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-services/openai/concepts/abuse-monitoring.md
+2-2Lines changed: 2 additions & 2 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -32,10 +32,10 @@ There are several components to abuse monitoring:
32
32
Some customers may want to use the Azure OpenAI Service for a use case that involves the processing of highly sensitive or highly confidential data, or otherwise may conclude that they do not want or do not have the right to permit Microsoft to store and conduct human review on their prompts and completions for abuse detection. To address these concerns, Microsoft allows customers who meet additional Limited Access eligibility criteria to apply to modify abuse monitoring by completing [this ](https://customervoice.microsoft.com/Pages/ResponsePage.aspx?id=v4j5cvGGr0GRqy180BHbR7en2Ais5pxKtso_Pz4b1_xUOE9MUTFMUlpBNk5IQlZWWkcyUEpWWEhGOCQlQCN0PWcu)form. Learn more about applying for modified abuse monitoring at [Limited access to Azure OpenAI Service](/legal/cognitive-services/openai/limited-access?context=%2Fazure%2Fai-services%2Fopenai%2Fcontext%2Fcontext), and about the impact of modified abuse monitoring on data processing at [Data, privacy, and security for Azure OpenAI Service](/legal/cognitive-services/openai/data-privacy?context=%2Fazure%2Fai-services%2Fopenai%2Fcontext%2Fcontext&tabs=azure-portal).
33
33
34
34
> [!NOTE]
35
-
> When abuse monitoring is modified and human review is not performed, detection of potential abuse may be less accurate. Customers will be notified of potential abuse detection as described above, and should be prepared to respond to such notification to avoid service interruption if possible.
35
+
> When abuse monitoring is modified and human review is not performed, detection of potential abuse may be less accurate. Customers are notified of potential abuse detection as described above, and should be prepared to respond to such notification to avoid service interruption if possible.
36
36
37
37
## Next steps
38
38
39
39
- Learn more about the [underlying models that power Azure OpenAI](../concepts/models.md).
40
40
- Learn more about understanding and mitigating risks associated with your application: [Overview of Responsible AI practices for Azure OpenAI models](/legal/cognitive-services/openai/overview?context=/azure/ai-services/openai/context/context).
41
-
- Learn more about how data is processed in connection with content filtering and abuse monitoring: [Data, privacy, and security for Azure OpenAI Service](/legal/cognitive-services/openai/data-privacy?context=/azure/ai-services/openai/context/context#preventing-abuse-and-harmful-content-generation).
41
+
- Learn more about how data is processed in content filtering and abuse monitoring: [Data, privacy, and security for Azure OpenAI Service](/legal/cognitive-services/openai/data-privacy?context=/azure/ai-services/openai/context/context#preventing-abuse-and-harmful-content-generation).
Copy file name to clipboardExpand all lines: articles/ai-services/openai/concepts/content-filter.md
+3Lines changed: 3 additions & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -24,6 +24,9 @@ In addition to the content filtering system, Azure OpenAI Service performs monit
24
24
25
25
The following sections provide information about the content filtering categories, the filtering severity levels and their configurability, and API scenarios to be considered in application design and implementation.
26
26
27
+
> [!NOTE]
28
+
> No prompts or completions are stored for the purposes of content filtering. No prompts or completions are used to train, retrain, or improve the content filtering system without your consent. For more information, see [Data, privacy, and security](/legal/cognitive-services/openai/data-privacy?context=%2Fazure%2Fai-services%2Fopenai%2Fcontext%2Fcontext&tabs=azure-portal).
29
+
27
30
## Content filter types
28
31
29
32
The content filtering system integrated in the Azure OpenAI Service contains:
Copy file name to clipboardExpand all lines: articles/ai-studio/concepts/architecture.md
+3-3Lines changed: 3 additions & 3 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -8,7 +8,7 @@ ms.custom:
8
8
- build-2024
9
9
- ignite-2024
10
10
ms.topic: conceptual
11
-
ms.date: 11/19/2024
11
+
ms.date: 02/11/2025
12
12
ms.reviewer: deeikele
13
13
ms.author: larryfr
14
14
author: Blackmist
@@ -24,9 +24,9 @@ At the top level, Azure AI Foundry provides access to the following resources:
24
24
25
25
<!-- The top level Azure AI Foundry resources (hub and project) are based on Azure Machine Learning. Connected resources, such as Azure OpenAI, Azure AI services, and Azure AI Search, are used by the hub and project in reference, but follow their own resource management lifecycle. -->
26
26
27
-
-**Azure OpenAI**: Provides access to the latest Open AI models. You can create secure deployments, try playgrounds, fine tune models, content filters, and batch jobs. The Azure OpenAI resource provider is `Microsoft.CognitiveServices/account` and the kind of resource is `OpenAI`. You can also connect to Azure OpenAI by using a kind of `AIServices`, which also includes other [Azure AI services](/azure/ai-services/what-are-ai-services).
27
+
-**Azure OpenAI**: Provides access to the latest OpenAI models. You can create secure deployments, try playgrounds, fine tune models, content filters, and batch jobs. The Azure OpenAI resource provider is `Microsoft.CognitiveServices/account` and the kind of resource is `OpenAI`. You can also connect to Azure OpenAI by using a kind of `AIServices`, which also includes other [Azure AI services](/azure/ai-services/what-are-ai-services).
28
28
29
-
When using Azure AI Foundry portal, you can directly work with Azure OpenAI without an Azure Studio project or you can use Azure OpenAI through a project.
29
+
When you use Azure AI Foundry portal, you can directly work with Azure OpenAI without an Azure Studio project. Or you can use Azure OpenAI through a project.
30
30
31
31
For more information, visit [Azure OpenAI in Azure AI Foundry portal](../azure-openai-in-ai-studio.md).
Copy file name to clipboardExpand all lines: articles/ai-studio/concepts/model-lifecycle-retirement.md
+1-1Lines changed: 1 addition & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -69,7 +69,7 @@ The following table lists the timelines for models that are on track for retirem
69
69
| ---- | ---- | ---- | --- | ---- | --- |
70
70
| AI21 Labs | Jamba Instruct | February 1, 2025 | February 1, 2025 | March 1, 2025 |[AI21-Jamba-1.5-Large](https://ai.azure.com/explore/models/AI21-Jamba-1.5-Large/version/1/registry/azureml-ai21) or [AI21-Jamba-1.5-Mini](https://ai.azure.com/explore/models/AI21-Jamba-1.5-Mini/version/1/registry/azureml-staging)|
71
71
| Mistral AI |[Mistral-large-2407](https://aka.ms/azureai/landing/Mistral-Large-2407)| January 13, 2025 | February 13, 2025 | May 13, 2025 |[Mistral-large-2411](https://aka.ms/aistudio/landing/Mistral-Large-2411)|
72
-
| Mistral AI |[Mistral-large](https://aka.ms/azureai/landing/Mistral-Large)| December 15, 2024 | January 15, 2025 | April 15, 2025 |[Mistral-large-2407](https://aka.ms/azureai/landing/Mistral-Large-2407)|
72
+
| Mistral AI |[Mistral-large](https://aka.ms/azureai/landing/Mistral-Large)| December 15, 2024 | January 15, 2025 | April 15, 2025 |[Mistral-large-2411](https://aka.ms/aistudio/landing/Mistral-Large-2411)|
@@ -64,7 +64,7 @@ The Bicep template is made up of the following files:
64
64
| [dependent-resources.bicep](https://github.com/Azure/azure-quickstart-templates/blob/master/quickstarts/microsoft.machinelearningservices/aistudio-basics/modules/dependent-resources.bicep) | Defines the dependent resources for the hub such as Azure Storage Account, Container Registry, Key Vault, and Application Insights. |
65
65
66
66
> [!IMPORTANT]
67
-
> The example templates may not always use the latest API version for the Azure resources it creates. Before using the template, we recommend modifying it to use the latest API versions. Each Azure service has its own set of API versions. For information on the API for a specific service, check the service information in the [Azure REST API reference](/rest/api/azure/).
67
+
> The example templates might not always use the latest API version for the Azure resources it creates. Before using the template, we recommend modifying it to use the latest API versions. Each Azure service has its own set of API versions. For information on the API for a specific service, check the service information in the [Azure REST API reference](/rest/api/azure/).
68
68
>
69
69
> The hub is based on Azure Machine Learning. For information on the latest API versions for Azure Machine Learning, see the [Azure Machine Learning REST API reference](/rest/api/azureml/). To update this API version, find the `Microsoft.MachineLearningServices/<resource>` entry for the resource type and update it to the latest version. The following example is an entry for a hub that uses an API version of `2023-08-01-preview`:
Copy file name to clipboardExpand all lines: articles/ai-studio/how-to/data-add.md
+16-16Lines changed: 16 additions & 16 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -9,7 +9,7 @@ ms.custom:
9
9
- build-2024
10
10
- ignite-2024
11
11
ms.topic: how-to
12
-
ms.date: 10/25/2024
12
+
ms.date: 02/11/2025
13
13
ms.author: franksolomon
14
14
author: fbsolo-ms1
15
15
---
@@ -25,7 +25,7 @@ Data can help when you need these capabilities:
25
25
> [!div class="checklist"]
26
26
> -**Versioning:** Data versioning is supported.
27
27
> -**Reproducibility:** Once you create a data version, it is *immutable*. It cannot be modified or deleted. Therefore, jobs or prompt flow pipelines that consume the data can be reproduced.
28
-
> -**Auditability:** Because the data version is immutable, you can track the asset versions, who updated a version, and when the version updates occurred.
28
+
> -**Auditability:** Because the data version is immutable, you can track the asset versions, who updated a version, and the date of each version update.
29
29
> -**Lineage:** For any given data, you can view which jobs or prompt flow pipelines consume the data.
30
30
> -**Ease-of-use:** An Azure AI Foundry data resembles web browser bookmarks (favorites). Instead of remembering long storage paths that *reference* your frequently-used data on Azure Storage, you can create a data *version* and then access that version of the asset with a friendly name.
31
31
@@ -57,9 +57,9 @@ Azure AI Foundry shows the supported source paths. You can create a data from a
57
57
58
58
A file (`uri_file`) data resource type points to a *single file* on storage (for example, a CSV file).
59
59
60
-
These steps explain how to create a File typed data in Azure AI Foundry portal:
60
+
These steps explain how to create a File typed data resource in the Azure AI Foundry portal:
61
61
62
-
1. Navigate to [Azure AI Foundry](https://ai.azure.com/).
62
+
1. Navigate to the [Azure AI Foundry](https://ai.azure.com/).
63
63
64
64
1. Select the project where you want to create the data.
65
65
@@ -119,13 +119,13 @@ A Folder (`uri_folder`) data source type points to a *folder* on a storage resou
119
119
### Delete data
120
120
121
121
> [!IMPORTANT]
122
-
> Data deletion is not supported. Data is immutable in Azure AI Foundry portal. Once you create a data version, it can't be modified or deleted. This immutability provides a level of protection when working in a team that creates production workloads.
122
+
> Data deletion isn't supported. Data is immutable in Azure AI Foundry portal. Once you create a data version, it can't be modified or deleted. This immutability provides a level of protection when working in a team that creates production workloads.
123
123
124
124
If Azure AI Foundry allowed data deletion, it would have the following adverse effects:
125
-
- Production jobs that consume data that is later deleted would fail.
126
-
- Machine learning experiment reproduction would become more difficult.
127
-
- Job lineage would break, because it would become impossible to view the deleted data version.
128
-
- You could no longer track and audit correctly, since versions could be missing.
125
+
- Production jobs that consume data that is later deleted would fail
126
+
- Machine learning experiment reproduction would become more difficult
127
+
- Job lineage would break, because it would become impossible to view the deleted data version
128
+
- You could no longer correctly track and audit, since versions could be missing
129
129
130
130
When a data resource is erroneously created - for example, with an incorrect name, type or path - Azure AI offers solutions to handle the situation without the negative consequences of deletion:
131
131
@@ -163,7 +163,7 @@ At this time, Azure AI Foundry doesn't support restoration of *all versions* of
163
163
#### Restore a specific data version
164
164
165
165
> [!IMPORTANT]
166
-
> If all data versions were archived, you cannot restore individual versions of the data - you must restore all versions.
166
+
> If all data versions were archived, you can't restore individual versions of the data - you must restore all versions.
167
167
168
168
Currently, Azure AI Foundry doesn't support restoration of a specific data version.
169
169
@@ -172,17 +172,17 @@ Currently, Azure AI Foundry doesn't support restoration of a specific data versi
172
172
Data tagging is extra metadata applied to the data in the form of a key-value pair. Data tagging offers many benefits:
173
173
174
174
- Data quality description. For example, if your organization uses a *medallion lakehouse architecture*, you can tag assets with `medallion:bronze` (raw), `medallion:silver` (validated) and `medallion:gold` (enriched).
175
-
-Provides efficient data searching and filtering, to help data discovery.
176
-
-Helps identify sensitive personal data, to properly manage and govern data access. For example, `sensitivity:PII`/`sensitivity:nonPII`.
177
-
-Identify whether data is approved, from a responsible AI (RAI) audit. For example, `RAI_audit:approved`/`RAI_audit:todo`.
175
+
-It provides efficient data searching and filtering, to help data discovery.
176
+
-It helps identify sensitive personal data, to properly manage and govern data access. For example, `sensitivity:PII`/`sensitivity:nonPII`.
177
+
-It identifies whether or not data is approved, from a responsible AI (RAI) audit. For example, `RAI_audit:approved`/`RAI_audit:todo`.
178
178
179
179
You can add tags to existing data.
180
180
181
181
### Data preview
182
182
183
-
You can browse the folder structure and preview the file in the Data details page. We support data preview for the following types:
184
-
- Data file types that are supported via preview API: ".tsv", ".csv", ".parquet", ".jsonl".
185
-
-Other file types, Azure AI Foundry portal attempts to preview the file in the browser natively. The supported file types might depend on the browser itself.
183
+
In the Data details page, you can browse the folder structure and preview the file. We support data preview for these types:
184
+
- Data file types that are supported via the preview API: ".tsv", ".csv", ".parquet", ".jsonl".
185
+
-For other file types, Azure AI Foundry portal tries to natively preview the file in the browser. The supported file types might depend on the browser itself.
186
186
Normally for images, these file image types are supported: ".png", ".jpg", ".gif". Normally, these file types are supported: ".ipynb", ".py", ".yml", ".html".
0 commit comments