Editing a Generative AI Service

Edit a Generative AI Service on the Generative AI Services, Create/Edit page.

This topic describes common Generative AI Service attributes. The actual attributes that display depend upon the selected AI Provider. To learn more about an attribute, see item Help.

To edit a Generative AI Service:

Navigate to the Generative AI Services page:
1. On the Workspace home page, click the App Builder icon.
2. On the App Builder home page, click the Workspace Utilities icon.
3. On the Workspace Utilities page, click Generative AI.
  
  The Generative AI Services page appears.
Select the AI Service Name.
Under Identification:
1. Identification, AI Provider - Determines the AI Provider to use for this Generative AI Service.
2. Identification, Name - The name of the Generative AI Service. The name displays on the Generative AI Services page in Workspace Utilities.
  
  Example: HCM OpenAI Service
  
  After this step, the UI changes depending upon the AI Provider you select. The steps that follow describe common attributes. To learn more about an attribute, see item Help.
Under OCI Generative AI:
1. Compartment ID - The Oracle Cloud Infrastructure Compartment ID used for OCI Generative AI requests.
2. Serving Mode - Select On-Demand or Dedicated.
3. Endpoint ID - Required when Serving Mode is Dedicated.
4. Region - The Oracle Cloud Infrastructure Region. If the region is altered for an existing OCI Generative AI service configuration, make sure to also change the corresponding Web Credential or create a new Web Credential for the selected region.
5. Project ID - Required when Provider API is Responses.
Settings:
1. Settings, Used by App Builder - When enabled, this Generative AI Service is used by App Builder.
2. Settings, Default for New Apps - When enabled, this Generative AI Service is automatically selected as the default AI Service for all newly created applications.
3. Settings, AI Model - The model to use for the Generative AI Service.
Credentials:

The Credentials attributes that display depend upon the selected AI Provider.
1. Edit the attributes. To learn more about an attribute, see item Help.
2. Test Connection - Select Test Connection to validate the information you enter prior to completing the setup. APEX tests the selected Provider API and validates the applicable OCI fields.
  
  If the connection is valid, the following message displays:
  
  Connection Succeeded!
  
  If the connection fails, resolve the errors that display.
Advanced:

The Advanced attributes that appear next depend upon the selected AI Provider. To learn more, see item Help.
1. Advanced, Additional Attributes - Specify additional provider-specific attributes in JSON format. The supported JSON structure depends on the selected Provider API.
2. Advanced, Provider API - Select the API format used by the Generative AI Service. Available values depend on the selected AI Provider. Chat Completions and Generate Text are deprecated.
3. Advanced, Static ID - The Static ID for the Generative AI Service. The static ID is used when using the service with the APEX_AI package (APEX_AI.CHAT).
  
  Example: HCM_OPENAI
4. Advanced, Maximum AI Tokens - Enter the maximum number of AI Tokens per 24 hour period that Oracle APEX can use for the Generative AI Service. Not every Generative AI Service provides token usage information, so Oracle APEX may not be able to enforce this limit.
  
  The APEX_AI.GET_AVAILABLE_TOKENS function also returns the number of tokens available.
  
  An administrator can also set the Maximum AI Tokens at the workspace or instance-level. See Viewing Existing Workspace Information and Configuring Instance-Level Workspace Isolation Attributes in Oracle APEX Administration Guide.
5. Advanced, HTTP Headers - Additional HTTP headers used in the Generative AI Service (REST) request.
  
  HTTP headers are specified in the following format:
  
  name_1=value_1
  
  name_2=value_2
6. Advanced, Comments - Enter any developer comments or notes.
Select Apply Changes.