Oracle Cloud Infrastructure Documentation
Try Free Tier

Updating an Endpoint in Generative AI Agents

  1. On the Agents list page, select the agent that you want to update its endpoint.
    If you need help finding the list page, see Listing Agents
  2. Under Resources, select Endpoints.
  3. Select the name of the endpoint that you want to update.
  4. Select Edit.
  5. Update the following information:
    • The endpoint name and description
    • Idle timeout in seconds. This option appears for endpoints created with enabled sessions. The default timeout is 3600 seconds (1 hour). This means that after the lack of activity between the user and agent for 1 hour, the session automatically ends, and the following conversations don't retain the context of the previous conversation. You can set it as low as 1 hour and as high as 7 days.
  6. Enable or disable Enable storage of large output results: Enable this feature to store large responses from the agent in Object Storage.
    Note

    When SQL execution is enabled on a SQL tool and you enable this feature, Generative AI Agents stores the output in a .csv file only if the SQL command returns more than 100 rows. Generative AI Agents doesn't store SQL results of less than 100 rows.
  7. If you enable storage of large output results, enter the following Object Storage details for storing the output:
    • bucket
    • Object prefix, if you have folders
    • Retention period in minutes. Enter a number up to 1,440 which equals to 24 hours. The default value is 360 minutes which is 6 hours.
  8. Update the options for the following guardrails.
    • Content moderation for input (user prompt), output (generated response), or both:
      • Disable: Don't apply content moderation.
      • Block: Apply content moderation.
      • Inform: Don't apply content moderation, but inform the user if the agent detects content that needs moderation.
    • Prompt injection (PI) protection:
      • Disable: Don't apply PI protection.
      • Block: Apply PI protection.
      • Inform: Don't apply PI protection, but inform the user if the agent detects content that needs PI protection.
    • Personally identifiable information (PII) protection for input (user prompt), output (generated response), or both:
      • Disable: Don't apply PII protection.
      • Block: Apply PII protection.
      • Inform: Don't apply PII protection, but inform the user if the agent detects content that needs PII protection.
  9. Update the following options for the endpoint.
    • Enable trace: Whether to track and display the conversation history, including both the original prompt and the generated response, during the chat conversation. If you don't enable this feature now, you can always add it later by editing the endpoint.
    • Enable citation: Whether to display details about the source of information for each chat response. If you don't enable this feature now, you can always add it later by editing the endpoint.
    • Enable multi-language: Whether to support chatting in the following languages: Arabic, English, French, German, Italian, Japanese, Portuguese, and Spanish. When disabled, English is the default language.
    • Enable human in the loop: Whether a user must oversee the agent's generated responses before the response can be used for use cases. For example, you might disable this feature for agent that runs an API for an application.
  10. Select Save changes.
  11. (Optional) Select Add tags to add tags to this endpoint:
    • Tag namespace: To add a defined tag, select an existing namespace. To add a free-from tag, leave the value blank.
    • Tag key: To add a defined tag, select an existing tag key. To add a free-form tag, type the key name that you want.
    • Tag value: Type the tag value that you want.
    • Add tag: Select to add another tag.

    After you add the tags, select Add tags. You can also select the Tags tab to view and manage the current defined and free-form tags for this endpoint.

Was this article helpful?