How to enforce a processing location for Azure Content Understanding in Foundry Tools resource?

Jan Dolecek 60 Reputation points
2026-07-08T13:17:11.2666667+00:00

Dear Azure team,

I have an interest in utilizing a Content Understanding service for analyzing documents, videos and creating own custom analyzers. The problem i am facing is whether is it possible to enforce the processing location for this service for other developers calling its endpoints?

So far i have been able to do this for other AI services like for example document intelligence or speech service (where processing occurs only in the region where the resource was created). Similarly for Azure OpenAI i could enforce data store location by creating an OpenAI resource in the given region and processing location by specifying for individual created model deployments (standard, global, data zone deployment etc.).

In Content Understanding all data are stored in the region of the resource, but the processing occurs based on the deployment type of my model deployments in Foundry and processingLocation parameter (https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/language-region-support#region-support-1).

What is problematic is that processingLocation parameter can be specified directly in the REST API request (for example see https://learn.microsoft.com/en-us/rest/api/contentunderstanding/content-analyzers/analyze?view=rest-contentunderstanding-2025-11-01&tabs=HTTP) and cannot be set directly in the Azure configuration of the Foundry/Content Understanding itself. That way any developer calling its endpoint can start processing the file outside our allowed regions or if not specified, then globally (as the default setting). Me as an Azure admin i don't see any other way how to enforce this other than developing some custom API gateway solution in front of this endpoint enforcing the correct configuration for this parameter (for example "data-zone" only) - on the other hand this solution would be then complicated for using Content Understanding UI (https://contentunderstanding.ai.azure.com/), because this can be only integrated directly to Foundry resource.

Are there please any other solutions or ways I am currently missing?

Thank you for any provided information and tips to help me resolve this issue.

Foundry Tools
Foundry Tools

Formerly known as Azure AI Services or Azure Cognitive Services is a unified collection of prebuilt AI capabilities within the Microsoft Foundry platform

0 comments
Answer accepted by question author
Thanmayi Godithi 11,905 Reputation points Microsoft External Staff Moderator
2026-07-08T13:45:04.8+00:00

Hi Jan Dolecek ,

Thank you for reaching out on Microsoft Q&A forum.

For Azure Content Understanding in Foundry Tools, it's important to distinguish between data storage location and processing location.

Data is stored in the region where the Foundry Tools resource is created, while the location where analysis is processed is determined by the supported processing locations and the processingLocation value supplied with the analysis request.

Because processingLocation is part of the API request, callers can choose from the processing options supported by the service and region. The documentation also notes that supported processing locations vary by region and scenario, and certain modes support only specific processing-location options.

From a governance perspective, there is no resource-level setting in Content Understanding that forces all requests to use a single processing location (for example, dataZone) regardless of what the caller sends. As a result, organizations that require strict enforcement of processing geography typically place a controlled layer in front of the service, such as an API gateway, to validate or enforce request parameters before requests reach the Content Understanding endpoint.

If your compliance requirements mandate that all processing remain within a specific geography or data zone, that gateway-based enforcement approach is currently the most practical way to ensure consistent behavior across all clients and developers using the service.

Kindly let us know if the above helps or you need further assistance on this issue.

If the answer is helpful, please click "Accept Answer" and kindly upvote it. If you have extra questions about this answer, please click "Comment".

Was this answer helpful?

1 person found this answer helpful.

0 additional answers

Sort by: Newest
Most helpful Newest Oldest

Your answer

Answers can be marked as 'Accepted' by the question author and 'Recommended' by moderators, which helps users know the answer solved the author's problem.