Semantic vector search in AI Search

  • Release version: Australia
  • Updated July 6, 2026
  • 3 minutes to read
    • Summarize
    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 Semantic vector search in AI Search

    Semantic vector search in AI Search enhances how the Now LLM Service finds results by analyzing the meaning and context of search terms rather than relying solely on keyword matching. This approach is integrated into features such as Now Assist Q&A Genius Results, Now Assist in Virtual Agent, and Now Assist Actions Genius Results, providing more accurate and contextually relevant search outcomes.

    Show full answer Show less

    Unlike traditional keyword search, which matches exact terms, semantic vector search interprets natural language queries to identify results that share similar meanings, improving recall and relevance without requiring synonym dictionaries.

    Key Features

    • Uses semantic vector analysis to compare the contextual meaning of search terms against indexed content.
    • Automatically enabled with no configuration needed, seamlessly overriding default keyword search relevancy.
    • Orders search results by similarity to query intent, prioritizing the most contextually relevant items.
    • Supports multiple Now Assist features, including Virtual Agent catalog item retrieval and live agent topic retrieval.
    • Integrates with External Content Connectors for semantic vector indexing of documents from external sources, enhancing content retrieval.

    Practical Benefits

    • Improves recall for knowledge articles, catalog items, and topics by matching on meaning rather than keywords.
    • Delivers a more natural and consistent search experience by recognizing varied queries with the same underlying intent.
    • Reduces the need for manual maintenance of synonym dictionaries, streamlining search management.

    What Customers Can Expect

    ServiceNow customers leveraging AI Search with semantic vector search will experience more relevant and context-aware search results, particularly in conversational AI scenarios like Virtual Agent and Now Assist. This leads to faster issue resolution, improved self-service outcomes, and more effective content discovery without extra configuration effort.

    Semantic vector search allows the Now LLM Service to find results based on how similar they are in meaning to your search terms. Now Assist Q&A Genius Results and Now Assist in Virtual Agent use semantic vector search to improve recall with natural language interpretation of search queries.

    By default, AI Search uses keyword search, meaning that it finds results for records that contain the best matches for the keywords (terms) in your search query. Term matching doesn't take into account the context or meaning of your search terms.

    Starting in the Vancouver Patch 4 release, AI Search includes an alternate search mode called semantic vector search that's used in features which work with the Now LLM Service. Examples of such features include Now Assist in Virtual Agent chats, Now Assist Multi-Content Response Genius Results, and Now Assist Actions Genius Results.

    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.

    As an example, suppose you index a source record including text how to prevent phishing and search for avoiding scams.
    • In keyword search mode, AI Search returns no result for this record because your search query terms aren't literal matches for the terms included in the indexed content.
    • In semantic vector search mode, however, AI Search might return a result for the record based on the following context-aware analysis:
      • Your search term avoiding is contextually similar in meaning to prevent
      • Your search term scams has meaning that overlaps with the meaning of phishing

    AI Search orders results from semantic vector search based on how similar they are to your search. In the example, if you had a second indexed record including text how to prevent scams, it would be more similar to the avoiding scams search and its search result would appear before the how to prevent phishing result.

    Unlike the default keyword-based search mode, semantic vector search does not rely on your synonym dictionaries to find term equivalences. AI Search identifies term similarities automatically when indexing source content and metadata for semantic vector search.

    Semantic vector search is automatically enabled and doesn’t include any configurable settings.

    Benefits of semantic vector search

    In comparison with the default keyword search mode, semantic vector search provides the following benefits:
    • Helps improve recall for knowledge article, Catalog Item, and topic retrieval searches by matching results based on the underlying meaning of your search rather than matching on keywords.
    • Provides a more natural and consistent search experience by returning similar results for varied search queries with the same underlying meaning.
    • Reduces the necessity to create and maintain synonym dictionaries to anticipate similarities in searches.

    Semantic vector search output

    Semantic vector search overrides the normal AI Search term matching and relevancy ranking mechanisms. Results are ordered based on their computed similarity to your search query terms, with the most similar results appearing first.

    Availability of semantic vector search

    Semantic vector search is available in the following contexts.
    • Now Assist in Virtual Agent uses semantic vector search for Catalog Item retrieval and live agent topic retrieval. For more details, see Now Assist in Virtual Agent.
    • Now Assist Q&A Genius Results use semantic vector search along with legacy keyword search when looking for knowledge articles that match your search query. They also use semantic vector search when looking for cached answers that match your query in the second-level cache. For more details, see Now Assist Q&A Genius Results and Caching for Now Assist Q&A Genius Results.
    • Now Assist Actions Genius Results use semantic vector search along with legacy keyword search when looking for Catalog Items that match your search query. For more details, see Now Assist Actions Genius Results.
    • All connectors from the External Content Connectors application support semantic vector indexing when retrieving document content from external source systems. Only features which use semantic vector search with the Now LLM Service can take advantage of this support. For more information on external content connector configuration and usage, see External Content Connectors.