Enable the custom embedding model for semantic indexing

  • Freigeben Version: Australia
  • Aktualisiert 12. März 2026
  • 1 Minute Lesedauer

    • Add your newly created embedding model in the semantic indexing table.

    Vorbereitungen

    Role required: admin

    Prozedur

    1. Navigate to All, and then enter ais_symantic_embedding_model.list in the filter to go to the AI Search Semantic Embedding Models [sys_generative_ai_config] table.
    2. Select New.
    3. In the Name field, enter a unique name.
    4. In the Model Id field, enter a unique id.
    5. In the One Extend Capability Definition field, select a BYOM capability definition you created to set a provider for embedding model.
    6. In the Model Config field, select a configured embedding model.
    7. Select the Active option.
    8. Select the Batching Supported option if you want to configure batching for your embedding model.
    9. In the Minimum Batch Size and Maximum Batch Size fields, enter the required values.
    10. In the Error Handler Extension Instance field, select an error handler instance.
      For more information, see Create error handler extension point.
    11. Select Submit.

    Nächste Maßnahme

    Add your embedding model to the semantic index configuration to enable content ingestion using that model. For more information, see Configure semantic indexing settings for an indexed source.