Updating the embedding model for semantic indexing

BMC HelixGPT maintains accurate search results by indexing data correctly during semantic model updates. This prevents issues that occur when indexes change while jobs are running. The data editor supports a configurable embedding model for better semantic indexing. You can switch to a new embedding model with enhanced k-NN vector settings.

Before you begin

Make sure to create a clone of the existing index.

Task 1: To clone the existing index

1. Log in to BMC Helix Innovation Studio.
2. In the Workspace tab, go to HelixGPT Agent Studio.
3. From the Records, select the DataConnectionJob and click Edit data.
4. In the Data editor (DataConnectionJob) window, click the job you want to clone.
5. In the Edit record window, specify the following fields:

   Field name	Description
   Type	Select Clone Index.
   SourceSemanticIndexId	Specify the ID of the currently active model.
   TargetSemanticIndexId	Specify the ID of the model you want to activate. To ensure that INGEST_DATA jobs use the correct semantic index and embedding model, specify a value for the TargetSemanticIndexId field for ingestion and cloning jobs. If this value is not set, the system uses the currently active index unless you manually change it.
   ExecuteNow.	Enable the radio button.

   

6. Click Save.

Task 2: To activate the embedding model for semantic indexing

1. Log in to BMC Helix Innovation Studio.
2. On the Workspace tab, click HelixGPT Agent Studio.
3. From the Records, select the SemanticIndex and click Edit data.
4. In the Data editor (SemanticIndex) window, click the model you want to activate.
5. In the Edit record window, from the Status drop-down list, select Active.
   
6. Click Save.
   The new model is activated, and the status of a previously active model automatically changes to Enabled.

Related links

Adding custom fields as attributes to the semantic model