Exploring Query Generation
Summarize
Summary of Exploring Query Generation
Query Generation is an AI-powered ServiceNow feature that converts user questions into executable queries, delivering results that include textual summaries, data visualizations, and follow-up suggestions. It leverages a semantic data layer, which organizes tables and columns into Entity and Dimension records, to accurately map user queries to relevant data sources.
Show less
This service is designed to provide precise, actionable query results by focusing only on relevant parts of the data schema, thereby enhancing accuracy and preventing the generation of queries based on incorrect or non-existent data structures.
How Query Generation Works
- Filters the instance schema to select the two most relevant Entity (facts) tables and the 30 most relevant Dimension (columns) based on the user’s question.
- Uses this filtered semantic data to generate a semantic query via a large language model (LLM).
- Translates the semantic query into an executable query that includes data source, filters, aggregations, and visualization instructions.
This process ensures better LLM performance and reduces hallucinations by limiting the context to relevant schema information.
Configuration and Management
Not all facts tables are included by default to avoid performance issues. Administrators can view and modify which tables participate via the Semantic Tables Configurations list, enabling or disabling semantic generation per table as needed. However, caution is advised when adding tables to avoid impacting system performance.
Users and Roles
- ServiceNow AI Platform administrators: Manage semantic data layer configurations, including adding or removing tables. Only users with the admin role can modify Query Generation records.
- End users of Now Assist in Platform Analytics applications: Access Query Generation functionality indirectly through these applications, with appropriate roles assigned. Query Generation is not directly visible to these users.
Next Steps
To implement or optimize Query Generation, ServiceNow customers should explore detailed configuration options and reference materials provided by ServiceNow for configuring Query Generation and understanding its capabilities in depth.
Query Generation is an AI-powered service that translates user questions into an executable query and returns the results. An executable query contains the data source, filter, aggregation, and visualization instructions that best answer the user's question. The results include a textual summary, a data visualization, and suggestions for follow-up.
Query Generation overview
Query Generation relies on a semantic data layer to generate queries. The semantic data layer is a flat representation of tables and table columns that the Query Generator uses to find the actual facts tables and columns related to a user utterance. Specifically, facts tables are represented by Entity records and their columns by Dimension records.
Not all facts tables are included in Query Generation, as this would overload an instance. To see which facts tables are included, open the Semantic Tables Configurations list [sn_query_gen_table_config_list], and note which tables are present and have Enable Semantic Generation = true. You can add more tables to the list, but be careful of possible performance impacts. For more information, see Add a table to the semantic data layer.
How Query Generation works
- It provides the LLM with precise grounds for truth about available tables and columns, preventing hallucination of non-existent data structures.
- It maintains a focused context window, which improves LLM performance and accuracy compared to processing the entire schema.
Query Generation uses a semantic filter to narrow the entities (facts tables) to the 2 closest matches to the user's question. Then from those entities, it narrows the dimensions (columns) to the 30 most similar to the user's question. Query Generation passes these results to the LLM, which generates a semantic query. A constitutor takes this semantic query and translates it into an executable query.
Query Generation users
| User | Description |
|---|---|
| ServiceNow AI Platform administrators responsible for Now Assist in Platform Analytics [admin] | Administrators can add or remove tables from the semantic data layer. Only users with the admin role can read or change Query Generation records. |
| Users of Now Assist in Platform Analytics applications | Users of the Now Assist in Platform Analytics applications call Query Generation through those applications, although Query Generation is not visible to them. They should have the required Query Generation user roles through the roles granted to them to use the intermediary application. |