Data Source: oci_generative_ai_agent_agent_endpoint

This data source provides details about a specific Agent Endpoint resource in Oracle Cloud Infrastructure Generative Ai Agent service.

Gets information about an endpoint.

Example Usage

data "oci_generative_ai_agent_agent_endpoint" "test_agent_endpoint" {
	#Required
	agent_endpoint_id = oci_generative_ai_agent_agent_endpoint.test_agent_endpoint.id
}

Argument Reference

The following arguments are supported:

• agent_endpoint_id - (Required) The OCID of the endpoint.

Attributes Reference

The following attributes are exported:

• agent_id - The OCID of the agent that this endpoint is associated with.
• compartment_id - The OCID of the compartment.
• content_moderation_config - The configuration details about whether to apply the content moderation feature to input and output. Content moderation removes toxic and biased content from responses. It is recommended to use content moderation.
  • should_enable_on_input - A flag to enable or disable content moderation on input.
  • should_enable_on_output - A flag to enable or disable content moderation on output.
• defined_tags - Defined tags for this resource. Each key is predefined and scoped to a namespace. For more information, see Resource Tags. Example: {"Operations.CostCenter": "42"}
• description - An optional description of the endpoint.
• display_name - A user-friendly name. Does not have to be unique, and it’s changeable.
• freeform_tags - Free-form tags for this resource. Each tag is a simple key-value pair with no predefined name, type, or namespace. For more information, see Resource Tags. Example: {"Department": "Finance"}
• guardrail_config - The configuration details about whether to apply the guardrail checks to input and output.
  • content_moderation_config - The configuration details about whether to apply the content moderation feature to input and output. Content moderation removes toxic and biased content from responses. It is recommended to use content moderation.
    • input_guardrail_mode - An input guardrail mode for content moderation.
    • output_guardrail_mode - An output guardrail mode for content moderation.
  • personally_identifiable_information_config - The configuration details for Personally Identifiable Information.
    • input_guardrail_mode - An input guardrail mode for personally identifiable information.
    • output_guardrail_mode - An output guardrail mode for personally identifiable information.
  • prompt_injection_config - The configuration details for Prompt Injection.
    • input_guardrail_mode - An input guardrail mode for prompt injection.
• human_input_config - Human Input Configuration for an AgentEndpoint.
  • should_enable_human_input - The Agent will request for human input for disambiguation or additional information gathering if this is enabled.
• id - The OCID of the endpoint.
• lifecycle_details - A message that describes the current state of the endpoint in more detail. For example, can be used to provide actionable information for a resource in the Failed state.
• metadata - Key-value pairs to allow additional configurations.
• output_config - Configuration to store results generated by agent.
  • output_location - Location of the output.
    • bucket - The name of the bucket.
    • namespace - The namespace of the object storage.
    • output_location_type - Type of OutputLocation.
    • prefix - The prefix of the object storage.
  • retention_period_in_minutes - Retention duration of the output data.
• session_config - Session Configuration on AgentEndpoint.
  • idle_timeout_in_seconds - The session will become inactive after this timeout.
• should_enable_citation - Whether to show citations in the chat result.
• should_enable_multi_language - Whether to enable multi-language for chat.
• should_enable_session - Whether or not to enable Session-based chat.
• should_enable_trace - Whether to show traces in the chat result.
• state - The current state of the endpoint.
• system_tags - System tags for this resource. Each key is predefined and scoped to a namespace. Example: {"orcl-cloud.free-tier-retained": "true"}
• time_created - The date and time the AgentEndpoint was created, in the format defined by RFC 3339. Example: 2016-08-25T21:10:29.600Z
• time_updated - The date and time the endpoint was updated, in the format defined by RFC 3339. Example: 2016-08-25T21:10:29.600Z