Semantic Index Configuration form
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 Index Configuration form
The Semantic Index Configuration form in ServiceNow enables you to define and manage semantic indexing settings for AI Search indexed sources. This functionality is accessible only when the AI Search Semantic Controller plugin is activated, which requires at least one ServiceNow Otto® application installed on your instance. Using this form, you can tailor how semantic indexing processes content from specific indexed sources to optimize search relevance and performance.
Show less
Key Features
- Name: Specify a unique, valid name for the semantic index generated. Avoid special characters, underscores, or whitespace.
- Embedding Models: Choose from predefined embedding models to generate semantic vectors:
- ServiceNow Embedding (E5): Default fine-tuned model with a 512-term encoder limit.
- Azure OpenAI Embedding: Integration with Azure’s fine-tuned model for custom embedding.
- Google Gemini Embedding: Google’s fine-tuned embedding integration.
- Custom Embedding: Use your own fine-tuned embedding model (BYOM).
- Active: Toggle to activate or deactivate the semantic index configuration. Inactive configurations are ignored during content indexing.
- Indexed Source: Automatically set reference to the AI Search indexed source to which this configuration applies.
- Application: Automatically set application scope for the configuration record.
- Chunking Configuration for Embedding: Controls how text is segmented (chunked) for semantic indexing, improving search effectiveness depending on content length and structure:
- Chunking Strategy: Choose among Passage (for longer text), Truncate, or Full Text (for shorter text fields).
- Overlap Sentences: For Passage strategy, define how many sentences overlap between chunks to enhance recall, balancing with performance.
- Chunk Unit: Select whether chunk size is measured in words or sentences.
- Chunk Size: Set the maximum number of words or sentences per chunk depending on the chosen chunk unit.
- Maximum Total Words: For Truncate strategy, define the maximum total words indexed from concatenated semantic fields.
Practical Benefits
This configuration form empowers ServiceNow customers to fine-tune semantic search indexing, enabling more accurate and efficient AI-driven search results. By selecting appropriate embedding models and chunking strategies, you can optimize indexing for your specific content types and search requirements. Activating or deactivating configurations allows flexible management of indexing behavior without removing settings.
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.
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 ServiceNow Otto® application installed.
| 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.
|
| 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. |
| 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.
|
| 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.
|
| 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.
|
| 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.
|
| 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.
|