You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: articles/ai-foundry/concepts/content-filtering.md
+1Lines changed: 1 addition & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -67,6 +67,7 @@ You can also enable the following special output filters:
67
67
-**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.
68
68
-**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.
69
69
-**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.
70
+
-**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.
Copy file name to clipboardExpand all lines: articles/ai-foundry/foundry-models/concepts/content-filter.md
+1Lines changed: 1 addition & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -47,6 +47,7 @@ The content filtering system integrated in the Foundry Models service in Azure A
47
47
| 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> |
48
48
| 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.
49
49
| 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.
50
+
| 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. |
50
51
|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. |
51
52
|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). |
|[mistral-document-ai-2505](https://ai.azure.com/explore/models/mistral-document-ai-2505/version/1/registry/azureml-mistral/?cid=learnDocs)| Image-to-Text | - **Input:** image or PDF pages (30 pages, max 30MB PDF file) <br /> - **Output:** text <br /> - **Languages:** en <br /> - **Tool calling:** no <br /> - **Response formats:** Text, JSON, Markdown |- Global standard (all regions) | Foundry |
72
+
|[mistral-document-ai-2505](https://ai.azure.com/explore/models/mistral-document-ai-2505/version/1/registry/azureml-mistral/?cid=learnDocs)| Image-to-Text | - **Input:** image or PDF pages (30 pages, max 30MB PDF file) <br /> - **Output:** text <br /> - **Languages:** en <br /> - **Tool calling:** no <br /> - **Response formats:** Text, JSON, Markdown |- Global standard (all regions) <br /> - Data zone standard (US and EU) | Foundry |
73
73
74
74
See [the Mistral model collection in Azure AI Foundry portal](https://ai.azure.com/explore/models?&selectedCollection=Mistral+AI/?cid=learnDocs). You can also find several Mistral models available [from partners and community](../concepts/models-from-partners.md#mistral-ai).
75
75
@@ -95,8 +95,8 @@ benchmarks. [Registration is required for access to the grok-4 model](https://ak
95
95
| Model | Type | Capabilities | Deployment type (region availability) | Project type |
![learn-build-service-prod[bot]](https://avatars.githubusercontent.com/in/237442?v=4&size=40){kind=avatar}
0 commit comments