Overview
AI Foundry is a platform for designing, customizing, and managing AI applications. Use the Azure AI Foundry integration to track the usage and performance of your model deployments.
Setup
Installation
If you haven’t already, set up the Microsoft Azure integration first. There are no other installation steps.
Data Collected
Metrics
| |
|---|
azure.cognitiveservices_accounts.model_availability_rate
(gauge) | Availability percentage with the following calculation: (total calls - server errors)/total calls. Server errors include any HTTP responses >=500.
Shown as percent |
azure.cognitiveservices_accounts.model_requests
(count) | Number of calls made to the model API over a period of time. Applies to PTU, ptu-managed and pay-as-you-go deployments. |
azure.cognitiveservices_accounts.input_tokens
(count) | Number of prompt tokens processed (input) on a model. Applies to PTU, ptu-managed and pay-as-you-go deployments. |
azure.cognitiveservices_accounts.output_tokens
(count) | Number of tokens generated (output) from an openai model. Applies to PTU, ptu-managed and pay-as-you-go deployments. |
azure.cognitiveservices_accounts.total_tokens
(count) | Number of inference tokens processed on a model. Calculated as prompt tokens (input) plus generated tokens (output). Applies to PTU, ptu-managed and pay-as-you-go deployments. |
azure.cognitiveservices_accounts.count
(gauge) | Count of CognitiveServices accounts. |
Service Checks
Azure AI Foundry does not include any service checks.
Events
Azure AI Foundry does not include any events.
Troubleshooting
Need help? Contact Datadog support.
