ai-services url

eric-urban · eric-urban · commit 553f3b4834c1 · 2023-07-23T07:50:18.000-07:00
diff --git a/articles/advisor/advisor-reference-performance-recommendations.md b/articles/advisor/advisor-reference-performance-recommendations.md
@@ -115,13 +115,13 @@ Learn more about [Front Door Profile - UpgradeCDNToLatestSDKLanguage (Upgrade SD
 
 We observed that there have been 1,000 or more 429 throttling errors on this resource in a one day timeframe.  Consider enabling autoscale to better handle higher call volumes and reduce the number of 429 errors.
 
-Learn more about [Cognitive Service - AzureAdvisor429LimitHit (429 Throttling Detected on this resource)](/azure/cognitive-services/autoscale?tabs=portal).
+Learn more about [Cognitive Service - AzureAdvisor429LimitHit (429 Throttling Detected on this resource)](/azure/ai-services/autoscale?tabs=portal).
 
 ### Upgrade to the latest Cognitive Service Text Analytics API version
 
 Upgrade to the latest API version to get the best results in terms of model quality, performance and service availability. Also there are new features available as new endpoints starting from V3.0 such as personally identifiable information recognition, entity recognition and entity linking available as separate endpoints. In terms of changes in preview endpoints we have opinion mining in SA endpoint, redacted text property in personally identifiable information endpoint
 
-Learn more about [Cognitive Service - UpgradeToLatestAPI (Upgrade to the latest Cognitive Service Text Analytics API version)](/azure/cognitive-services/text-analytics/how-tos/text-analytics-how-to-call-api).
+Learn more about [Cognitive Service - UpgradeToLatestAPI (Upgrade to the latest Cognitive Service Text Analytics API version)](/azure/ai-services/text-analytics/how-tos/text-analytics-how-to-call-api).
 
 ### Upgrade to the latest API version of Azure Cognitive Service for Language
 
@@ -133,7 +133,7 @@ Learn more about [Cognitive Service - UpgradeToLatestAPILanguage (Upgrade to the
 
 Upgrade to the latest SDK version to get the best results in terms of model quality, performance and service availability. Also there are new features available as new endpoints starting from V3.0 such as personally identifiable information recognition, Entity recognition and entity linking available as separate endpoints. In terms of changes in preview endpoints we have Opinion Mining in SA endpoint, redacted text property in personally identifiable information endpoint
 
-Learn more about [Cognitive Service - UpgradeToLatestSDK (Upgrade to the latest Cognitive Service Text Analytics SDK version)](/azure/cognitive-services/text-analytics/quickstarts/text-analytics-sdk?tabs=version-3-1&pivots=programming-language-csharp).
+Learn more about [Cognitive Service - UpgradeToLatestSDK (Upgrade to the latest Cognitive Service Text Analytics SDK version)](/azure/ai-services/text-analytics/quickstarts/text-analytics-sdk?tabs=version-3-1&pivots=programming-language-csharp).
 
 ### Upgrade to the latest Cognitive Service Language SDK version
 
diff --git a/articles/azure-health-insights/trial-matcher/transparency-note.md b/articles/azure-health-insights/trial-matcher/transparency-note.md
@@ -42,7 +42,7 @@ Organizations can use the Trial Matcher model to match patients to potentially s
 Trial Matcher analyzes and matches clinical trial eligibility criteria and patients’ clinical information.
 Clinical trial eligibility criteria are extracted from clinical trials available on clinicaltrials.gov or provided by the service user as a custom trial. Patient clinical information is provided either as unstructured clinical note, FHIR  bundles or key-value schema.
 
-Trial Matcher uses [Text Analytics for health](https://docs.microsoft.com/azure/cognitive-services/language-service/text-analytics-for-health/overview?tabs=ner) to identify and extract medical entities in case the information provided is unstructured, either from clinical trial protocols from clinicaltrials.gov, custom trials and patient clinical notes.
+Trial Matcher uses [Text Analytics for health](https://docs.microsoft.com/azure/ai-services/language-service/text-analytics-for-health/overview?tabs=ner) to identify and extract medical entities in case the information provided is unstructured, either from clinical trial protocols from clinicaltrials.gov, custom trials and patient clinical notes.
 
 When Trial Matcher is in patient centric mode, it returns a list of potentially suitable clinical trials, based on the patient clinical information. When Trial Matcher is in trial centric mode, it     returns a list of patients who are potentially eligible for a clinical trial.   The Trial Matcher results should be reviewed by a human decision maker for a further full qualification.
 Trial Matcher results also include an explainability layer. When a patient appears to be ineligible for a trial, Trial Matcher provides evidence of why the patient is not eligible to meet the criteria of the specific trial.
diff --git a/articles/cognitive-services/Bing-News-Search/endpoint-news.md b/articles/cognitive-services/Bing-News-Search/endpoint-news.md
@@ -52,4 +52,4 @@ Returns news topics that are currently trending on social networks. When the `/t
 For details about headers, parameters, market codes, response objects, errors, etc., see the [Bing News search API v7](/rest/api/cognitiveservices-bingsearch/bing-news-api-v7-reference) reference.
 
 For complete information about the parameters supported by each endpoint, see the reference pages for each type.
-For examples of basic requests using the News search API, see [Bing News Search Quick-starts](/azure/cognitive-services/bing-news-search).
+For examples of basic requests using the News search API, see [Bing News Search Quick-starts](/azure/ai-services/bing-news-search).
diff --git a/articles/machine-learning/.openpublishing.redirection.machine-learning.json b/articles/machine-learning/.openpublishing.redirection.machine-learning.json
@@ -2697,7 +2697,7 @@
     },
     {
         "source_path_from_root": "/articles/machine-learning/machine-learning-apps-text-analytics.md",
-        "redirect_url": "/azure/cognitive-services/cognitive-services-text-analytics-quick-start",
+        "redirect_url": "/azure/ai-services/cognitive-services-text-analytics-quick-start",
         "redirect_document_id": false
     },
     {
diff --git a/articles/machine-learning/how-to-use-openai-models-in-azure-ml.md b/articles/machine-learning/how-to-use-openai-models-in-azure-ml.md
@@ -133,7 +133,7 @@ You might receive any of the following errors when you try to deploy an Azure Op
     - **Fix**: Unable to create the resource. Due to one of, the following reasons. You aren't in correct region, or you have exceeded the maximum limit of three Azure Open AI resources. You need to delete an existing Azure OpenAI resource or you need to make sure you created a workspace in one of the [supported regions](../ai-services/openai/concepts/models.md#model-summary-table-and-region-availability).
 
 - **Model Not Deployable**
-    - **Fix**: This usually happens while trying to deploy a GPT-4 model. Due to high demand you need to [apply for access to use GPT-4 models](https://learn.microsoft.com/azure/cognitive-services/openai/concepts/models#gpt-4-models).
+    - **Fix**: This usually happens while trying to deploy a GPT-4 model. Due to high demand you need to [apply for access to use GPT-4 models](https://learn.microsoft.com/azure/ai-services/openai/concepts/models#gpt-4-models).
 
 - **Resource Create Failed**
     - **Fix**: We tried to automatically create the Azure OpenAI resource but the operation failed. Try again on a new workspace.
diff --git a/articles/machine-learning/prompt-flow/get-started-prompt-flow.md b/articles/machine-learning/prompt-flow/get-started-prompt-flow.md
@@ -243,7 +243,7 @@ Copy following sample input data, paste to the input box, and select **Test**, t
 
 ```json
 {
-  "url": "https://learn.microsoft.com/en-us/azure/cognitive-services/openai/"
+  "url": "https://learn.microsoft.com/en-us/azure/ai-services/openai/"
 }
 ```
 
diff --git a/articles/role-based-access-control/includes/resource-provider-operations/ai-machine-learning.md b/articles/role-based-access-control/includes/resource-provider-operations/ai-machine-learning.md
@@ -703,7 +703,7 @@ Azure service: [Cognitive Services](../../../ai-services/index.yml)
 > | Microsoft.CognitiveServices/accounts/Language/analyze-conversations/projects/models/load-snapshot/jobs/read | Gets the status for loading a snapshot. |
 > | Microsoft.CognitiveServices/accounts/Language/analyze-conversations/projects/models/verification/read | Get trained model verification report. |
 > | Microsoft.CognitiveServices/accounts/Language/analyze-conversations/projects/prebuilts/read | Get list of Supported prebuilts for conversational projects. |
-> | Microsoft.CognitiveServices/accounts/Language/analyze-conversations/projects/resources/assign/action | Assign new Azure resources to a project to allow deploying new deployments to them.<br>This API is available only via AAD authentication and not supported via subscription key authentication.<br>For more details about AAD authentication, check here: [Authenticate with Azure Active Directory](/azure/cognitive-services/authentication?tabs=powershell#authenticate-with-azure-active-directory) |
+> | Microsoft.CognitiveServices/accounts/Language/analyze-conversations/projects/resources/assign/action | Assign new Azure resources to a project to allow deploying new deployments to them.<br>This API is available only via AAD authentication and not supported via subscription key authentication.<br>For more details about AAD authentication, check here: [Authenticate with Azure Active Directory](/azure/ai-services/authentication?tabs=powershell#authenticate-with-azure-active-directory) |
 > | Microsoft.CognitiveServices/accounts/Language/analyze-conversations/projects/resources/read | Lists the deployments resources assigned to the project. |
 > | Microsoft.CognitiveServices/accounts/Language/analyze-conversations/projects/resources/unassign/action | Unassign resources from a project. This disallows deploying new deployments to these resources, and deletes existing deployments assigned to them. |
 > | Microsoft.CognitiveServices/accounts/Language/analyze-conversations/projects/resources/assign/jobs/read | Gets the status of an existing assign deployment resources job. |
@@ -765,7 +765,7 @@ Azure service: [Cognitive Services](../../../ai-services/index.yml)
 > | Microsoft.CognitiveServices/accounts/Language/analyze-text/projects/models/evaluation/summary-result/read | Get trained model evaluation summary. |
 > | Microsoft.CognitiveServices/accounts/Language/analyze-text/projects/models/load-snapshot/jobs/read | Gets the status for loading a snapshot. |
 > | Microsoft.CognitiveServices/accounts/Language/analyze-text/projects/models/verification/read | Get trained model verification report. |
-> | Microsoft.CognitiveServices/accounts/Language/analyze-text/projects/resources/assign/action | Assign new Azure resources to a project to allow deploying new deployments to them.<br>This API is available only via AAD authentication and not supported via subscription key authentication.<br>For more details about AAD authentication, check here: [Authenticate with Azure Active Directory](/azure/cognitive-services/authentication?tabs=powershell#authenticate-with-azure-active-directory) |
+> | Microsoft.CognitiveServices/accounts/Language/analyze-text/projects/resources/assign/action | Assign new Azure resources to a project to allow deploying new deployments to them.<br>This API is available only via AAD authentication and not supported via subscription key authentication.<br>For more details about AAD authentication, check here: [Authenticate with Azure Active Directory](/azure/ai-services/authentication?tabs=powershell#authenticate-with-azure-active-directory) |
 > | Microsoft.CognitiveServices/accounts/Language/analyze-text/projects/resources/read | Lists the deployments resources assigned to the project. |
 > | Microsoft.CognitiveServices/accounts/Language/analyze-text/projects/resources/unassign/action | Unassign resources from a project. This disallows deploying new deployments to these resources, and deletes existing deployments assigned to them. |
 > | Microsoft.CognitiveServices/accounts/Language/analyze-text/projects/resources/assign/jobs/read | Gets the status of an existing assign deployment resources job. |
diff --git a/articles/sap/workloads/integration-get-started.md b/articles/sap/workloads/integration-get-started.md
@@ -48,7 +48,7 @@ Select an area for resources about how to integrate SAP and Azure in that space.
 
 ### Azure OpenAI service
 
-For more information about integration with [Azure OpenAI service](/azure/cognitive-services/openai/overview), see the following Azure documentation:
+For more information about integration with [Azure OpenAI service](/azure/ai-services/openai/overview), see the following Azure documentation:
 
 - [Microsoft AI SDK for SAP](https://microsoft.github.io/aisdkforsapabap/docs/intro)
 - [ABAP SDK for Azure](https://github.com/microsoft/ABAP-SDK-for-Azure)
diff --git a/articles/search/vector-search-how-to-chunk-documents.md b/articles/search/vector-search-how-to-chunk-documents.md
@@ -19,7 +19,7 @@ This article describes several approaches for chunking large documents so that y
 
 ## Why is chunking important?
 
-The models used to generate embedding vectors have maximum limits on the text fragments provided as input. For example, the maximum length of input text for the [Azure OpenAI](/azure/cognitive-services/openai/how-to/embeddings) embedding models is 8,191 tokens. Given that each token is around 4 characters of text for common OpenAI models, this maximum limit is equivalent to around 6000 words of text. If you're using these models to generate embeddings, it's critical that the input text stays under the limit. Partitioning your content into chunks ensures that your data can be processed by the Large Language Models (LLM) used for indexing and queries. 
+The models used to generate embedding vectors have maximum limits on the text fragments provided as input. For example, the maximum length of input text for the [Azure OpenAI](/azure/ai-services/openai/how-to/embeddings) embedding models is 8,191 tokens. Given that each token is around 4 characters of text for common OpenAI models, this maximum limit is equivalent to around 6000 words of text. If you're using these models to generate embeddings, it's critical that the input text stays under the limit. Partitioning your content into chunks ensures that your data can be processed by the Large Language Models (LLM) used for indexing and queries. 
 
 ## How chunking fits into the workflow
 
@@ -117,14 +117,14 @@ mountains. /n You can both ski in winter and swim in summer.
 
 ## Try it out: Chunking and vector embedding generation sample
 
-A [fixed-sized chunking and embedding generation sample](https://github.com/Azure-Samples/azure-search-power-skills/blob/main/Vector/EmbeddingGenerator/README.md) demonstrates both chunking and vector embedding generation using [Azure OpenAI](/azure/cognitive-services/openai/) embedding models. This sample uses a [Cognitive Search custom skill](cognitive-search-custom-skill-web-api.md) in the [Power Skills repo](https://github.com/Azure-Samples/azure-search-power-skills/tree/main#readme) to wrap the chunking step.
+A [fixed-sized chunking and embedding generation sample](https://github.com/Azure-Samples/azure-search-power-skills/blob/main/Vector/EmbeddingGenerator/README.md) demonstrates both chunking and vector embedding generation using [Azure OpenAI](/azure/ai-services/openai/) embedding models. This sample uses a [Cognitive Search custom skill](cognitive-search-custom-skill-web-api.md) in the [Power Skills repo](https://github.com/Azure-Samples/azure-search-power-skills/tree/main#readme) to wrap the chunking step.
 
 This sample is built on LangChain, Azure OpenAI, and Azure Cognitive Search.
 
 ## See also
 
-+ [Understanding embeddings in Azure OpenAI Service](/azure/cognitive-services/openai/concepts/understand-embeddings)
-+ [Learn how to generate embeddings](/azure/cognitive-services/openai/how-to/embeddings?tabs=console)
-+ [Tutorial: Explore Azure OpenAI Service embeddings and document search](/azure/cognitive-services/openai/tutorials/embeddings?tabs=command-line)
++ [Understanding embeddings in Azure OpenAI Service](/azure/ai-services/openai/concepts/understand-embeddings)
++ [Learn how to generate embeddings](/azure/ai-services/openai/how-to/embeddings?tabs=console)
++ [Tutorial: Explore Azure OpenAI Service embeddings and document search](/azure/ai-services/openai/tutorials/embeddings?tabs=command-line)
 
 
diff --git a/articles/search/vector-search-how-to-generate-embeddings.md b/articles/search/vector-search-how-to-generate-embeddings.md
diff --git a/articles/search/vector-search-overview.md b/articles/search/vector-search-overview.md
diff --git a/articles/search/vector-search-ranking.md b/articles/search/vector-search-ranking.md

Original file line number	Diff line number	Diff line change
`@@ -2697,7 +2697,7 @@`
`2697`	`2697`	`},`
`2698`	`2698`	`{`
`2699`	`2699`	`"source_path_from_root": "/articles/machine-learning/machine-learning-apps-text-analytics.md",`
`2700`		`- "redirect_url": "/azure/cognitive-services/cognitive-services-text-analytics-quick-start",`
	`2700`	`+ "redirect_url": "/azure/ai-services/cognitive-services-text-analytics-quick-start",`
`2701`	`2701`	`"redirect_document_id": false`
`2702`	`2702`	`},`
`2703`	`2703`	`{`
Original file line number	Diff line number	Diff line change
`@@ -243,7 +243,7 @@ Copy following sample input data, paste to the input box, and select Test, t`
`243`	`243`
`244`	`244`	```json
`245`	`245`	`{`
`246`		`- "url": "https://learn.microsoft.com/en-us/azure/cognitive-services/openai/"`
	`246`	`+ "url": "https://learn.microsoft.com/en-us/azure/ai-services/openai/"`
`247`	`247`	`}`
`248`	`248`	```
`249`	`249`