--- sourceDocument: Australia ServiceNow AI Platform Administration sourceDocumentLink: https://www.servicenow.com/docs/r/platform-administration Release : - australia ft:locale : - en-US ft:publication_title : - Australia ServiceNow AI Platform Administration ft:clusterId : - platadm bundleId : - platadm workflow : - Platform --- # Hybrid search # Hybrid search in AI Search {#ariaid-title1} Release version: Australia Updated August 25, 2026 ![](https://www.servicenow.com/docs/portal-asset/ico-clock) 4 minutes to read Summarize ![AI sparkle icon](https://servicenow.com/docs/portal-asset/ai-sparkle-icon) Summarized using AI This content was generated using new OpenAI-powered functionality. Results are provided on an as is basis and are not guaranteed to be accurate or complete. ## Summary of Hybrid search in AI Search Hybrid search in AI Search combines traditional keyword search with semantic vector search to deliver results that match both the terms and the underlying meaning of your query. This mode is available for any indexed source that supports semantic vector search. Show full answer Show less Previously, AI Search relied solely on keyword search, which matches terms exactly but does not interpret context or intent. Semantic vector search, introduced starting with the Yokohama Patch 11 release, analyzes the meaning behind search terms to improve recall and relevance by understanding natural language context. The ServiceNow Otto for AI Search application introduces the hybrid search mode, which merges keyword relevance scores and semantic similarity scores using Reciprocal Rank Fusion (RRF) to rank results. This blend enhances precision and contextual relevance in search results. Hybrid search is configurable and can be enabled or disabled by administrators on a per-search-application-configuration (SAC) basis. It applies to indexed sources included in the semantic index, such as the Knowledge table, Catalog Item table, Skills, and all External Content Connectors by default, with the option to extend to other sources via manual configuration. In portal searches, hybrid search uses default semantic fields (title and body) unless configured otherwise, allowing flexibility to accommodate different semantic field mappings per indexed source. ## Benefits * **Improved search quality and recall:** By combining keyword and semantic matching, hybrid search retrieves more relevant results even when queries differ in phrasing. * **More relevant top-ranked results:** Understanding the search intent enhances the relevance of the highest-ranked results. * **Reduced zero-result queries:** Semantic matching helps return useful results for vague or misspelled queries, lowering the chance of no results. ## Availability and Configuration Hybrid search requires the ServiceNow Otto for AI Search application version 15 or later. It is not supported with legacy Zing text indexing and search engines and is not enabled by default on AI Search-powered configurations. Administrators must manually activate hybrid search for specific search application configurations through the AI Search Admin console. ## Interactions and Considerations * Activating hybrid search disables search result counts for facets in the affected search application. * The "Most recent" sort option changes behavior: AI Search merges keyword and semantic results first, then sorts by last modification date, instead of sorting all results purely by recency. 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. ## Overview of hybrid search {#hybrid-search-ais__section_vwh_qzv_bhc} In older releases, AI Search performs all searches in keyword search mode. This mode looks for the best matches for your search terms, but doesn't take the context or meaning of those terms into account. The keyword search relevance score for a search result indicates how well the indexed terms in that search result match your search terms. Starting with the Yokohama Patch 11 release, AI Search includes an alternate semantic vector search mode in features which work with the Now LLM Service. Semantic vector search analyzes the meanings and context of your search terms and uses that information to find results with similar meanings. It improves search recall by interpreting natural language to more accurately reflect your search's intent. The semantic vector search relevance score for a search result indicates how closely the search result matches the meaning of your search. Note: To learn more about semantic vector search mode and how it differs from keyword search mode, see [Semantic vector search in AI Search](https://www.servicenow.com/docs/2DCULyElDqaFQk0zc_7vQw "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."). Installation of ServiceNow Otto for AI Search offers a new hybrid search mode. This mode combines keyword relevance scores and semantic similarity scores into a single result ranking using Reciprocal Rank Fusion (RRF). By blending keyword and semantic vector search modes, AI Search offers the best of both worlds, providing users with both search precision and contextual relevance. Upgrading an existing installation doesn't change current hybrid search settings. Users with the admin role can activate or deactivate hybrid search for individual SACs after installation. Note: Hybrid search applies to any indexed source that's included in the semantic index. By default, the following indexed sources ship with preconfigured semantic indexing and work with hybrid search: * Knowledge Table indexed source \[kb_knowledge table\] * Catalog Item Table indexed source \[sc_cat_item table\] * Skills indexed source \[sys_gen_ai_skill table\] * All External Content Connectors indexed sources \[connector-specific tables\] {#hybrid-search-ais__ul_qb5_5sl_cjc} You can manually configure additional indexed sources to be included in the semantic index, extending hybrid search to those sources as well. For details on this procedure, see [Configure semantic indexing settings for an indexed source](https://www.servicenow.com/docs/FCz4vqBVFx_rBmrku4r_XQ "Specify the semantic indexing configuration settings you want to apply when AI Search indexes records from your indexed sources."). In portal search, hybrid search queries the default semantic field names, title and body. These default field names are specified by the value of the glide.ais.query.default_hybrid_semantic_fields system property. If your indexed source's semantic configuration uses non-default semantic field names, you can set the value of the glide.ais.query.use_default_hybrid_semantic_fields system property to false. With this value set, hybrid search resolves each indexed source's own semantic field mappings instead of using the default field names. ## Benefits of hybrid search {#hybrid-search-ais__section_ksd_rzv_bhc} Hybrid search offers these benefits when compared with keyword search. Improved search quality and recall : Hybrid search combines keyword and semantic matching, increasing the chances of retrieving relevant results, even when users phrase their queries differently. More relevant top-ranked search results : Understanding the intent of your search, along with matching the words you use, helps find results that match what you mean. Fewer zero-result searches : Hybrid search can return useful results even for vague or misspelled queries because it uses semantic matching to understand meaning beyond exact keywords. This reduces the number of searches that return no results. ## Availability of hybrid search {#hybrid-search-ais__section_ggs_bdw_bhc} Hybrid search requires installation of the ServiceNow Otto for AI Search application. This feature is available beginning in ServiceNow Otto for AI Search 15. Note: Search application configurations that use the legacy Zing text indexing and search engine don't support hybrid search. Hybrid search isn't automatically activated for your search application configurations that use AI Search as their search engine. To learn how to manually activate hybrid search for these search application configurations in the AI Search Admin console, see [Manage hybrid search in search applications](https://www.servicenow.com/docs/mE~4vzp8x1cskDuOnrv8sw "Control hybrid search settings in AI Search applications to optimize search performance. Enable hybrid search to create context-aware results that combine keyword matching with semantic understanding. Disabling it generates results that rely solely on keyword-based queries."). ## Interactions with other features {#hybrid-search-ais__section_gcm_54t_k3c} Activating hybrid search in a search application configuration disables search result counts for facets in that search application configuration. For more information on search result counts for facets, see [Show search result counts for facets on the results page for a search application](https://www.servicenow.com/docs/0av7J6O05uJAXuWkJMqF7g "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."). When you activate hybrid search in a search application configuration, the behavior of the Most recent search result sort option changes for the specified search application. Instead of sorting the entire list of search results by last modification date, AI Search first retrieves keyword search results and the most relevant semantic vector search results, then merges those results and sorts them by last modification date. To learn about sorting search results based on recency, see [Change the sort order for your search results](https://www.servicenow.com/docs/p0airKdNWAPgRSTbdxY1cg "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.").