Skip to content

Commit 5aa211e

Browse files
ElazarKElazarK
committed
Merge branch 'main' of https://github.com/MicrosoftDocs/azure-docs-pr into WI274839-aI-threat-protection
2 parents 5b2d832 + 1b42492 commit 5aa211e

File tree

450 files changed

+5703
-2761
lines changed

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

450 files changed

+5703
-2761
lines changed

‎.openpublishing.publish.config.json

Lines changed: 6 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1225,6 +1225,12 @@
12251225
"url": "https://github.com/MicrosoftDocs/SupportArticles-docs",
12261226
"branch": "main",
12271227
"branch_mapping": {}
1228+
},
1229+
{
1230+
"path_to_root": "msdocs-python-fastapi-webapp-quickstart",
1231+
"url": "https://github.com/Azure-Samples/msdocs-python-fastapi-webapp-quickstart",
1232+
"branch": "main",
1233+
"branch_mapping": {}
12281234
}
12291235
],
12301236
"branch_target_mapping": {

‎.openpublishing.redirection.baremetal-infrastructure.json

Lines changed: 6 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -134,6 +134,11 @@
134134
"source_path_from_root": "/articles/baremetal-infrastructure/workloads/sap/baremetal-overview-architecture.md",
135135
"redirect_url": "/azure/baremetal-infrastructure/concepts-baremetal-infrastructure-overview",
136136
"redirect_document_id": false
137-
}
137+
},
138+
{
139+
"source_path": "articles/baremetal-infrastructure/workloads/nc2-on-azure/solution-design.md",
140+
"redirect_url": "/azure/baremetal-infrastructure/workloads/nc2-on-azure/architecture",
141+
"redirect_document_id": false
142+
}
138143
]
139144
}

‎.openpublishing.redirection.json

Lines changed: 20 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1189,6 +1189,16 @@
11891189
"redirect_url": "/azure/azure-maps/",
11901190
"redirect_document_id": true
11911191
},
1192+
{
1193+
"source_path_from_root": "/articles/azure-maps/tutorial-creator-indoor-maps.md",
1194+
"redirect_url": "/azure/azure-maps/creator-indoor-maps",
1195+
"redirect_document_id": false
1196+
},
1197+
{
1198+
"source_path_from_root": "/articles/azure-maps/about-creator.md",
1199+
"redirect_url": "/azure/azure-maps/creator-indoor-maps",
1200+
"redirect_document_id": true
1201+
},
11921202
{
11931203
"source_path_from_root": "/articles/azure-maps/search-categories.md",
11941204
"redirect_url": "/azure/azure-maps/supported-search-categories",
@@ -3702,6 +3712,16 @@
37023712
"redirect_url": "/sql/sql-server/stretch-database/stretch-database-databases-and-tables-stretch-database-advisor",
37033713
"redirect_document_id": false
37043714
},
3715+
{
3716+
"source_path_from_root": "/articles/stream-analytics/stream-analytics-job-metrics.md",
3717+
"redirect_url": "/azure/stream-analytics/monitor-azure-stream-analytics-reference#metrics",
3718+
"redirect_document_id": false
3719+
},
3720+
{
3721+
"source_path_from_root": "/articles/stream-analytics/stream-analytics-job-metrics-dimensions.md",
3722+
"redirect_url": "/azure/stream-analytics/monitor-azure-stream-analytics-reference#metric-dimensions",
3723+
"redirect_document_id": false
3724+
},
37053725
{
37063726
"source_path_from_root": "/articles/dms/tutorial-azure-postgresql-to-azure-postgresql-online-portal.md",
37073727
"redirect_url": "/azure/postgresql/migrate/migration-service/tutorial-migration-service-single-to-flexible",

‎.openpublishing.redirection.operator-nexus.json

Lines changed: 6 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -29,6 +29,11 @@
2929
"source_path_from_root": "/articles/operator-nexus/template-cloud-native-network-function-deployment.md",
3030
"redirect_url": "/azure/operator-nexus/quickstarts-kubernetes-cluster-deployment-cli",
3131
"redirect_document_id": false
32+
},
33+
{
34+
"source_path_from_root": "/articles/operator-nexus/concepts-nexus-network.md",
35+
"redirect_url": "/azure/operator-nexus/concepts-nexus-networking",
36+
"redirect_document_id": false
3237
}
3338
]
34-
}
39+
}

‎articles/active-directory-b2c/claimsschema.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -395,7 +395,7 @@ The **Readonly** user input type is used to provide a readonly field to display
395395

396396
#### Paragraph
397397

398-
The **Paragraph** user input type is used to provide a field that shows text only in a paragraph tag. For example, <p>text</p>. A **Paragraph** user input type `OutputClaim` of self-asserted technical profile, must set the `Required` attribute `false` (default).
398+
The **Paragraph** user input type is used to provide a field that shows text only in a paragraph tag. For example, <p>text</p>. A **Paragraph** user input type `OutputClaim` of self-asserted technical profile, must set the `Required` attribute `false` (default). This user input type is only supported in self-asserted page layouts. Unified sign-in and sign-up pages (unifiedssp) might not display this properly.
399399

400400
![Using claim type with paragraph](./media/claimsschema/paragraph.png)
401401

‎articles/ai-services/.openpublishing.redirection.ai-services.json

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -3,12 +3,12 @@
33
{
44
"source_path_from_root": "/articles/ai-services/computer-vision/how-to/install-sdk.md",
55
"redirect_url": "/azure/ai-services/computer-vision/sdk/install-sdk",
6-
"redirect_document_id": false
6+
"redirect_document_id": true
77
},
88
{
99
"source_path_from_root": "/articles/ai-services/document-intelligence/concept-document-intelligence-studio.md",
1010
"redirect_url": "/azure/ai-services/document-intelligence/studio-overview",
11-
"redirect_document_id": false
11+
"redirect_document_id": true
1212
}
1313
]
14-
}
14+
}

‎articles/ai-services/openai/concepts/default-safety-policies.md

Lines changed: 68 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,68 @@
1+
---
2+
title: Azure OpenAI default content safety policies
3+
titleSuffix: Azure OpenAI
4+
description: Learn about the default content safety policies that Azure OpenAI uses to flag content.
5+
author: PatrickFarley
6+
ms.author: pafarley
7+
ms.service: azure-ai-openai
8+
ms.topic: conceptual
9+
ms.date: 07/15/2024
10+
manager: nitinme
11+
---
12+
13+
# Default content safety policies
14+
15+
16+
Azure OpenAI Service includes default safety applied to all models, excluding Azure OpenAI Whisper. These configurations provide you with a responsible experience by default, including [content filtering models](/azure/ai-services/openai/concepts/content-filter?tabs=warning%2Cpython-new), blocklists, prompt transformation, [content credentials](/azure/ai-services/openai/concepts/content-credentials), and others.
17+
18+
Default safety aims to mitigate risks such as hate and fairness, sexual, violence, self-harm, protected material content and user prompt injection attacks. To learn more about content filtering, visit our documentation describing categories and severity levels [here](/azure/ai-services/openai/concepts/content-filter?tabs=warning%2Cpython-new).
19+
20+
All safety is configurable. To learn more about configurability, visit our documentation on [configuring content filtering](/azure/ai-services/openai/how-to/content-filters).
21+
22+
## Text models: GPT-4, GPT-3.5
23+
24+
Text models in the Azure OpenAI Service can take in and generate both text and code. These models leverage Azure’s text content filtering models to detect and prevent harmful content. This system works on both prompt and completion.
25+
26+
| Risk Category | Prompt/Completion | Severity Threshold |
27+
|-------------------------------------------|------------------------|---------------------|
28+
| Hate and Fairness | Prompts and Completions| Medium |
29+
| Violence | Prompts and Completions| Medium |
30+
| Sexual | Prompts and Completions| Medium |
31+
| Self-Harm | Prompts and Completions| Medium |
32+
| User prompt injection attack (Jailbreak) | Prompts | N/A |
33+
| Protected Material – Text | Completions | N/A |
34+
| Protected Material – Code | Completions | N/A |
35+
36+
37+
38+
## Vision models: GPT-4o, GPT-4 Turbo, DALL-E 3, DALL-E 2
39+
40+
### GPT-4o and GPT-4 Turbo
41+
42+
| Risk Category | Prompt/Completion | Severity Threshold |
43+
|------------------------------------------------------|------------------------|---------------------|
44+
| Hate and Fairness | Prompts and Completions| Medium |
45+
| Violence | Prompts and Completions| Medium |
46+
| Sexual | Prompts and Completions| Medium |
47+
| Self-Harm | Prompts and Completions| Medium |
48+
| Identification of Individuals and Inference of Sensitive Attributes | Prompts | N/A |
49+
| User prompt injection attack (Jailbreak) | Prompts | N/A |
50+
51+
### DALL-E 3 and DALL-E 2
52+
53+
54+
| Risk Category | Prompt/Completion | Severity Threshold |
55+
|---------------------------------------------------|------------------------|---------------------|
56+
| Hate and Fairness | Prompts and Completions| Low |
57+
| Violence | Prompts and Completions| Low |
58+
| Sexual | Prompts and Completions| Low |
59+
| Self-Harm | Prompts and Completions| Low |
60+
| Content Credentials | Completions | N/A |
61+
| Deceptive Generation of Political Candidates | Prompts | N/A |
62+
| Depictions of Public Figures | Prompts | N/A |
63+
| User prompt injection attack (Jailbreak) | Prompts | N/A |
64+
| Protected Material – Art and Studio Characters | Prompts | N/A |
65+
| Profanity | Prompts | N/A |
66+
67+
68+
In addition to the above safety configurations, Azure OpenAI DALL-E also comes with [prompt transformation](./prompt-transformation.md) by default. This transformation occurs on all prompts to enhance the safety of your original prompt, specifically in the risk categories of diversity, deceptive generation of political candidates, depictions of public figures, protected material, and others.

‎articles/ai-services/openai/concepts/prompt-transformation.md

Lines changed: 81 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,81 @@
1+
---
2+
title: Azure OpenAI prompt transformation concepts
3+
titleSuffix: Azure OpenAI
4+
description: Learn about the prompt transformation feature in Azure OpenAI DALL-E 3, how it works, and why it's necessary.
5+
author: PatrickFarley
6+
ms.author: pafarley
7+
ms.service: azure-ai-openai
8+
ms.topic: conceptual
9+
ms.date: 07/16/2024
10+
manager: nitinme
11+
---
12+
13+
# What is prompt transformation?
14+
15+
Prompt transformation is a process in DALL-E 3 image generation that applies a safety and quality system message to your original prompt using a large language model (LLM) call before being sent to the model for image generation. This system message enriches your original prompt with the goal of generating more diverse and higher-quality images, while maintaining intent.
16+
17+
Prompt transformation is applied to all Azure OpenAI DALL-E 3 requests by default. There may be scenarios in which your use case requires a lower level of enrichment. To generate images that use prompts that more closely resemble your original prompt, append this text to your prompt: `I NEED to test how the tool works with extremely simple prompts. DO NOT add any detail, just use it AS-IS:`. This ensures there is minimal prompt transformation. Evaluating your system behavior with and without this prompt helps you better understand the impact and value of prompt transformation.
18+
19+
After prompt transformation is applied to the original prompt, content filtering is applied as a secondary step before image generation; for more information, see [Content filtering](./content-filter.md).
20+
21+
> [!TIP]
22+
> Learn more about image generation prompting in OpenAI's [DALL·E documentation](https://platform.openai.com/docs/guides/images/language-specific-tips).
23+
24+
## Prompt transformation example
25+
26+
27+
| **Example text prompt** | **Example generated image without prompt transformation** | **Example generated image with prompt transformation** |
28+
|---|---|---|
29+
|"Watercolor painting of the Seattle skyline" | ![Watercolor painting of the Seattle skyline (simple).](../media/how-to/generated-seattle.png) | ![Watercolor painting of the Seattle skyline, with more detail and structure.](../media/how-to/generated-seattle-prompt-transformed.png) |
30+
31+
32+
## Why is prompt transformation needed?
33+
34+
Prompt transformation is essential for responsible and high-quality generations. Not only does prompt transformation improve the safety of your generated image, but it also enriches your prompt in a more descriptive manner, leading to higher quality and descriptive imagery.
35+
36+
Default prompt transformation in Azure OpenAI DALL-E 3 contains safety enhancements that steer the model away from generating images of Copyright Studio characters and artwork, public figures, and other harmful content such as sexual, hate and unfairness, violence, and self-harm content.
37+
38+
## How do I use prompt transformation?
39+
40+
Prompt transformation is applied by default to all Azure OpenAI DALL-E 3 requests. No extra setup is required to benefit from prompt transformation enhancements.
41+
42+
Like image generation, prompt transformation is non-deterministic due to the nature of large language models. A single original prompt may lead to many image variants.
43+
44+
45+
## View prompt transformations
46+
47+
Your revised or transformed prompt is visible in the API response object as shown here, in the `revised_prompt` field.
48+
49+
50+
```json
51+
Input Content:
52+
{
53+
"prompt": "Watercolor painting of the Seattle skyline",
54+
"n": 1,
55+
"size": "1024x1024"
56+
}
57+
58+
Output Content:
59+
{
60+
"created": 1720557218,
61+
"data": [
62+
{
63+
"content_filter_results": {
64+
...
65+
},
66+
"prompt_filter_results": {
67+
...
68+
},
69+
"revised_prompt": "A soft and vivid watercolor painting capturing the scenic beauty of the Seattle skyline. The painting illustrates a setting sun casting warm hues over the sprawling cityscape, with the Space Needle prominently standing tall against the sky. Imagine the scattered high-rise buildings, a soothing blend of the lush green of the parks with the winding blue water of the Puget Sound, and the snow-covered peak of Mount Rainier in the distance. A play of light and shadow adds depth and dynamism to this multihued urban panorama."
70+
}
71+
}
72+
```
73+
74+
> [!NOTE]
75+
> Azure OpenAI Service does not offer configurability for prompt transformation at this time. To bypass prompt transformation, prepend the following to any request: `I NEED to test how the tool works with extremely simple prompts. DO NOT add any detail, just use it AS-IS:`.
76+
>
77+
> While this addition will encourage the revised prompt to be more representative of your original prompt, the system may alter specific details.
78+
79+
## Next steps
80+
81+
* [DALL-E quickstart](/azure/ai-services/openai/dall-e-quickstart)

‎articles/ai-services/openai/how-to/dall-e.md

Lines changed: 2 additions & 22 deletions
Original file line numberDiff line numberDiff line change
@@ -255,30 +255,10 @@ It's also possible that the generated image itself is filtered. In this case, th
255255

256256
Your image prompts should describe the content you want to see in the image, as well as the visual style of image.
257257

258-
> [!TIP]
259-
> For a thorough look at how you can tweak your text prompts to generate different kinds of images, see the [Dallery DALL-E 2 prompt book](https://dallery.gallery/wp-content/uploads/2022/07/The-DALL%C2%B7E-2-prompt-book-v1.02.pdf).
260-
261-
#### [DALL-E 3](#tab/dalle3)
262-
263258
When writing prompts, consider that the image generation APIs come with a content moderation filter. If the service recognizes your prompt as harmful content, it doesn't generate an image. For more information, see [Content filtering](../concepts/content-filter.md).
264259

265-
### Prompt transformation
266-
267-
DALL-E 3 includes built-in prompt rewriting to enhance images, reduce bias, and increase natural variation of images.
268-
269-
| **Example text prompt** | **Example generated image without prompt transformation** | **Example generated image with prompt transformation** |
270-
|---|---|---|
271-
|"Watercolor painting of the Seattle skyline" | ![Watercolor painting of the Seattle skyline (simple).](../media/how-to/generated-seattle.png) | ![Watercolor painting of the Seattle skyline, with more detail and structure.](../media/how-to/generated-seattle-prompt-transformed.png) |
272-
273-
The updated prompt is visible in the `revised_prompt` field of the data response object.
274-
275-
While it is not currently possible to disable this feature, you can use special prompting to get outputs closer to your original prompt by adding the following to it: `I NEED to test how the tool works with extremely simple prompts. DO NOT add any detail, just use it AS-IS:`.
276-
277-
#### [DALL-E 2 (preview)](#tab/dalle2)
278-
279-
When writing prompts, consider that the image generation APIs come with a content moderation filter. If the service recognizes your prompt as harmful content, it doesn't generate an image. For more information, see [Content filtering](../concepts/content-filter.md).
280-
281-
---
260+
> [!TIP]
261+
> For a thorough look at how you can tweak your text prompts to generate different kinds of images, see the [Image prompt engineering guide](/azure/ai-services/openai/concepts/gpt-4-v-prompt-engineering).
282262
283263

284264
## Specify API options

‎articles/ai-services/openai/how-to/deployment-types.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -33,7 +33,7 @@ Azure OpenAI offers three types of deployments. These provide a varied level of
3333
| **Best suited for** | Applications that don’t require data residency. Recommended starting place for customers. | For customers with data residency requirements. Optimized for low to medium volume. | Real-time scoring for large consistent volume. Includes the highest commitments and limits.|
3434
| **How it works** | Traffic may be routed anywhere in the world | | |
3535
| **Getting started** | [Model deployment](./create-resource.md) | [Model deployment](./create-resource.md) | [Provisioned onboarding](./provisioned-throughput-onboarding.md) |
36-
| **Cost** | [Baseline](https://azure.microsoft.com/pricing/details/cognitive-services/openai-service/) | [Regional Pricing](https://azure.microsoft.com/pricing/details/cognitive-services/openai-service/) | May experience cost savings for consistent usage |
36+
| **Cost** | [Global deployment pricing](https://azure.microsoft.com/pricing/details/cognitive-services/openai-service/) | [Regional pricing](https://azure.microsoft.com/pricing/details/cognitive-services/openai-service/) | May experience cost savings for consistent usage |
3737
| **What you get** | Easy access to all new models with highest default pay-per-call limits.<br><br> Customers with high volume usage may see higher latency variability | Easy access with [SLA on availability](https://azure.microsoft.com/support/legal/sla/). Optimized for low to medium volume workloads with high burstiness. <br><br>Customers with high consistent volume may experience greater latency variability. | Regional access with very high & predictable throughput. Determine throughput per PTU using the provided [capacity calculator](./provisioned-throughput-onboarding.md#estimate-provisioned-throughput-and-cost) |
3838
| **What you don’t get** | ❌Data residency guarantees | ❌High volume w/consistent low latency | ❌Pay-per-call flexibility |
3939
| **Per-call Latency** | Optimized for real-time calling & low to medium volume usage. Customers with high volume usage may see higher latency variability. Threshold set per model | Optimized for real-time calling & low to medium volume usage. Customers with high volume usage may see higher latency variability. Threshold set per model | Optimized for real-time. |

0 commit comments

Comments
 (0)