Merge branch 'main' of https://github.com/MicrosoftDocs/azure-docs-pr into vnet-peer-spn

Author: asudbring

articles/ai-services/openai/concepts/model-retirements.md

@@ -4,7 +4,7 @@ titleSuffix: Azure OpenAI
 description: Learn about the model deprecations and retirements in Azure OpenAI.
 ms.service: azure-ai-openai
 ms.topic: conceptual
-ms.date: 03/12/2024
+ms.date: 04/24/2024
 ms.custom: 
 manager: nitinme
 author: mrbullwinkle
@@ -60,8 +60,8 @@ These models are currently available for use in Azure OpenAI Service.
 
 | Model | Version | Retirement date |
 | ---- | ---- | ---- |
-| `gpt-35-turbo` | 0301 | No earlier than June 13, 2024 |
-| `gpt-35-turbo`<br>`gpt-35-turbo-16k` | 0613 | No earlier than July 13, 2024 |
+| `gpt-35-turbo` | 0301 | No earlier than August 1, 2024 |
+| `gpt-35-turbo`<br>`gpt-35-turbo-16k` | 0613 | No earlier than August 1, 2024 |
 | `gpt-35-turbo` | 1106 | No earlier than Nov 17, 2024 |
 | `gpt-35-turbo` | 0125 | No earlier than Feb 22, 2025 |
 | `gpt-4`<br>`gpt-4-32k` | 0314 | No earlier than July 13, 2024 |
@@ -114,6 +114,10 @@ If you're an existing customer looking for information about these models, see [
 
 ## Retirement and deprecation history
 
+### April 24, 2024
+
+Earliest retirement date for `gpt-35-turbo` 0301 and 0613 has been updated to August 1, 2024.
+
 ### March 13, 2024
 
 We published this document to provide information about the current models, deprecated models, and upcoming retirements.

articles/ai-services/openai/concepts/models.md

@@ -4,7 +4,7 @@ titleSuffix: Azure OpenAI
 description: Learn about the different model capabilities that are available with Azure OpenAI.
 ms.service: azure-ai-openai
 ms.topic: conceptual
-ms.date: 04/17/2024
+ms.date: 04/24/2024
 ms.custom: references_regions, build-2023, build-2023-dataai, refefences_regions
 manager: nitinme
 author: mrbullwinkle #ChrisHMSFT
@@ -165,14 +165,14 @@ The following GPT-4 models are available with [Azure Government](/azure/azure-go
 > [!IMPORTANT]
 > The NEW `gpt-35-turbo (0125)`  model has various improvements, including higher accuracy at responding in requested formats and a fix for a bug which caused a text encoding issue for non-English language function calls.
 
-GPT-3.5 Turbo is used with the Chat Completion API. GPT-3.5 Turbo version 0301 can also be used with the Completions API.  GPT-3.5 Turbo versions 0613 and 1106 only support the Chat Completions API.
+GPT-3.5 Turbo is used with the Chat Completion API. GPT-3.5 Turbo version 0301 can also be used with the Completions API, though this is not recommended.  GPT-3.5 Turbo versions 0613 and 1106 only support the Chat Completions API.
 
 GPT-3.5 Turbo version 0301 is the first version of the model released.  Version 0613 is the second version of the model and adds function calling support.
 
 See [model versions](../concepts/model-versions.md) to learn about how Azure OpenAI Service handles model version upgrades, and [working with models](../how-to/working-with-models.md) to learn how to view and configure the model version settings of your GPT-3.5 Turbo deployments.
 
 > [!NOTE]
-> Version `0613` of `gpt-35-turbo` and `gpt-35-turbo-16k` will be retired no earlier than July 13, 2024. Version `0301` of `gpt-35-turbo` will be retired no earlier than June 13, 2024.  See [model updates](../how-to/working-with-models.md#model-updates) for model upgrade behavior.
+> Version `0613` of `gpt-35-turbo` and `gpt-35-turbo-16k` will be retired no earlier than August 1, 2024. Version `0301` of `gpt-35-turbo` will be retired no earlier than August 1, 2024.  See [model updates](../how-to/working-with-models.md#model-updates) for model upgrade behavior.
 
 |  Model ID   | Max Request (tokens) | Training Data (up to) |
 |  --------- |:------:|:----:|

articles/ai-services/openai/how-to/chat-markup-language.md

@@ -14,7 +14,7 @@ keywords: ChatGPT
 # Chat Markup Language ChatML (Preview)
 
 > [!IMPORTANT]
-> Using GPT-3.5-Turbo models with the completion endpoint as described in this article remains in preview and is only possible with `gpt-35-turbo` version (0301) which is [slated for retirement as early as June 13th, 2024](../concepts/model-retirements.md#current-models). We strongly recommend using the [GA Chat Completion API/endpoint](./chatgpt.md). The Chat Completion API is the recommended method of interacting with the GPT-3.5-Turbo models. The Chat Completion API is also the only way to access the GPT-4 models.
+> Using GPT-3.5-Turbo models with the completion endpoint as described in this article remains in preview and is only possible with `gpt-35-turbo` version (0301) which is [slated for retirement as early as August 1, 2024](../concepts/model-retirements.md#current-models). We strongly recommend using the [GA Chat Completion API/endpoint](./chatgpt.md). The Chat Completion API is the recommended method of interacting with the GPT-3.5-Turbo models. The Chat Completion API is also the only way to access the GPT-4 models.
 
 The following code snippet shows the most basic way to use the GPT-3.5-Turbo models with ChatML. If this is your first time using these models programmatically we recommend starting with our [GPT-35-Turbo & GPT-4 Quickstart](../chatgpt-quickstart.md).
 

articles/ai-services/openai/includes/chat-completion.md

@@ -425,7 +425,7 @@ def num_tokens_from_messages(messages, model="gpt-3.5-turbo-0613"):
         return num_tokens_from_messages(messages, model="gpt-4-0613")
     else:
         raise NotImplementedError(
-            f"""num_tokens_from_messages() is not implemented for model {model}. See https://github.com/openai/openai-python/blob/main/chatml.md for information on how messages are converted to tokens."""
+            f"""num_tokens_from_messages() is not implemented for model {model}."""
         )
     num_tokens = 0
     for message in messages:
@@ -547,13 +547,13 @@ The token counting portion of the code demonstrated previously is a simplified v
 
 Here's a troubleshooting tip.
 
-### Don't use ChatML syntax with the chat completion endpoint
+### Don't use ChatML syntax or special tokens with the chat completion endpoint
 
-Some customers try to use the [legacy ChatML syntax](../how-to/chat-markup-language.md) with the chat completion endpoints and newer models. ChatML was a preview capability that only worked with the legacy completions endpoint with the `gpt-35-turbo` version 0301 model. This model is [slated for retirement](../concepts/model-retirements.md). If you attempt to use ChatML syntax with newer models and the chat completion endpoint, it can result in errors and unexpected model response behavior. We don't recommend this use.
+Some customers try to use the [legacy ChatML syntax](../how-to/chat-markup-language.md) with the chat completion endpoints and newer models. ChatML was a preview capability that only worked with the legacy completions endpoint with the `gpt-35-turbo` version 0301 model. This model is [slated for retirement](../concepts/model-retirements.md). If you attempt to use ChatML syntax with newer models and the chat completion endpoint, it can result in errors and unexpected model response behavior. We don't recommend this use. This same issue can occur when using common special tokens.
 
 | Error |Cause | Solution |
 |---|---|---|
-| 400 - "Failed to generate output due to special tokens in the input." | Your prompt contains legacy ChatML tokens not recognized or supported by the model/endpoint. | Ensure that your prompt/messages array doesn't contain any legacy ChatML tokens. If you're upgrading from a legacy model, exclude all special tokens before you submit an API request to the model.|
+| 400 - "Failed to generate output due to special tokens in the input." | Your prompt contains legacy ChatML tokens not recognized or supported by the model/endpoint. | Ensure that your prompt/messages array doesn't contain any legacy ChatML tokens/special tokens. If you're upgrading from a legacy model, exclude all special tokens before you submit an API request to the model.|
 
 ## Next steps
 

articles/ai-studio/how-to/deploy-models-cohere-command.md

@@ -74,7 +74,7 @@ The previously mentioned Cohere models can be deployed as a service with pay-as-
 - An [Azure AI hub resource](../how-to/create-azure-ai-resource.md).
 
     > [!IMPORTANT]
-    > For Cohere family models, the pay-as-you-go model deployment offering is only available with AI hubs created in EastUS, EastUS2 or Sweden Central regions.
+    > For Cohere family models, the pay-as-you-go model deployment offering is only available with AI hubs created in EastUS2 or Sweden Central region.
 
 - An [Azure AI project](../how-to/create-projects.md) in Azure AI Studio.
 - Azure role-based access controls (Azure RBAC) are used to grant access to operations in Azure AI Studio. To perform the steps in this article, your user account must be assigned the __Azure AI Developer role__ on the resource group. For more information on permissions, see [Role-based access control in Azure AI Studio](../concepts/rbac-ai-studio.md).
@@ -93,7 +93,7 @@ To create a deployment:
 
     :::image type="content" source="../media/deploy-monitor/cohere-command/command-r-deploy-pay-as-you-go.png" alt-text="A screenshot showing how to deploy a model with the pay-as-you-go option." lightbox="../media/deploy-monitor/cohere-command/command-r-deploy-pay-as-you-go.png":::
 
-1. Select the project in which you want to deploy your model. To deploy the model your project must be in the EastUS, EastUS2 or Sweden Central regions.
+1. Select the project in which you want to deploy your model. To deploy the model your project must be in the EastUS2 or Sweden Central region.
 1. In the deployment wizard, select the link to **Azure Marketplace Terms** to learn more about the terms of use.
 1. You can also select the **Marketplace offer details** tab to learn about pricing for the selected model.
 1. If this is your first time deploying the model in the project, you have to subscribe your project for the particular offering. This step requires that your account has the **Azure AI Developer role** permissions on the Resource Group, as listed in the prerequisites. Each project has its own subscription to the particular Azure Marketplace offering of the model, which allows you to control and monitor spending. Select **Subscribe and Deploy**. Currently you can have only one deployment for each model within a project.
@@ -799,6 +799,16 @@ Response:
 | OpenAI SDK (experimental)    | [openaisdk.ipynb](https://aka.ms/samples/cohere-command/openaisdk)                                    |
 | LangChain      | [langchain.ipynb](https://aka.ms/samples/cohere/langchain)                                |
 | Cohere SDK     | [cohere-sdk.ipynb](https://aka.ms/samples/cohere-python-sdk)                                 |
+| LiteLLM SDK    | [litellm.ipynb](https://github.com/Azure/azureml-examples/blob/main/sdk/python/foundation-models/cohere/litellm.ipynb) |
+
+##### Retrieval Augmented Generation (RAG) and tool use samples
+**Description** | **Sample Type** | **Sample Notebook**
+--|--|--
+Create a local Facebook AI similarity search (FAISS) vector index, using Cohere embeddings - Langchain|`langchain`, `langchain_cohere`|[cohere_faiss_langchain_embed.ipynb](https://github.com/Azure/azureml-examples/blob/main/sdk/python/foundation-models/cohere/cohere_faiss_langchain_embed.ipynb)
+Use Cohere Command R/R+ to answer questions from data in local FAISS vector index - Langchain|`langchain`, `langchain_cohere`|[command_faiss_langchain.ipynb](https://github.com/Azure/azureml-examples/blob/main/sdk/python/foundation-models/cohere/command_faiss_langchain.ipynb)
+Use Cohere Command R/R+ to answer questions from data in AI search vector index - Langchain|`langchain`, `langchain_cohere`|[cohere-aisearch-langchain-rag.ipynb](https://github.com/Azure/azureml-examples/blob/main/sdk/python/foundation-models/cohere/cohere-aisearch-langchain-rag.ipynb)
+Use Cohere Command R/R+ to answer questions from data in AI search vector index - Cohere SDK| `cohere`, `azure_search_documents`|[cohere-aisearch-rag.ipynb](https://github.com/Azure/azureml-examples/blob/main/sdk/python/foundation-models/cohere/cohere-aisearch-rag.ipynb)
+Command R+ tool/function calling, using LangChain|`cohere`, `langchain`, `langchain_cohere`|[command_tools-langchain.ipynb](https://github.com/Azure/azureml-examples/blob/main/sdk/python/foundation-models/cohere/command_tools-langchain.ipynb)
 
 ## Cost and quotas
 

articles/ai-studio/how-to/deploy-models-cohere-embed.md

@@ -52,7 +52,7 @@ The previously mentioned Cohere models can be deployed as a service with pay-as-
 - An [Azure AI hub resource](../how-to/create-azure-ai-resource.md).
 
     > [!IMPORTANT]
-    > For Cohere family models, the pay-as-you-go model deployment offering is only available with AI hubs created in EastUS, EastUS2 or Sweden Central regions.
+    > For Cohere family models, the pay-as-you-go model deployment offering is only available with AI hubs created in EastUS2 or Sweden Central region.
 
 - An [Azure AI project](../how-to/create-projects.md) in Azure AI Studio.
 - Azure role-based access controls are used to grant access to operations in Azure AI Studio. To perform the steps in this article, your user account must be assigned the __Azure AI Developer role__ on the resource group. For more information on permissions, see [Role-based access control in Azure AI Studio](../concepts/rbac-ai-studio.md).
@@ -71,7 +71,7 @@ To create a deployment:
 
     :::image type="content" source="../media/deploy-monitor/cohere-embed/embed-english-deploy-pay-as-you-go.png" alt-text="A screenshot showing how to deploy a model with the pay-as-you-go option." lightbox="../media/deploy-monitor/cohere-embed/embed-english-deploy-pay-as-you-go.png":::
 
-1. Select the project in which you want to deploy your model. To deploy the model, your project must be in the EastUS, EastUS2 or Sweden Central regions.
+1. Select the project in which you want to deploy your model. To deploy the model, your project must be in the EastUS2 or Sweden Central region.
 1. In the deployment wizard, select the link to **Azure Marketplace Terms** to learn more about the terms of use.
 1. You can also select the **Marketplace offer details** tab to learn about pricing for the selected model.
 1. If it is your first time deploying the model in the project, you have to subscribe your project for the particular offering. This step requires that your account has the **Azure AI Developer role** permissions on the Resource Group, as listed in the prerequisites. Each project has its own subscription to the particular Azure Marketplace offering of the model, which allows you to control and monitor spending. Select **Subscribe and Deploy**. Currently you can have only one deployment for each model within a project.
@@ -119,15 +119,15 @@ These models can be consumed using the embed API.
     Content-type: application/json
 ```
 
-#### v1/emebeddings request schema
+#### v1/embeddings request schema
 
 Cohere Embed v3 - English and Embed v3 - Multilingual accept the following parameters for a `v1/embeddings` API call:
 
 | Property | Type | Default | Description |
 | --- | --- | --- | --- |
 |`input` |`array of strings` |Required |An array of strings for the model to embed. Maximum number of texts per call is 96. We recommend reducing the length of each text to be under 512 tokens for optimal quality. |
 
-#### v1/emebeddings response schema
+#### v1/embeddings response schema
 
 The response payload is a dictionary with the following fields:
 
@@ -330,6 +330,16 @@ Response:
 | OpenAI SDK (experimental)    | [openaisdk.ipynb](https://aka.ms/samples/cohere-embed/openaisdk)                                    |
 | LangChain      | [langchain.ipynb](https://aka.ms/samples/cohere-embed/langchain)                                |
 | Cohere SDK     | [cohere-sdk.ipynb](https://aka.ms/samples/cohere-embed/cohere-python-sdk)                                 |
+| LiteLLM SDK    | [litellm.ipynb](https://github.com/Azure/azureml-examples/blob/main/sdk/python/foundation-models/cohere/litellm.ipynb) |
+
+##### Retrieval Augmented Generation (RAG) and tool-use samples
+**Description** | **Sample Type** | **Sample Notebook**
+--|--|--
+Create a local Facebook AI Similarity Search (FAISS) vector index, using Cohere embeddings - Langchain|`langchain`, `langchain_cohere`|[cohere_faiss_langchain_embed.ipynb](https://github.com/Azure/azureml-examples/blob/main/sdk/python/foundation-models/cohere/cohere_faiss_langchain_embed.ipynb)
+Use Cohere Command R/R+ to answer questions from data in local FAISS vector index - Langchain|`langchain`, `langchain_cohere`|[command_faiss_langchain.ipynb](https://github.com/Azure/azureml-examples/blob/main/sdk/python/foundation-models/cohere/command_faiss_langchain.ipynb)
+Use Cohere Command R/R+ to answer questions from data in AI search vector index - Langchain|`langchain`, `langchain_cohere`|[cohere-aisearch-langchain-rag.ipynb](https://github.com/Azure/azureml-examples/blob/main/sdk/python/foundation-models/cohere/cohere-aisearch-langchain-rag.ipynb)
+Use Cohere Command R/R+ to answer questions from data in AI search vector index - Cohere SDK| `cohere`, `azure_search_documents`|[cohere-aisearch-rag.ipynb](https://github.com/Azure/azureml-examples/blob/main/sdk/python/foundation-models/cohere/cohere-aisearch-rag.ipynb)
+Command R+ tool/function calling, using LangChain|`cohere`, `langchain`, `langchain_cohere`|[command_tools-langchain.ipynb](https://github.com/Azure/azureml-examples/blob/main/sdk/python/foundation-models/cohere/command_tools-langchain.ipynb)
 
 ## Cost and quotas
 

articles/aks/long-term-support.md

@@ -120,9 +120,10 @@ For customers that wish to carry out an in-place migration, the AKS service will
 To carry out an in-place upgrade to the latest LTS version, you need to specify an LTS enabled Kubernetes version as the upgrade target.
 
 ```azurecli
-az aks upgrade --resource-group myResourceGroup --name myAKSCluster --kubernetes-version 1.30.2
+az aks upgrade --resource-group myResourceGroup --name myAKSCluster --kubernetes-version 1.32.2
 ```
 
 > [!NOTE]
-> Kubernetes 1.30.2 is used as an example version in this article. Check the [AKS release tracker](release-tracker.md) for available Kubernetes releases.
+> Kubernetes version 1.32 is the next Long Term Support Version after 1.27. Customers will get a minimum 6 months of overlap between 1.27 LTS and 1.32 LTS versions to plan upgrades.  
+> Kubernetes 1.32.2 is used as an example version in this article. Check the [AKS release tracker](release-tracker.md) for available Kubernetes releases.
 

articles/api-management/credentials-how-to-azure-ad.md

@@ -127,7 +127,9 @@ On the **Connection** tab, complete the steps for your connection to the provide
     |**URL** for GET    |  /me/joinedTeams |
 
 1. Select **All operations**. In the **Inbound processing** section, select the (**</>**) (code editor) icon.
-1. Make sure the `provider-id` and `authorization-id` values in the `get-authorization-context` policy correspond to the names of the credential provider and connection, respectively, that you configured in the preceding steps. Select **Save**. 
+1. Copy and paste the following snippet. Update the `get-authorization-context` policy with the names of the credential provider and connection that you configured in the preceding steps, and select **Save**.
+    * Substitute your credential provider name as the value of `provider-id`
+    * Substitute your connection name as the value of `authorization-id`  
 
     ```xml
     <policies>

articles/app-service/quickstart-python.md

@@ -194,7 +194,7 @@ Azure App Service captures all messages output to the console to assist you in d
 
 ### [Flask](#tab/flask)
 
-:::code language="python" source="~/msdocs-python-flask-webapp-quickstart/app.py" range="6-21" highlight="3,12,15":::
+:::code language="python" source="~/msdocs-python-flask-webapp-quickstart/app.py" range="9-29" highlight="11,24,27":::
 
 ### [Django](#tab/django)