How can we enable private endpoint for Pay as you go Model Endpoints in Azure AI
Following Meta Llama 2 7B product in Azure marketplace, I deployed it in azure ai service. AFter the deployment I got my endpoint as something like
https://mydemo-llama-serverless.eastus2.inference.ai.azure.com
I already enabled the private endpoint for my Azure AI but those endpoints can give the private endpoints for the domain privatelink.api.azureml.ms and privatelink.notebooks.azure.net however my Pay-as-you-go deployment having the domain as inference.ai.azure.com which is still public.
Question: How can I make my inference endpoint for my Pay-as-you-go model deployment as private?
If the answer is not yet supported can someone guide me on any workaround or when we can expect this feature?
Finally, Microsoft has released this feature around July, read more here
I tried the solution and noticed one additional limitation will be
If an AI hub is disabled public network, It cannot able to reach the marketplace to subscribe the models. Please see my below error
To be exact the API which is failing is
https://ai.azure.com/api/<region>/modelEndpointDiscovery/v1.0/subscriptions/<>/resourceGroups/<>/providers/Microsoft.MachineLearningServices/workspaces/demoproject/marketplaceSubscriptions?api-version=2023-10-01-preview
with 403 Forbidden
To bypass this error, I have to make the Hub publicly accessible then subscribe to the model from the marketplace, and then deploy after all this is done. I have to revert my hub to disable public access after subscribing from the marketplace
- Can't signin into microsoft account
- TenantGuidNotFound when trying to send email using Microsfot GraphAPI
- Azure Function App Kudu Functions API with empty response
- Get Azure Active Directory password expiry date in PowerShell
- Provision new SQL Azure database into existing, non-terraform managed SQL Server instance
- Azure Logic App HTTP Request Authentication Scope
- Get Log analytics workspace ID of a virtual machine in Azure connected to a workspace in a different subscription
- Enabling minimum apiVersion to 2021-08-01 in Azure API Management causing saving issues or deployment errors for existing logic apps
- Privileged Identity Management - My roles
- Creating a VM in Azure using Powershell
- Creating multiple function apps with one Flex Consumption plan
- Azure Bicep reference existing resources from different subscriptions using ternary operators inside scope property
- Trigger azure function on user registration in b2c
- Migrating from validate-jwt to validate-azure-ad-token policy
- Azure DevOps Pipeline Expression Evaluation
- Using Event Hubs binding for Azure Functions with managed identities?
- How to connect a microsoft SQL Server database to Open Data Discovery (odd-odd-platform)?
- Cosmos DB for MongoDB private endpoint requests blocked by network firewall
- Specifying SAS Token Authorization header with Azure REST API
- Databricks ui is different between different Azure Tenants with activated SCIM Integration
- Download large files in Azure image builder process
- TriggerBuild Could not queue the build because there were validation errors or warnings
- How to filter users in directory by company name with Microsoft Graph Java SDK?
- How to get the azure subscription current cost using PowerShell
- How to automate Azure Data Factory (ADF) credential updates from development to production using Azure DevOps?
- Azure Form Recognizer Set API Version
- Is there a way to deploy a azure function directly to a storage account with private endpoint
- How do I flatten certain properties in a nested structure using Linq for Cosmos noSQL?
- Unable to locate executable file: 'bash'. Please verify either the file path exists
- "We're sorry, your sql database is unavailable" What does this mean exactly in Azure SQL?