--- sourceDocument: Yokohama ServiceNow AI Platform Administration sourceDocumentLink: https://www.servicenow.com/docs/r/yokohama/platform-administration Release : - yokohama ft:locale : - en-US ft:publication_title : - Yokohama ServiceNow AI Platform Administration ft:clusterId : - platadm bundleId : - platadm workflow : - Platform --- # Semantic Index Configuration form # Semantic Index Configuration form {#ariaid-title1} * Release version: Yokohama * * Updated June 8, 2026 * * ![](https://www.servicenow.com/docs/portal-asset/ico-clock) 3 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 Semantic Index Configuration form The Semantic Index Configuration form in ServiceNow enables you to define settings for semantic indexing of AI Search indexed sources. This configuration is essential for optimizing how AI Search processes and retrieves semantically relevant content. The form becomes available only when theAI Search Semantic Controller plugin (com.glide.ais.semanticsearch)is active, which requires at least one Now Assist application installed on your instance. Show full answer Show less ## Key Features * **Name:** Assign a unique, special-character-free name to the semantic index configuration for clear identification, such as *Knowledge-Table-semantic-index*. * **Embedding Models:** Select from multiple fine-tuned embedding models to generate semantic vectors, including: * ServiceNow Embedding (E5) -- default, with a 512-term encoder limit. * Azure OpenAI Embedding * Google Gemini Embedding * Custom Embedding (Bring Your Own Model) These options allow you to tailor semantic indexing to your content and AI capabilities. * **Active:** Toggle to activate or deactivate the configuration. Inactive configurations are ignored during indexing. * **Indexed Source:** Automatically references the AI Search indexed source to which the configuration applies. * **Application:** Automatically sets the application scope of the configuration record. * **Chunking Configuration:** Controls how text is broken into chunks for embedding, with three strategies: * **Passage (default):** Breaks longer text into chunks by words or sentences, with configurable chunk size and overlap to balance recall and performance. * **Truncate:** Concatenates all semantic fields and indexes up to a maximum total word limit, suitable for short texts. * **Full Text:** Concatenates all semantic fields and indexes all terms up to the embedding model's encoder limit. When using Passage strategy, you can configure: * **Overlap Sentences:** Number of overlapping sentences between chunks to improve search recall. * **Chunk Unit:** Choose whether chunks are measured in words or sentences. * **Chunk Size:** Maximum number of words or sentences per chunk. When using Truncate strategy, you can set the **Maximum Total Words** to limit indexing size. ## Practical Benefits for ServiceNow Customers By configuring semantic indexing settings precisely, you can enhance AI Search's ability to understand and retrieve content semantically, leading to more relevant search results for end users. Selecting appropriate embedding models and chunking strategies lets you optimize indexing for different content types and sizes, balancing recall, precision, and performance. Activating and associating these configurations with indexed sources ensures your semantic search capabilities are tailored and effective across your ServiceNow environment. The Semantic Index Configuration form enables you to define semantic indexing settings for an AI Search indexed source. For details on defining and modifying semantic indexing settings for an indexed source, see [Configure semantic indexing settings for an indexed source](https://www.servicenow.com/docs/TcWjjPwH0IKmA4L6_axmTA "Specify the semantic indexing configuration settings you want to apply when AI Search indexes records from your indexed sources."). Note: This form is only available when the AI Search Semantic Controller plugin (com.glide.ais.semantic_search) is active on your instance. To activate this plugin, your instance must have at least one [Now Assist application](https://www.servicenow.com/docs/access?context=platform-now-assist-landing&version=yokohama&pubname=yokohama-intelligent-experiences&ft:locale=en-US) installed. {#semantic-index-configuration-form__table_t1b_wjh_xcc__entry__2} | Field | Description | |-|-| | Name | Unique name for the semantic index generated by this semantic index configuration. As an example, if you're creating a semantic index configuration for the Knowledge Table indexed source, you might name it Knowledge-Table-semantic-index. Note: The semantic index's name can't contain special characters, underscores, or whitespace. | | Embedding Models | List of embedding models to use for the semantic index configuration. * Default value: ServiceNow Embedding (E5) * Supported values: * ServiceNow Embedding (E5): Use the E5 fine-tuned embedding model for content in the semantic index. The embedding model's encoder limit is 512 terms. * Azure OpenAI Embedding: Use the Azure OpenAI fine-tuned embedding model for content in the semantic index. For more information, see [Configuring an external or custom embedding model](https://www.servicenow.com/docs/7EXaLFHHayzbjXSbY1~4HA "You can connect and configure an external or custom embedding model in the AI Search Retrieval Augmented Generation (RAG) application to generate embeddings."). * Google Gemini Embedding: Use the Google Gemini fine-tuned embedding model for content in the semantic index. For more information, see [Configuring an external or custom embedding model](https://www.servicenow.com/docs/7EXaLFHHayzbjXSbY1~4HA "You can connect and configure an external or custom embedding model in the AI Search Retrieval Augmented Generation (RAG) application to generate embeddings."). * Custom Embedding: Use the custom fine-tuned embedding model for content in the semantic index. For more information, see [Configuring bring your own model (BYOM)](https://www.servicenow.com/docs/3Q7kx0v_vosuPwVGyPyW5A "As an administrator, you can create your own custom embedding model to use in the AI Search Retrieval Augmented Generation (RAG) application to generate embeddings for semantic indexing."). {#semantic-index-configuration-form__ul_o3v_r23_xcc} {#semantic-index-configuration-form__ul_wc2_flh_xcc} | | Active | Option to make the semantic index configuration active for your instance. AI Search ignores inactive semantic index configurations when indexing content from the specified index source. | | Indexed Source | Reference to the AI Search indexed source that you want to apply this semantic index configuration to. This field is automatically set. For more details on indexed sources, see [Indexed sources in AI Search](https://www.servicenow.com/docs/hKmPER6CuDD8sNqtd_4w0g "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."). | | Application | Application scope for the semantic index configuration record. This field is automatically set. | | Chunking Configuration For Embedding || | Chunking Strategy | Strategy to use when chunking semantically indexed text for the embedding model. * Default value: Passage * Supported values: * Passage: Chunking strategy for longer text field values. Index text from semantic field values in chunks. Each chunk contains a maximum number of words or sentences determined by your Chunk Unit and Chunk Size selections. * Truncate: Chunking strategy for short text field values. Concatenate all semantic index field values, then perform semantic indexing for terms up to the Maximum Total Words limit. * Full Text: Chunking strategy for short text field values. Concatenate all semantic index fields, then perform semantic indexing for all terms up to the embedding model's encoder limit. {#semantic-index-configuration-form__ul_dkn_qlh_xcc} * Type: choice list {#semantic-index-configuration-form__ul_cfb_mlh_xcc} | | Overlap Sentences | Number of sentences to overlap between chunks when indexing text from semantic index field values. Higher overlap values increase recall for semantic vector search at the expense of performance. This field appears only when Passage is selected from Chunking Strategy. * Default value: 5 * Supported values: Any non-negative integer * Type: integer {#semantic-index-configuration-form__ul_scc_rg3_xcc} | | Chunk Unit | Textual unit to use as the basis for chunk size when indexing semantic field values for semantic vector search. This field appears only when Passage is selected from Chunking Strategy. * Default value: Words * Supported values: * Words: Use words as the textual unit by which semantic index field values are chunked. Each chunk can include up to Chunk Size words. * Sentences: Use sentences as the textual unit by which semantic index field values are chunked. Each chunk can include up to Chunk Size sentences. {#semantic-index-configuration-form__ul_www_cg3_xcc} * Type: choice list {#semantic-index-configuration-form__ul_qd3_cg3_xcc} | | Chunk Size | Maximum number of words or sentences (depending on your Chunk Unit selection) to include in a chunk when indexing semantic field values for semantic vector search. This field appears only when Passage is selected from Chunking Strategy. * Default value: 250 when Words is selected from Chunk Unit, or 15 when Sentences is selected from Chunk Unit * Supported values: Any non-negative integer * Type: integer {#semantic-index-configuration-form__ul_axg_jj3_xcc} | | Maximum Total Words | Maximum number of words to index for semantic vector search from the concatenated values of all semantic index fields. This field appears only when Truncate is selected from Chunking Strategy. * Default value: 500 * Supported values: Any non-negative integer * Type: integer {#semantic-index-configuration-form__ul_xzx_nj3_xcc} | [Table 1. Semantic Index Configuration form] {#semantic-index-configuration-form__table_t1b_wjh_xcc}