Merge pull request #7483 from PatrickFarley/aoai-build

denrea · web-flow · commit d8bed87183a4 · 2025-10-07T10:54:36.000-07:00
Revert "remove pii docs"
diff --git a/articles/ai-foundry/concepts/content-filtering.md b/articles/ai-foundry/concepts/content-filtering.md
@@ -67,6 +67,7 @@ You can also enable the following special output filters:
 - **Protected material for text**: Protected material text describes known text content (for example, song lyrics, articles, recipes, and selected web content) that a large language model might output.
 - **Protected material for code**: Protected material code describes source code that matches a set of source code from public repositories, which a large language models might output without proper citation of source repositories.
 - **Groundedness**: The groundedness detection filter detects whether the text responses of large language models (LLMs) are grounded in the source materials provided by the users.
+- **Personally identifiable information (PII)**: The PII filter detects whether the text responses of large language models (LLMs) contain personally identifiable information (PII). PII refers to any information that can be used to identify a particular individual, such as a name, address, phone number, email address, social security number, driver's license number, passport number, or similar information.
 
 [!INCLUDE [create-content-filter](../includes/create-content-filter.md)]
 
diff --git a/articles/ai-foundry/foundry-models/concepts/content-filter.md b/articles/ai-foundry/foundry-models/concepts/content-filter.md
@@ -47,6 +47,7 @@ The content filtering system integrated in the Foundry Models service in Azure A
 | Self-Harm  | Self-harm describes language related to physical actions intended to purposely hurt, injure, damage one's body or kill oneself. <br><br> This category includes, but isn't limited to: <ul><li>Eating Disorders</li><li>Bullying and intimidation</li></ul>  |
 | Protected Material for Text<sup>*</sup> | Protected material text describes known text content (for example, song lyrics, articles, recipes, and selected web content) that large language models can return as output.
 | Protected Material for Code | Protected material code describes source code that matches a set of source code from public repositories, which large language models can output without proper citation of source repositories.
+| Personally identifiable information (PII) | Personally identifiable information (PII) refers to any information that can be used to identify a particular individual. PII detection involves analyzing text content in LLM completions and filtering any PII that was returned. |
 |User Prompt Attacks |User prompt attacks are user prompts designed to provoke the generative AI model into exhibiting behaviors it was trained to avoid or to break the rules set in the system message. Such attacks can vary from intricate roleplay to subtle subversion of the safety objective. |
 |Indirect Attacks |Indirect Attacks, also referred to as Indirect Prompt Attacks or Cross-Domain Prompt Injection Attacks, are a potential vulnerability where third parties place malicious instructions inside of documents that the generative AI system can access and process. Requires [OpenAI models with document embedding and formatting](../../openai/concepts/content-filter-document-embedding.md). |
 
diff --git a/articles/ai-foundry/openai/concepts/content-filter-annotations.md b/articles/ai-foundry/openai/concepts/content-filter-annotations.md
@@ -33,25 +33,27 @@ When annotations are enabled as shown in the code snippets below, the following
 |indirect attacks|detected (true or false), </br>filtered (true or false)|
 |protected material text|detected (true or false), </br>filtered (true or false)|
 |protected material code|detected (true or false), </br>filtered (true or false), </br>Example citation of public GitHub repository where code snippet was found, </br>The license of the repository|
+|Personally identifiable information (PII)|detected (true or false)</br>filtered (true or false) </br>redacted (true or false) |
 |Groundedness | detected (true or false)</br>filtered (true or false, with details) </br>(Annotate mode only) details:(`completion_end_offset`, `completion_start_offset`) |
 
 When displaying code in your application, we strongly recommend that the application also displays the example citation from the annotations. Compliance with the cited license may also be required for Customer Copyright Commitment coverage.
 
 See the following table for the annotation mode availability in each API version:
 
-|Filter category |2024-10-01-preview|2024-02-01 GA| 2024-04-01-preview | 2023-10-01-preview | 2023-06-01-preview| 
-|--|--|--|--|
-| Hate | ✅|✅ |✅ |✅ |✅ |
-| Violence | ✅|✅ |✅ |✅ |✅ |
-| Sexual |✅ |✅|✅ |✅ |✅ |
-| Self-harm |✅|✅|✅ |✅ |✅ |
-| Prompt Shield for user prompt attacks|✅|✅|✅ |✅ |✅ |
-|Prompt Shield for indirect attacks|   | | ✅ | | |
-|Protected material text|✅|✅ |✅ |✅ |✅ |
-|Protected material code|✅|✅ |✅ |✅ |✅ |
-|Profanity blocklist|✅|✅ |✅ |✅ |✅ |
-|Custom blocklist|✅| | ✅ |✅ |✅ |
-|Groundedness<sup>1</sup>|✅| |  | |  |
+|Filter category |2024-10-01-preview|2024-02-01 GA| 2024-04-01-preview | 2023-10-01-preview | 2023-06-01-preview| 2025-01-01-preview |
+|--|--|--|--|--|
+| Hate | ✅|✅ |✅ |✅ |✅ |✅ |
+| Violence | ✅|✅ |✅ |✅ |✅ |✅ |
+| Sexual |✅ |✅|✅ |✅ |✅ |✅ |
+| Self-harm |✅|✅|✅ |✅ |✅ |✅ |
+| Prompt Shield for user prompt attacks|✅|✅|✅ |✅ |✅ |✅ |
+|Prompt Shield for indirect attacks|   | | ✅ | | |✅ |
+|Protected material text|✅|✅ |✅ |✅ |✅ |✅ |
+|Protected material code|✅|✅ |✅ |✅ |✅ |✅ |
+|Personally identifiable information (PII)| |  |  |  |  |✅ |
+|Profanity blocklist|✅|✅ |✅ |✅ |✅ |✅ |
+|Custom blocklist|✅| | ✅ |✅ |✅ |✅ |
+|Groundedness<sup>1</sup>|✅| |  | |  |✅ |
 
 <sup>1</sup> Not available in non-streaming scenarios; only available for streaming scenarios. The following regions support Groundedness Detection: Central US, East US, France Central, and Canada East 
 
diff --git a/articles/ai-foundry/openai/concepts/content-filter-personal-information.md b/articles/ai-foundry/openai/concepts/content-filter-personal-information.md
@@ -0,0 +1,26 @@
+---
+title: Personally Identifiable Information (PII) Filter
+description: Learn about the Personally Identifiable Information (PII) filter for identifying and flagging known personal information in large language model outputs.
+author: PatrickFarley
+ms.author: pafarley
+ms.date: 07/03/2025
+ms.topic: conceptual
+ms.service: azure-ai-openai
+---
+
+# Personally identifiable information (PII) filter
+
+Personally identifiable information (PII) refers to any information that can be used to identify a particular individual, such as a name, address, phone number, email address, social security number, driver's license number, passport number, or similar information.
+
+PII detection is used to help prevent PII from being exposed or shared, protecting users from identity theft, financial fraud, or other types of privacy violations.
+
+In the context of large language models (LLMs), PII detection involves analyzing text content in LLM completions. When PII has been identified, it can be flagged for further review, or the output can be blocked. The PII filter scans the output of LLMs to identify and flag known personal information. It's designed to help organizations prevent the generation of content that closely matches sensitive personal information.
+
+
+## PII types
+
+There are many different types of PII, and you can specify which types you want to filter. The set of PII types that can be detected by the filter matches the set that's defined in the [Azure AI Language docs](/azure/ai-services/language-service/personally-identifiable-information/concepts/entity-categories).
+
+## Filtering modes
+
+The PII filter can be configured to operate in two modes. **Annotate** mode flags PII that's returned in the model output. **Annotate and Block** mode blocks the entire output if PII is detected. The filtering mode can be set for each PII category individually.
diff --git a/articles/ai-foundry/openai/concepts/content-filter.md b/articles/ai-foundry/openai/concepts/content-filter.md
@@ -29,7 +29,7 @@ The articles in this section provide information about the content filtering cat
 ## Content filter types
 
 The content filtering system integrated in Azure OpenAI contains: 
-* Neural multclass classification models aimed at detecting and filtering harmful content. The models cover four categories (hate, sexual, violence, and self-harm) across four severity levels (safe, low, medium, and high). Content detected at the 'safe' severity level is labeled in annotations but isn't subject to filtering and isn't configurable.
+* Neural multiclass classification models aimed at detecting and filtering harmful content. The models cover four categories (hate, sexual, violence, and self-harm) across four severity levels (safe, low, medium, and high). Content detected at the 'safe' severity level is labeled in annotations but isn't subject to filtering and isn't configurable.
 * Other optional classification models aimed at detecting jailbreak risk and known content for text and code. These models are binary classifiers that flag whether user or model behavior qualifies as a jailbreak attack or match to known text or source code. The use of these models is optional, but use of protected material code model may be required for Customer Copyright Commitment coverage.
 
 ## Filter categories
@@ -48,7 +48,7 @@ The following table summarizes the risk categories supported by Azure OpenAI's c
 | [Groundedness](/azure/ai-foundry/openai/concepts/content-filter-groundedness)<sup>2</sup> | Groundedness detection flags whether the text responses of large language models (LLMs) are grounded in the source materials provided by the users. Ungrounded material refers to instances where the LLMs produce information that is non-factual or inaccurate from what was present in the source materials. Requires [document embedding and formatting](./content-filter-document-embedding.md). |
 | [Protected Material for Text](/azure/ai-foundry/openai/concepts/content-filter-protected-material)<sup>1</sup> | Protected material text describes known text content (for example, song lyrics, articles, recipes, and selected web content) that can be outputted by large language models.|
 | [Protected Material for Code](/azure/ai-foundry/openai/concepts/content-filter-protected-material) | Protected material code describes source code that matches a set of source code from public repositories, which can be outputted by large language models without proper citation of source repositories.|
-
+| [Personally identifiable information (PII)](/azure/ai-services/openai/concepts/content-filter-personal-information) | Personally identifiable information (PII) refers to any information that can be used to identify a particular individual. PII detection involves analyzing text content in LLM completions and filtering any PII that was returned. |
 
 <sup>1</sup> If you're an owner of text material and want to submit text content for protection, [file a request](https://aka.ms/protectedmaterialsform).
 
diff --git a/articles/ai-foundry/openai/how-to/content-filters.md b/articles/ai-foundry/openai/how-to/content-filters.md
@@ -49,6 +49,7 @@ You can configure the following filter categories in addition to the default har
 | Protected material - code |GA| On | Completion | Filters protected code or gets the example citation and license information in annotations for code snippets that match any public code sources, powered by GitHub Copilot. For more information about consuming annotations, see the [Protected material concepts guide](/azure/ai-foundry/openai/concepts/content-filter-protected-material) |
 | Protected material - text | GA| On | Completion | Identifies and blocks known text content from being displayed in the model output (for example, song lyrics, recipes, and selected web content).  |
 | Groundedness | Preview |Off | Completion |Detects whether the text responses of large language models (LLMs) are grounded in the source materials provided by the users. Ungroundedness refers to instances where the LLMs produce information that is non-factual or inaccurate from what was present in the source materials. Requires: [Document embedding and formatting](/azure/ai-foundry/openai/concepts/content-filter?tabs=warning%2Cuser-prompt%2Cpython-new#embedding-documents-in-your-prompt).|
+| Personally identifiable information (PII) | Preview | Off | Completion | Filters information that can be used to identify a particular individual, such as a name, address, phone number, email address, social security number, driver's license number, passport number, or similar information. |
 
 
 [!INCLUDE [create-content-filter](../../../ai-foundry/includes/create-content-filter.md)]
diff --git a/articles/ai-foundry/openai/whats-new.md b/articles/ai-foundry/openai/whats-new.md
@@ -19,6 +19,12 @@ ms.custom:
 
 This article provides a summary of the latest releases and major documentation updates for Azure OpenAI.
 
+## October 2025
+
+### PII detection content filter
+
+Personally identifiable information (PII) detection is now available as a built-in content filter. This feature allows you to identify and block sensitive information in LLM outputs, enhancing data privacy. For more information, see the [PII detection](./concepts/content-filter-personal-information.md) documentation.
+
 ## September 2025
 
 ## GPT-5-codex is now available
diff --git a/articles/ai-foundry/toc-files/models/toc.yml b/articles/ai-foundry/toc-files/models/toc.yml
@@ -241,6 +241,8 @@ items:
           href: ../../openai/concepts/content-filter-groundedness.md
         - name: Protected material detection
           href: ../../openai/concepts/content-filter-protected-material.md
+        - name: Personally identifiable information (PII) detection
+          href: ../../openai/concepts/content-filter-personal-information.md
         - name: Content filter configurability
           href: ../../openai/concepts/content-filter-configurability.md
         - name: Content filter annotations
