected in global search and workspace search results pages.

The AI Search Country To Search Language form enables you to define a knowledge article search language for a country.

List of source facet buckets that appear by default in AI Search for Next Experience global search results.

This ServiceNow Store application enables administrators to configure AI Search as the search engine for Unified Navigation searches in Next Experience, including global search and configurable workspace search.

The AI Search RAG (Retrieval-Augmented Generation) capability provides a framework that enhances the search accuracy of AI Search results by narrowing the focus of your large language model (LLM) to a specific, contextual data set, instead of the vast, general data it was trained on.

Allow source facet filter selections to reduce the search result count used by the system when checking whether to resubmit multi-term search queries using the OR operator.

Grant users the ais_admin, ais_external_content, ais_high_security_admin, and search_application_admin roles so they can configure and manage settings and content for AI Search and search applications.

Improve multilingual search recall by defining a set of Knowledge article search languages for each user country. User searches can match Knowledge articles in any of the search languages specified for their country as well as in the language associated with their ServiceNow AI Platform session.

Obtain an OAuth 2.0 token from Microsoft SharePoint Online so that External Content Q&A Genius Results can find documents and generate answers when you search.

Auto-complete displays intelligent suggestions in your search application's input field to help users formulate their searches or jump directly to relevant results. Suggestions can include relevant search results, popular queries, recent queries from the user's personal history, and popular search results.

AI Search provides multiple types of auto-complete suggestions that you can configure for display to users in the search field.

ServiceNow Otto for AI Search includes an auto-complete suggestion type that displays suggestedconfirm name ServiceNow Otto for Virtual Agent conversational prompts.

When a search query returns too few results, AI Search automatically modifies and resubmits it with the goal of returning at least the desired number of results.

Configure a result improvement rule to prevent specific documents from appearing as Genius Results or search results.

Increase the relevancy scores for search results that satisfy a custom set of conditions.

AI Search provides two query-time caches to improve search performance for Knowledge base articles Genius Results. Caching enables AI Search to return previously generated answers without submitting knowledge articles to the Now LLM Service for answer generation.

The Child Table form enables you to enable AI Search content indexing for a child table that extends an indexed source table.

Field descriptions for the AI Search Datasource Churn Audit table, which lists fields that AI Search has flagged as high-churn.

Create a copy of an existing search profile. The cloned search profile retains search sources, stop word and synonym dictionaries, Genius Result configurations, and result improvement rules from the original search profile.

Create a copy of an existing stop word dictionary.

Create a copy of an existing synonym dictionary.

Several types of components are installed with activation of the AI Search plugin, including scheduled jobs, tables, and user roles.

The ServiceNow Otto for AI Search application installs new system components including scheduled jobs and Entity View Action Mapping (EVAM) configurations and templates.

Modify default settings for display of auto-complete suggestions of a selected type in your search application's input field.

Define settings for source facet buckets in a search application configuration. Users of the application can select source facet buckets to refine their search query results by search source.

Modify typo handling dictionary settings for a search profile.

Configure AI Search Assist settings for a record producer to help users view related Catalog Item and knowledge article search results.

Enable term highlighting in enhanced chat's Ask ServiceNow Otto suggestions by configuring AI Search as the source for those suggestions.

Define an encoded query for knowledge articles that you want to make searchable in any language.

Configure the navigation actions that trigger when a user selects View full table on an NLQ Genius Result action card. Each navigation action includes a redirection payload and can optionally include filters for a table's name, the NLQ source that returned the table, or the search profile used by the search application.

Configure the settings that External Content Q&A Genius Results need to interact with your Microsoft SharePoint Online instance.

Customize display settings for Search Result EVAM (Entity View Action Mapping) cards in portal and non-portal AI Search applications.

Specify the semantic indexing configuration settings you want to apply when AI Search indexes records from your indexed sources.

Use a Guided Setup module to step through configuration of search application settings and enablement of AI Search for Next Experience on your instance.

Plan and configure your AI Search implementation.

As an administrator or search administrator, you can configure settings to control the behavior of ServiceNow Otto for AI Search.

Integrate a capability definition with your custom embedding model.

AI Search filters search query results and displays only records that the currently logged in user can access.

Create your custom embedding model in the Generative AI Model Configuration table so that your AI Search RAG application can use it to generate embeddings for semantic indexing. This setup ensures the model is recognized and properly connected to send and receive requests.

Create a scripted extension point to handle embedding generation errors that occur when custom embedding models generate semantic vectors. Using extension point enables you to create a primary ticket type as per the extension point definition.

Define a schema table with columns corresponding to fields on records from an external data source. AI Search uses the schema when indexing content from the external data source.

Define facets to refine your searches using categories dynamically generated from the current search results.

Define an indexed source field setting to configure AI Search content indexing behavior for a specific field on source table records.

Create a Genius Result configuration, set its trigger condition, and configure the results displayed on its answer card.

Define an indexed source to make content and metadata from ServiceNow AI Platform table records searchable using AI Search.

Define an indexed source attribute to configure the AI Search content indexing behavior for all records on a source table.

Create a rule to boost, block, or promote search results or to block Genius Results. Specify the conditions that activate your rule and choose the action it performs when activated.

Create a search application configuration to specify AI Search as the search engine for a ServiceNow AI Platform application. Select a search profile for the application to use. Configure the application's settings for refinement and display of search results.

Customize the global search experience to return exact match search results from a specified table and column (field). You can configure custom search matchers for search terms with prefixes followed by numbers, such as INT470271, or for numeric search terms with delimiter characters, such as 525-326-3827 or 2016/01/08.

Create a new search profile to store search experience settings for a search application.

Make searchable content from an indexed source available in user search experiences by defining a search source.

Define terms to remove from search queries.

Define a new stop word dictionary and link it to a search profile.

Define terms to treat as equivalent in search queries.

Define a new synonym dictionary and link it to a search profile.

As an administrator, you can create your own custom embedding model to use in AI Search RAG application to generate embeddings for semantic indexing.

The Custom Matcher form enables you to create a global search custom matcher.

Use the Session Log to view the set of externally defined user and group access permission filters associated with the current ServiceNow AI Platform user. Administrators can use this approach to verify that the proper user mappings exist for the current user.

Use the Session Log to view search source and content security filters applied to results for a search query. Administrators can use this approach to verify search source filters and content security settings.

Preconfigured AI Search Genius Result configurations display concise, actionable answers derived from high-relevancy search results. These configurations return Genius Result answers for Catalog Items, tables, users, and Knowledge articles that match your search.

Define a Java regular expression pattern that a search must match to be eligible for triggering Knowledge base articles Genius Results. Searches that don't match this pattern don't return Genius Result answers from Knowledge base articles Genius Results.

You can specify access permissions for externally defined users and groups when ingesting external documents. AI Search preserves these permissions during indexing so that user content security filters can operate on them at search time.

A search application configuration specifies the search engine and settings to use for search in a ServiceNow AI Platform application. When you choose AI Search as an application's search engine, you can select a search profile for the application and configure its search result display and refinement settings.

Search profiles contain settings for a search experience, including synonyms, stop words, typo handling, Genius Results, and result improvement rules. Define a search profile for each unique search experience that you want to offer in a ServiceNow AI Platform application. Publish search profiles to make them available in your search applications.

Remove a stop word dictionary that isn't linked from any search profile.

Remove a synonym dictionary that isn't linked from any search profile.

Use the Search Preview UI and the AI Search High Security administrator elevated privilege role to determine whether filters prevent a search user from viewing a specific search result in the AI Search index.

The Dictionary form enables you to create a typo handling, stop word, or synonym dictionary for use in your AI Search search profiles.

The Dictionary Term form enables you to create a typo handling entry, a stop word, or a synonym in a dictionary linked to an AI Search search profile.

Configure the system to display search result preview lists for NLQ Genius Result answers in Service Portal search applications.

Display search result counts for facets on the results page for AI Search applications that use Seismic components. Search result counts for facets show the number of matching search results for each source facet bucket.

Increase search flexibility by configuring AI Search to display search result links as standard HTML anchors. You can open these search result links in new browser tabs using your browser's right-click or long-press functionality.

Increase search flexibility by configuring AI Search to display search suggestion links as standard HTML anchors. You can open these search suggestion links in new browser tabs using your browser's right-click or long-press functionality.

Dynamic Translation improves the international search experience for Catalog Items and Virtual Agent topics. When Dynamic Translation is activated, AI Search can translate searches into English before matching Catalog Items and Virtual Agent topics for inclusion in Genius Result answers, and can translate generated answers into the search user's language.

Dynamic Translation improves the international search experience for knowledge article content. When Dynamic Translation is activated, AI Search can generate Knowledge base articles Genius Result answers from non-English knowledge articles. Dynamic Translation also enables AI Search to translate Knowledge base articles Genius Result answers into the search user's language.

Walk through a Guided Setup task to configure AI Search as the search engine for global and workspace searches from the Unified Navigation search field.

Configure an indexed source attribute to enable indexing of content from attachments found on records from an indexed source.

Add your newly created embedding model in the semantic indexing table.

Configure and use the AI Search engine in the Customer Service Management, Now Mobile, Service Portal, and Virtual Agent applications.

Configure AI Search to match translated documents in a global fallback locale's language as well as the user's session language.

Specify the ServiceNow Otto for AI Search Genius Result types you want to make available in each of your AI Search portals and mobile applications.

Configure a field setting to automatically index domain field value updates for records from a referenced table.

Configure an indexed source to index field values from tables referenced by fields in the source table. You can index these field values for use in filters and EVAM search result configurations, index them for search, or both.

Run a scheduled job to make search-based auto-complete suggestions available in AI Search for Next Experience.

Configure an indexed source attribute to enable indexing of content from tags found on records from an indexed source.

As a search administrator, you can use the Knowledge base articles Genius Results skill in AI Search portals and mobile applications by enabling the skill in search profiles. You can also use the skill in global search by enabling Knowledge base articles Genius Results in the AI Search for Next Experience application.

AI Search excludes source record fields encrypted with Encryption Support or Edge Encryption.

Prevent AI Search from indexing content found in your knowledge blocks.

Prevent AI Search from auto-correcting a term in user search queries by excluding the term from a typo handling dictionary.

AI Search excludes the following ServiceNow AI Platform tables when indexing content. You can't configure these tables, or tables derived from them, as AI Search indexed sources.

The AI Search index stores data from ServiceNow AI Platform records or external sources and makes that data available for users to search in multiple applications. Search query features use ServiceNow AI Platform technologies to improve the search user experience.

Improve incident deflection for Service Portal users by displaying the most relevant search results within a record producer.

AI Search is the default search engine for Unified Navigation searches in Next Experience, including global search and configurable workspace search.

Learn about AI Search features that enable you to provide consumer-grade search experiences for your users.

When indexing records, AI Search preserves their ServiceNow AI Platform security features. At query time, AI Search filters search query results and displays only records that the user can access.

AI Search enables users to refine searches by filtering their results. Use source facet buckets to filter results by source, or select facets to apply filters dynamically generated from the result set.

AI Search provides users with clear answers for their search queries.

AI Search includes search features that help users find the answers they need.

Make alphanumeric content from text and string fields on your records searchable by configuring an indexed source. Each indexed source retrieves data from a table and adds it to the AI Search index.

AI Search supports indexing and search for all languages offered by the ServiceNow AI Platform. Search administrators can configure AI Search search features for languages activated in your instance.

Provide multiple search entry points across your organization by enabling AI Search as the search engine for search applications. The base system enables AI Search as the search engine for global and workspace search, Customer Service Management, Now Mobile, Service Portal, and Virtual Agent .

Search profiles define search sources and settings for linguistic search query features. Each search profile represents an individual search experience that you want to offer users in a supported ServiceNow AI Platform application.

A search source defines a subset of indexed content that users can search using a search profile. Create search sources by applying filter conditions to content from indexed sources.

The AI Search External Search User Mapping Table Data Source Relationship form enables you to link a user mapping table to an indexed source for external content in AI Search.

Applications and integrations from the ServiceNow Store extend AI Search functionality and provide insight into search usage and behavior.

With a subscription for the External Content for AI Search plugin, you can enable AI Search users to search content and metadata from documents in external repositories and remote tables.

External Content Q&A Genius Results display concise, actionable AI-generated answers derived from documents in your Microsoft SharePoint Online instance.

AI Search preserves user and group security access permissions specified for documents indexed from external sources. You can control access to external content search results by mapping these externally defined users and groups to ServiceNow AI Platform users.

The Facet form enables you to create a facet refinement filter in the search application configuration for an AI Search application.

Factoid extraction uses the machine reading comprehension (MRC) model to find the exact span of text within a longer extracted snippet that represents the answer to your question.

The Field Setting form enables you to create a field setting for an indexed source in AI Search.

A field setting controls indexing behavior for a specified field (column) on all records from an indexed source.

You can adjust indexing behavior for source record fields in an AI Search indexed source by configuring field setting attributes and values.

Define a Microsoft Keyword Query Language (KQL) query to restrict the set of Microsoft SharePoint Online sites (paths) that External Content Q&A Genius Results can search for documents. Only documents that satisfy your query are eligible for External Content Q&A Genius Result answer generation.

Fuzzy numeric search lets you find indexed records by their Number field values without needing to enter alphabetic prefixes or leading zeroes.

Multi-content source synthesis lets AI Search gather and combine information from any indexed source in your system to provide comprehensive AI-generated responses to your questions.

Catalog Item Genius Results display top search results from the Catalog Item [sc_cat_item] table. Each answer card shows a single Catalog Item record. You can create a request for the Catalog Item directly from the answer card.

The AI Search Genius Result Configuration form enables you to create a Genius Result configuration for use in your AI Search search profiles.

Users can submit feedback for each Genius Result answer card, specifying whether it was helpful for their search or not. For cards from default Genius Result configurations, users can also select the reason they found an answer unhelpful. AI Search records feedback responses as search signals that you can use to assess the relevancy of your Genius Result configurations.

NLQ (Natural Language Query) Genius Results use NLQ processing to surface relevant results from tables that match your search query. Each NLQ Genius Result answer card displays a preview of records from matching tables. You can navigate to a matching table's list view or the CMDB workspace directly from the Genius Result answer card.

People Genius Results display top search results from the User [sys_user] table. Each People Genius Result answer card shows a single user record. You can view the user's full profile directly from the answer card.

Q&A Genius Results display top search results extracted from HTML fields of records on the Knowledge [kb_knowledge] table and tables that extend it. Each Q&A Genius Result answer card shows a topic snippet and an answer snippet extracted from a single Knowledge article. You can view the full article directly from the answer card.

Optionally display the best answers for a search query as actionable Genius Result cards included with search results.

The AI Search Genius Result Configuration NLU Model Mapping form enables you to link a Genius Result configuration to an NLU model.

Add the AllSites.FullControl SharePoint API delegated permission to your External Q&A Genius Results OAuth 2.0 application in Microsoft Azure portal and grant admin consent to allow the application to access this permission. The OAuth 2.0 application for External Q&A Genius Results requires the delegated permission to search your Microsoft SharePoint Online sites.

Configure your AI Search applications to display attachment search results grouped with the results for their parent records.

Search application administrators can control whether attachment search results appear grouped with their parent search results or whether they display on their own. By default, AI Search displays attachments grouped with their parent search results.

Some indexed source fields change so frequently that repeatedly reindexing them adds load to AI Search without adding search value. AI Search automatically identifies these high-churn fields and lets an admin decide whether to continue indexing them or to exclude them from the index going forward.

In hybrid search mode, AI Search blends keyword search and semantic vector search to find results that best match the terms and meaning of your search. Hybrid search is usable for any indexed source that has semantic vector search enabled.

List of fields available on records in the AI Search index. AI Search populates these fields with values from source record fields during indexing.

Make content from multiple internal indexed sources searchable by performing a full table index. This procedure indexes existing records from the source tables and any child tables configured for indexing. You can manually reindex content from internal indexed sources by repeating this procedure.

Make content from an internal indexed source searchable by performing a full table index. This procedure indexes existing records from the source table and any child tables configured for indexing. You can manually reindex content from an internal indexed source by repeating this procedure.

The Indexed Source Attribute form enables you to create an indexed source attribute for an indexed source in AI Search.

An indexed source attribute defines indexing behavior for all records from an indexed source.

You can adjust indexing behavior for an AI Search indexed source by configuring indexed source attributes and values.

The Indexed Source form enables you to create an indexed source for use in AI Search.

Reduce index size and increase search performance with guardrails that limit the number of task and alert source records indexed from indexed sources.

The Indexed Source History form enables you to review details from the ingestion history for an AI Search indexed source.

Indexed sources designate ServiceNow AI Platform tables and external document sets with alphanumeric text and string field content that you want to make searchable. AI Search ingests text and string fields from table records or external documents and stores their searchable alphanumeric content in its search index.

AI Search indexes records on indexed source tables to make their content searchable.

Install the AI Search for Next Experience application from the ServiceNow Store.

As an administrator, you can install the ServiceNow Otto for AI Search application (sn_ais_assist) from the AI Admin Hub module.

When you activate the External Content for AI Search plugin (com.glide.ais.external_content), the system creates a new virtual table.

AI Search integrates with other ServiceNow AI Platform applications. Populate your UI Builder pages with search components and customize display of search results and Genius Results with EVAM definitions. Improve incident deflection in Service Portal by configuring AI Search Assist for record producers.

When a fallback language is configured for the user's session language, AI Search searches translated documents in both languages. Search uses the appropriate stop word, synonym, and typo handling dictionaries for the fallback language.

AI Search supports indexing and search in all languages offered by the ServiceNow AI Platform. Search linguistic features are supported in Arabic, Brazilian Portuguese, Czech, Danish, Dutch, English, Finnish, French, French - Canada, German, Hebrew, Hungarian, Italian, Japanese, Korean, Norwegian (Bokmål), Polish, Portuguese, Russian, Simplified Chinese, Spanish, Swedish, Traditional Chinese, and Turkish.

AI Search filters search results from external content connectors, showing only results in the user's session language, fallback language, and global fallback locale language.

AI Search normalizes inflected words and Unicode glyphs during indexing and at search query time. Normalization improves search recall and enables users to find content with variant forms of their search query terms.

Link a Genius Result configuration to one or more search profiles.

Specify the NLU model and intents to use for a Genius Result configuration with an NLU trigger condition.

Link search sources to a search profile to specify the content users can search through that profile.

Link an existing stop word dictionary to one or more search profiles.

Link an existing synonym dictionary to one or more search profiles.

Review AI Search logs and history to analyze performance and diagnose issues. View log messages and ingestion history, or use session debugging to capture detailed messages for a user session.

AI Search displays the most relevant search results for a query first. Machine learning automatically tunes search result relevancy scoring for search experiences based on aggregated user interactions.

Walk through a Guided Setup task to migrate your existing Zing search application configurations to AI Search application configurations.

Make your search experiences more consistent by configuring a search profile to mirror result improvement rules from other search profiles.

The Source Facet Bucket form enables you to configure display settings for a source facet bucket in the search application configuration for an AI Search application.

The ServiceNow Otto for AI Search application combines the power of search with a large language model (LLM) to provide actionable AI-generated or AI-selected answers in user searches. By constraining the context passed to the LLM, ServiceNow Otto for AI Search can increase the likelihood that LLM responses are grounded in indexed content.

Genius Results display actionable answers showing Catalog Items and Virtual Agent topics that match your search query. AI Search matches records based on their similarity to your search's intent and meaning instead of looking for exact term matches.

Summary Genius Results use an LLM to generate search and chat responses that synthesize information from knowledge articles, Service Catalog items, and other available content types.

Knowledge base articles Genius Results use the LLM to generate concise, actionable answers from knowledge article results in Service Portal, Virtual Agent, Employee Center, and global searches.

The ServiceNow AI Search application provides a consumer-grade search engine for ServiceNow Service Portal, ServiceNow Now Mobile, and ServiceNow Virtual Agent. Intelligent query features help you quickly find the answers you need.

Specify whether AI Search applications should preserve existing facet filters when you select a new source facet bucket.

AI Search adds the following plugin.

View the ServiceNow AI Platform table records that match a search source's indexed source table and filter conditions.

Configure a result improvement rule to make specific records appear first in results for a search.

System properties that you can use to modify behavior for ServiceNow Otto for AI Search Genius Results.

confirm name throughoutProvide positive or negative feedback on Summary Genius Result answers.

Publish a search profile to make pending changes to its settings take effect in linked search applications.

Execute a scheduled job to delete stale records from the AI Search index.

Learn how to construct search queries using terms, phrases, and AI Search query operators.

Understand where your indexed content originates by viewing record counts for your indexed sources in the AI Search Indexed Source Statistics table.

The Record Producer Configuration form enables you to create an AI Search Assist record producer configuration.

Reference information for the AI Search for Next Experience application.

These reference topics provide additional information about AI Search installed components, system properties, features, and forms.

Reference information for the ServiceNow Otto for AI Search application.

Re-enable the display of auto-complete suggestions of a selected type in your search application's input field.

Disable the display of auto-complete suggestions of a selected type in your search application's input field.

The AI Search Results Improvement Rule form enables you to create a result improvement rule in an AI Search search profile.

Define rules with configurable trigger conditions to boost, block, or promote search results for specific searches. You can also boost search results for documents matching elements of the user context, such as a user's country, OS, or device type.

To limit the set of records indexed from source tables, you can configure retention policies and filter conditions for your indexed sources. AI Search also uses these settings to automatically purge stale records from the index, optimizing search performance.

Revert to using Zing text indexing and search engine for the Unified Navigation search field in Next Experience.

View all versions of the ServiceNow Otto for AI Search application on the ServiceNow Store. Use this information to find the latest version of the application that's compatible with your instance's current ServiceNow AI Platform family release.

Review fields that AI Search flagged as high-churn and decide whether to keep indexing them or exclude them from the index.

View processing results and performance statistics associated with an ingestion event for an indexed source.

External Content for AI Search includes the following roles.

The Rule - Action Mapping form enables you to link a boost action to a result improvement rule in an AI Search search profile.

Use scripted post-processors to modify search result records for display in a search application.

The Search Application Configuration form enables you to create a search application configuration for an AI Search application.

The ServiceNow AI Platform offers a variety of search tools, which may return different answers for the same or similar searches. This disparity in results is expected. It occurs because each tool uses a different approach and architecture to find results and generate answers that match your search.

Learn about the output, controls, and fields provided by admin tools in the new Search Preview UI.

The Search Preview UI enables you to test AI Search queries using settings from a selected search application configuration or search profile. Administrator tools help you review search query performance data and feedback, debug queries, and override default query settings for testing purposes.

The Search Profile - Dictionary Mapping form enables you to link a stop word or synonym dictionary to a search profile in AI Search.

The Search Profile - Genius Result Mapping form enables you to link a Genius Result configuration to a search profile in AI Search.

The Search Profile - Search Source Mapping form enables you to link a search source to a search profile in AI Search.

The Search Profile form enables you to create a search profile for use in AI Search applications.

You can customize the appearance of standard search results in your AI Search application by changing these properties in the application's Search Result EVAM (Entity View Action Mapping) cards.

The Search Scripted Post-processors form enables you to create a search scripted post-processor in the search application configuration for an AI Search application.

The Search Source form enables you to create a search source that you can make available in AI Search user search experiences.

Define search sources to make your indexed content searchable in AI Search search applications. Choose an indexed source and configure optional filter conditions to limit the content that users can search.

Understand how AI Search searches translated fields and documents.

When a user searches referenced table field values that you have indexed for search with the searchable_dot_walk_fields field setting, only field values that the user can view appear in the search results. The system uses a field value's role-based access control list rules (ACLs) to determine whether the search user can view that field value.

The AI Search generalized RAG (Retrieval-Augmented Generation) framework offers a streamlined way to configure semantic indexing settings for records indexed from ServiceNow AI Platform tables.

The Semantic Index Configuration form enables you to define semantic indexing settings for an AI Search indexed source.

The Semantic Index Field form enables you to define a semantic index field for use in an AI Search semantic index configuration.

Semantic vector search enables the Now LLM Service to find results based on how similar they are in meaning to your search terms. Knowledge base articles Genius Results and ServiceNow Otto for Virtual Agent use semantic vector search to improve recall with natural language interpretation of search queries.

Capture and review detailed AI Search log messages for a user session.

Specify how you want factoid extraction to display and highlight answers for Q&A Genius Results.

Change the order in which AI Search evaluates Genius Result configurations linked to a search profile.

Specify the minimum number of terms that a search must contain to be eligible for triggering Knowledge base articles Genius Results. Searches with fewer terms don't return Knowledge base articles Genius Result answers.

Determine which AI provider to use for your embedding model to work in the AI Search RAG application.

Connect and configure your external or custom embedding model to enable it generate embeddings.

Set up connection and credential record for your aliases to authenticate an integration between your ServiceNow instance and third-party embedding model.

Display borders between search result cards in portal search and in global and workspace search.

The Sort Option form enables you to create a search result sort option in the search application configuration for an AI Search application.

A search result sort option enables users to display search results in an order determined by their field values. Applying a search result sort option overrides the default AI Search relevancy-based result order. You can define custom search result sort options for your AI Search applications.

Choose the order in which AI Search displays results for your search. By default, the most relevant search results appear first. You can override this behavior and view search results ordered by their field values.

AI Search performs A/B test evaluations that compare result relevancy for alternate sets of search query parameter values. These evaluations determine the models that AI Search uses for machine learning relevancy and for Q&A Genius Results.

Stop words remove search query terms that don't produce meaningful results. Improve search precision and relevancy by configuring stop word dictionaries and defining stop words.

The Suggestion Reader Group form enables you to modify settings for an auto-complete suggestion type in the search application configuration for an AI Search application.

Synonyms expand search queries to include additional terms with equivalent meaning or usage. Improve search recall by configuring synonym dictionaries and defining synonyms.

A system property determines whether the system displays search result preview lists for NLQ Genius Result answers in Service Portal search applications.

A system property determines how the system extracts factoids from knowledge articles when computing Q&A Genius Results.

Users with the admin role can configure the following system properties for AI Search by navigating to All System Properties AI Search .

Specify whether facets should display knowledge article reference field values in the search user's session language. If you disable translation, facets display knowledge article reference field values in your instance's default language.

AI Search replaces misspelled search query terms with auto-correction terms derived from indexed content. Configure typo handling dictionary settings to control derivation of auto-correction terms.

Unlink search sources from a search profile to prevent their content from being searchable through that profile. Deleted search sources aren't automatically unlinked from search profiles.

Remove a stop word dictionary that isn't linked from any search profile.

Remove a synonym dictionary from a search profile.

Install translated search UI element labels for a newly activated ServiceNow AI Platform language by repairing the AI Search for Next Experience application.

See how AI Search displays search results, refinement filter options, and Genius Result answers. Learn how to search using the AI Search query language. Understand when and how AI Search automatically resubmits queries.

AI Search external user mappings enable you to configure externally defined user and group aliases for ServiceNow AI Platform users. AI Search uses these aliased security principals to apply content security filters that control user access to search results indexed from external documents.

Global search enables you to search multiple record types at once from the Next Experience Unified Navigation search field. You can switch between global search results and results from workspace applications that you have access to.

AI Search can index searchable content and metadata from multiple variable types found on indexed source records.