---
sourceDocument: Zurich ServiceNow AI Platform Administration
sourceDocumentLink: https://www.servicenow.com/docs/r/zurich/platform-administration

 Release :

    - zurich

ft:locale :

    - en-US

ft:publication_title :

    - Zurich ServiceNow AI Platform Administration

ft:clusterId :

    - platadm

bundleId :

    - platadm

workflow :

    - Platform


---

# Connect your custom embedding model with the Generative AI application

# Connect your custom embedding model with the Generative AI application {#ariaid-title1}

Release version: Zurich  
Updated July 31, 2025  
![](https://www.servicenow.com/docs/portal-asset/ico-clock) 1 minute to read  
Integrate your custom embedding model with a capability definition to help the Generative AI application understand your data better and deliver more relevant, tailored responses.

## Before you begin

Role required: admin

## Procedure

1. Navigate to All, and then enter <kbd class="ph userinput">sys_generative_ai_config.list</kbd> in the filter to go to the Generative AI Configurations \[sys_generative_ai_config\] table.
2. Select New.
3. Verify that Definition Table field is prepopulated with sys_one_extend_capability_definition.
4. In the Definition field, select the search icon ![Lookup documents using list.]()to select the definition document.
   1. In the Table name field, select One API System Executor \[one_api_system_executor\].
   2. In the Document field, select the OneExtend capability definition that you want to integrate with the embedding model.
   3. Select OK.
   {#connect-em-with-genai__substeps_a1h_1gr_bgc}
5. In the Model field, select an embedding model of your choice.
6. Select the Active option.
7. Populate the Additional Configurations field.  
   * In the Name field, enter <kbd class="ph userinput">resource _path</kbd>.
   * In the Value field, enter the end point path for the connection alias URL that you created for your embedding model.

     For example,
     <kbd class="ph userinput">/text-embedding-3-large/embeddings?api-version=2023-05-15</kbd>.

     It ensures that the base URL remains generic and reusable, while the specific resource path can be adjusted as
     needed for different models. For more information, see [Configuring resource path for your custom embedding model](https://www.servicenow.com/docs/4zRLRCrZFDj9VJAC8ciaGw "The bring your own model (BYOM) configuration uses the shared alias from Generative AI Controller to connect the LLM with your custom embedding model. To avoid configuration issues, ensure the connection URL is set separately and any additional paths are correctly set in the resource path.").
   {#connect-em-with-genai__ul_vv2_yqr_bgc}
8. Select Submit.