OCI Generative AI

Integration version1.0.0

To find out if this integration is available in your organization, see your Datadog Integrations page or ask your organization administrator.

To initiate an exception request to enable this integration for your organization, email support@ddog-gov.com.

Overview

Oracle Cloud Infrastructure (OCI) Generative AI is a fully managed service that provides access to state-of-the-art large language models for tasks like text generation, summarization, and chat.

This integration allows you to monitor and alert on the usage, performance, and errors of your OCI Generative AI resources by collecting metrics and tags from the oci_generativeai namespace.

Setup

Installation

Once you set up the Oracle Cloud Infrastructure integration, ensure that any namespaces mentioned above are included in your Connector Hub.

Data Collected

Metrics

oci.generativeai.client_error_count
(count)		Number of calls with a client side error.
Shown as error
oci.generativeai.input_token_count
(count)		Number of input tokens that the models hosted on this resource have processed.
Shown as token
oci.generativeai.invocation_latency
(gauge)		Total processing time for a call to finish on this resource.
Shown as millisecond
oci.generativeai.output_token_count
(count)		Number of output tokens that the models hosted on this resource have processed.
Shown as token
oci.generativeai.server_error_count
(count)		Number of calls with a service internal error.
Shown as error
oci.generativeai.total_invocation_count
(count)		Number of calls to this resource.
Shown as invocation

Events

OCI Generative AI does not include any events.

Service Checks

OCI Generative AI does not include any service checks.

Troubleshooting

Need help? Contact Datadog support.