Skip to content

Commit 77b2cd4

Browse files
committed
foundry portal freshness
1 parent 9c75a8e commit 77b2cd4

File tree

5 files changed

+9
-23
lines changed

5 files changed

+9
-23
lines changed

articles/ai-foundry/ai-services/content-safety-overview.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -7,7 +7,7 @@ ms.service: azure-ai-foundry
77
ms.custom:
88
- ignite-2024
99
ms.topic: overview
10-
ms.date: 05/01/2025
10+
ms.date: 05/31/2025
1111
ms.author: pafarley
1212
author: PatrickFarley
1313
---

articles/ai-foundry/concepts/content-filtering.md

Lines changed: 4 additions & 17 deletions
Original file line numberDiff line numberDiff line change
@@ -9,7 +9,7 @@ ms.custom:
99
- build-2024
1010
- ignite-2024
1111
ms.topic: conceptual
12-
ms.date: 04/29/2025
12+
ms.date: 05/31/2025
1313
ms.reviewer: eur
1414
ms.author: pafarley
1515
author: PatrickFarley
@@ -24,9 +24,9 @@ author: PatrickFarley
2424
2525
## How it works
2626

27-
The content filtering system is powered by [Azure AI Content Safety](../../ai-services/content-safety/overview.md), and it works by running both the prompt input and completion output through a set of classification models designed to detect and prevent the output of harmful content. Variations in API configurations and application design might affect completions and thus filtering behavior.
27+
The content filtering system is powered by [Azure AI Content Safety](../../ai-services/content-safety/overview.md), and it works by running both the model prompt input and completion output through a set of classification models designed to detect and prevent the output of harmful content. Variations in API configurations and application design might affect completions and thus filtering behavior.
2828

29-
With Azure OpenAI model deployments, you can use the default content filter or create your own content filter (described later on). Models available through **standard deployments** have content filtering enabled by default. To learn more about the default content filter enabled for standard deployments, see [Content safety for Models Sold Directly by Azure ](model-catalog-content-safety.md).
29+
With Azure OpenAI model deployments, you can use the default content filter or create your own content filter (described later). Models available through **standard deployments** have content filtering enabled by default. To learn more about the default content filter enabled for standard deployments, see [Content safety for Models Sold Directly by Azure ](model-catalog-content-safety.md).
3030

3131
## Language support
3232

@@ -73,20 +73,7 @@ You can also enable the following special output filters:
7373

7474
### Configurability (preview)
7575

76-
The default content filtering configuration for the GPT model series is set to filter at the medium severity threshold for all four content harm categories (hate, violence, sexual, and self-harm) and applies to both prompts (text, multi-modal text/image) and completions (text). This means that content that is detected at severity level medium or high is filtered, while content detected at severity level low isn't filtered by the content filters. For DALL-E, the default severity threshold is set to low for both prompts (text) and completions (images), so content detected at severity levels low, medium, or high is filtered.
77-
78-
The configurability feature allows customers to adjust the settings, separately for prompts and completions, to filter content for each content category at different severity levels as described in the table below:
79-
80-
| Severity filtered | Configurable for prompts | Configurable for completions | Descriptions |
81-
|-------------------|--------------------------|------------------------------|--------------|
82-
| Low, medium, high | Yes | Yes | Strictest filtering configuration. Content detected at severity levels low, medium and high is filtered.|
83-
| Medium, high | Yes | Yes | Content detected at severity level low isn't filtered, content at medium and high is filtered.|
84-
| High | Yes| Yes | Content detected at severity levels low and medium isn't filtered. Only content at severity level high is filtered. Requires approval<sup>1</sup>.|
85-
| No filters | If approved<sup>1</sup>| If approved<sup>1</sup>| No content is filtered regardless of severity level detected. Requires approval<sup>1</sup>.|
86-
87-
<sup>1</sup> For Azure OpenAI models, only customers who have been approved for modified content filtering have full content filtering control, including configuring content filters at severity level high only or turning off content filters. Apply for modified content filters via these forms: [Azure OpenAI Limited Access Review: Modified Content Filters](https://customervoice.microsoft.com/Pages/ResponsePage.aspx?id=v4j5cvGGr0GRqy180BHbR7en2Ais5pxKtso_Pz4b1_xUMlBQNkZMR0lFRldORTdVQzQ0TEI5Q1ExOSQlQCN0PWcu), and [Modified Abuse Monitoring](https://customervoice.microsoft.com/Pages/ResponsePage.aspx?id=v4j5cvGGr0GRqy180BHbR7en2Ais5pxKtso_Pz4b1_xUOE9MUTFMUlpBNk5IQlZWWkcyUEpWWEhGOCQlQCN0PWcu).
88-
89-
Customers are responsible for ensuring that applications integrating Azure OpenAI comply with the [Code of Conduct](/legal/ai-code-of-conduct?context=%2Fazure%2Fai-services%2Fopenai%2Fcontext%2Fcontext).
76+
[!INCLUDE [content-filter-configurability](../../ai-services/openai/includes/content-filter-configurability.md)]
9077

9178

9279
## Related content

articles/ai-foundry/how-to/use-blocklists.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -7,7 +7,7 @@ ms.service: azure-ai-foundry
77
ms.custom:
88
- ignite-2024
99
ms.topic: how-to
10-
ms.date: 05/01/2025
10+
ms.date: 05/31/2025
1111
ms.author: pafarley
1212
author: PatrickFarley
1313
---

articles/ai-foundry/responsible-use-of-ai-overview.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -6,7 +6,7 @@ manager: nitinme
66
keywords: Azure AI services, cognitive
77
ms.service: azure-ai-foundry
88
ms.topic: overview
9-
ms.date: 05/09/2025
9+
ms.date: 05/31/2025
1010
ms.author: pafarley
1111
author: PatrickFarley
1212
ms.custom: ignite-2024

articles/ai-services/responsible-use-of-ai-overview.md

Lines changed: 2 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -6,7 +6,7 @@ author: PatrickFarley
66
manager: nitinme
77
ms.service: azure-ai-services
88
ms.topic: conceptual
9-
ms.date: 05/01/2025
9+
ms.date: 05/31/2025
1010
ms.author: pafarley
1111
---
1212

@@ -20,9 +20,8 @@ Azure AI services provides information and guidelines on how to responsibly use
2020

2121
## Vision
2222
- [Azure AI Vision - Image Analysis](/legal/cognitive-services/computer-vision/imageanalysis-transparency-note?context=/azure/ai-services/computer-vision/context/context)
23-
- [Azure AI Vision - OCR](/legal/cognitive-services/computer-vision/ocr-transparency-note?context=/azure/ai-services/computer-vision/context/context)
23+
- [Azure AI Vision - OCR (legacy)](/legal/cognitive-services/computer-vision/ocr-transparency-note?context=/azure/ai-services/computer-vision/context/context)
2424
- [Azure AI Vision - Face](/legal/cognitive-services/face/transparency-note?context=/azure/ai-services/computer-vision/context/context)
25-
- [Azure AI Vision - Spatial Analysis](/legal/cognitive-services/computer-vision/transparency-note-spatial-analysis?context=/azure/ai-services/computer-vision/context/context)
2625
- [Azure Custom Vision](/legal/cognitive-services/custom-vision/custom-vision-cvs-transparency-note?context=/azure/ai-services/custom-vision-service/context/context)
2726
- [Azure Video Indexer](/legal/azure-video-indexer/transparency-note?context=%2Fazure%2Fazure-video-indexer%2Fcontext%2Fcontext)
2827

0 commit comments

Comments
 (0)