Skip to content

Commit 876aabf

Browse files
committed
add disable content filtering
1 parent 9572efe commit 876aabf

File tree

1 file changed

+22
-2
lines changed

1 file changed

+22
-2
lines changed

articles/ai-services/content-understanding/overview.md

Lines changed: 22 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -7,7 +7,7 @@ ms.author: lajanuar
77
manager: nitinme
88
ms.service: azure-ai-content-understanding
99
ms.topic: overview
10-
ms.date: 02/19/2025
10+
ms.date: 03/06/2025
1111
ms.custom: ignite-2024-understanding-release
1212

1313
#customer intent: As a user, I want to learn more about Content Understanding solutions.
@@ -77,13 +77,33 @@ See [Quickstart](quickstart/use-ai-foundry.md) for more examples.
7777

7878
### Modified Content Filtering
7979

80-
Azure AI Content Understanding now supports turning off content filtering for approved customers. The subscription IDs with approved modified content filtering impacts the Azure AI Content Understanding output.
80+
Azure AI Content Understanding now supports disabling content filtering for approved customers. The subscription IDs with approved modified content filtering impacts the Azure AI Content Understanding output.
8181

8282
> [!IMPORTANT]
8383
>
8484
> * Apply for modified content filters via this form: [Azure OpenAI Limited Access Review: Modified Content Filters](https://ncv.microsoft.com/uEfCgnITdR).
8585
> * For more information, *see* [**Content Filtering**](../openai/concepts/content-filter.md).
8686
87+
By default, Content Understanding employs a content filtering system that identifies specific risk categories for potentially harmful content in both submitted prompts and generated outputs. If content is flagged with a high severity level, indicating a significant potential for harm, the output is blocked. For more information on risk categories, *see* [Content filtering](../openai/concepts/content-filter.md#risk-categories).
88+
89+
To disable content filtering, follow these steps:
90+
91+
* Complete the [Azure OpenAI Limited Access Review: Modified Content Filtering](https://customervoice.microsoft.com/Pages/ResponsePage.aspx?id=v4j5cvGGr0GRqy180BHbR7en2Ais5pxKtso_Pz4b1_xUMlBQNkZMR0lFRldORTdVQzQ0TEI5Q1ExOSQlQCN0PWcu) for your subscription.
92+
93+
* Once approved, create or update your Content Understanding analyzer to include the property `"disableContentFiltering": true`as follows:
94+
95+
```bash
96+
{
97+
"config": {
98+
"enableFace": true,
99+
"returnDetails": true,
100+
"disableContentFiltering": true
101+
}
102+
```
103+
104+
105+
106+
87107
## Data privacy and security
88108
Developers using the Content Understanding service should review Microsoft's policies on customer data. For more information, visit our [**Data, protection and privacy**](https://www.microsoft.com/trust-center/privacy) page.
89109

0 commit comments

Comments
 (0)