Merge pull request #255 from msakande/fix-response-format-for-chat-completions-models

Fix response format for chat completions models (AI Studio)

Author: prmerger-automator[bot]

articles/ai-studio/how-to/deploy-models-jais.md

@@ -201,7 +201,7 @@ print_stream(result)
 Explore other parameters that you can specify in the inference client. For a full list of all the supported parameters and their corresponding documentation, see [Azure AI Model Inference API reference](https://aka.ms/azureai/modelinference).
 
 ```python
-from azure.ai.inference.models import ChatCompletionsResponseFormatText
+from azure.ai.inference.models import ChatCompletionsResponseFormat
 
 response = client.complete(
     messages=[
@@ -214,12 +214,12 @@ response = client.complete(
     stop=["<|endoftext|>"],
     temperature=0,
     top_p=1,
-    response_format=ChatCompletionsResponseFormatText(),
+    response_format={ "type": ChatCompletionsResponseFormat.TEXT },
 )
 ```
 
 > [!WARNING]
-> Jais doesn't support JSON output formatting (`response_format = { "type": "json_object" }`). You can always prompt the model to generate JSON outputs. However, such outputs are not guaranteed to be valid JSON.
+> Jais models don't support JSON output formatting (`response_format = { "type": "json_object" }`). You can always prompt the model to generate JSON outputs. However, such outputs are not guaranteed to be valid JSON.
 
 If you want to pass a parameter that isn't in the list of supported parameters, you can pass it to the underlying model using *extra parameters*. See [Pass extra parameters to the model](#pass-extra-parameters-to-the-model).
 
@@ -482,7 +482,7 @@ var response = await client.path("/chat/completions").post({
 ```
 
 > [!WARNING]
-> Jais doesn't support JSON output formatting (`response_format = { "type": "json_object" }`). You can always prompt the model to generate JSON outputs. However, such outputs are not guaranteed to be valid JSON.
+> Jais models don't support JSON output formatting (`response_format = { "type": "json_object" }`). You can always prompt the model to generate JSON outputs. However, such outputs are not guaranteed to be valid JSON.
 
 If you want to pass a parameter that isn't in the list of supported parameters, you can pass it to the underlying model using *extra parameters*. See [Pass extra parameters to the model](#pass-extra-parameters-to-the-model).
 
@@ -580,7 +580,7 @@ Deployment to a serverless API endpoint doesn't require quota from your subscrip
 
 ### The inference package installed
 
-You can consume predictions from this model by using the `Azure.AI.Inference` package from [Nuget](https://www.nuget.org/). To install this package, you need the following prerequisites:
+You can consume predictions from this model by using the `Azure.AI.Inference` package from [NuGet](https://www.nuget.org/). To install this package, you need the following prerequisites:
 
 * The endpoint URL. To construct the client library, you need to pass in the endpoint URL. The endpoint URL has the form `https://your-host-name.your-azure-region.inference.ai.azure.com`, where `your-host-name` is your unique model deployment host name and `your-azure-region` is the Azure region where the model is deployed (for example, eastus2).
 * Depending on your model deployment and authentication preference, you need either a key to authenticate against the service, or Microsoft Entra ID credentials. The key is a 32-character string.
@@ -606,7 +606,7 @@ using Azure.Identity;
 using Azure.AI.Inference;
 ```
 
-This example also use the following namespaces but you may not always need them:
+This example also uses the following namespaces but you may not always need them:
 
 
 ```csharp
@@ -775,7 +775,7 @@ Console.WriteLine($"Response: {response.Value.Choices[0].Message.Content}");
 ```
 
 > [!WARNING]
-> Jais doesn't support JSON output formatting (`response_format = { "type": "json_object" }`). You can always prompt the model to generate JSON outputs. However, such outputs are not guaranteed to be valid JSON.
+> Jais models don't support JSON output formatting (`response_format = { "type": "json_object" }`). You can always prompt the model to generate JSON outputs. However, such outputs are not guaranteed to be valid JSON.
 
 If you want to pass a parameter that isn't in the list of supported parameters, you can pass it to the underlying model using *extra parameters*. See [Pass extra parameters to the model](#pass-extra-parameters-to-the-model).
 
@@ -1088,7 +1088,7 @@ Explore other parameters that you can specify in the inference client. For a ful
 ```
 
 > [!WARNING]
-> Jais doesn't support JSON output formatting (`response_format = { "type": "json_object" }`). You can always prompt the model to generate JSON outputs. However, such outputs are not guaranteed to be valid JSON.
+> Jais models don't support JSON output formatting (`response_format = { "type": "json_object" }`). You can always prompt the model to generate JSON outputs. However, such outputs are not guaranteed to be valid JSON.
 
 If you want to pass a parameter that isn't in the list of supported parameters, you can pass it to the underlying model using *extra parameters*. See [Pass extra parameters to the model](#pass-extra-parameters-to-the-model).
 
@@ -1165,14 +1165,14 @@ The following example shows how to handle events when the model detects harmful
 
 ## More inference examples
 
-For more examples of how to use Jais, see the following examples and tutorials:
+For more examples of how to use Jais models, see the following examples and tutorials:
 
 | Description                               | Language          | Sample                                                          |
 |-------------------------------------------|-------------------|-----------------------------------------------------------------|
 | Azure AI Inference package for JavaScript | JavaScript        | [Link](https://aka.ms/azsdk/azure-ai-inference/javascript/samples)  |
 | Azure AI Inference package for Python     | Python            | [Link](https://aka.ms/azsdk/azure-ai-inference/python/samples)  |
 
-## Cost and quota considerations for Jais family of models deployed as serverless API endpoints
+## Cost and quota considerations for Jais models deployed as serverless API endpoints
 
 Quota is managed per deployment. Each deployment has a rate limit of 200,000 tokens per minute and 1,000 API requests per minute. However, we currently limit one deployment per model per project. Contact Microsoft Azure Support if the current rate limits aren't sufficient for your scenarios.
 
@@ -1189,4 +1189,4 @@ For more information on how to track costs, see [Monitor costs for models offere
 * [Deploy models as serverless APIs](deploy-models-serverless.md)
 * [Consume serverless API endpoints from a different Azure AI Studio project or hub](deploy-models-serverless-connect.md)
 * [Region availability for models in serverless API endpoints](deploy-models-serverless-availability.md)
-* [Plan and manage costs (marketplace)](costs-plan-manage.md#monitor-costs-for-models-offered-through-the-azure-marketplace)
+* [Plan and manage costs (marketplace)](costs-plan-manage.md#monitor-costs-for-models-offered-through-the-azure-marketplace)

articles/ai-studio/how-to/deploy-models-llama.md

@@ -255,7 +255,7 @@ print_stream(result)
 Explore other parameters that you can specify in the inference client. For a full list of all the supported parameters and their corresponding documentation, see [Azure AI Model Inference API reference](https://aka.ms/azureai/modelinference).
 
 ```python
-from azure.ai.inference.models import ChatCompletionsResponseFormatText
+from azure.ai.inference.models import ChatCompletionsResponseFormat
 
 response = client.complete(
     messages=[
@@ -268,12 +268,12 @@ response = client.complete(
     stop=["<|endoftext|>"],
     temperature=0,
     top_p=1,
-    response_format=ChatCompletionsResponseFormatText(),
+    response_format={ "type": ChatCompletionsResponseFormat.TEXT },
 )
 ```
 
 > [!WARNING]
-> Meta Llama doesn't support JSON output formatting (`response_format = { "type": "json_object" }`). You can always prompt the model to generate JSON outputs. However, such outputs are not guaranteed to be valid JSON.
+> Meta Llama models don't support JSON output formatting (`response_format = { "type": "json_object" }`). You can always prompt the model to generate JSON outputs. However, such outputs are not guaranteed to be valid JSON.
 
 If you want to pass a parameter that isn't in the list of supported parameters, you can pass it to the underlying model using *extra parameters*. See [Pass extra parameters to the model](#pass-extra-parameters-to-the-model).
 
@@ -610,7 +610,7 @@ var response = await client.path("/chat/completions").post({
 ```
 
 > [!WARNING]
-> Meta Llama doesn't support JSON output formatting (`response_format = { "type": "json_object" }`). You can always prompt the model to generate JSON outputs. However, such outputs are not guaranteed to be valid JSON.
+> Meta Llama models don't support JSON output formatting (`response_format = { "type": "json_object" }`). You can always prompt the model to generate JSON outputs. However, such outputs are not guaranteed to be valid JSON.
 
 If you want to pass a parameter that isn't in the list of supported parameters, you can pass it to the underlying model using *extra parameters*. See [Pass extra parameters to the model](#pass-extra-parameters-to-the-model).
 
@@ -765,7 +765,7 @@ For deployment to a self-hosted managed compute, you must have enough quota in y
 
 ### The inference package installed
 
-You can consume predictions from this model by using the `Azure.AI.Inference` package from [Nuget](https://www.nuget.org/). To install this package, you need the following prerequisites:
+You can consume predictions from this model by using the `Azure.AI.Inference` package from [NuGet](https://www.nuget.org/). To install this package, you need the following prerequisites:
 
 * The endpoint URL. To construct the client library, you need to pass in the endpoint URL. The endpoint URL has the form `https://your-host-name.your-azure-region.inference.ai.azure.com`, where `your-host-name` is your unique model deployment host name and `your-azure-region` is the Azure region where the model is deployed (for example, eastus2).
 * Depending on your model deployment and authentication preference, you need either a key to authenticate against the service, or Microsoft Entra ID credentials. The key is a 32-character string.
@@ -791,7 +791,7 @@ using Azure.Identity;
 using Azure.AI.Inference;
 ```
 
-This example also use the following namespaces but you may not always need them:
+This example also uses the following namespaces but you may not always need them:
 
 
 ```csharp
@@ -973,7 +973,7 @@ Console.WriteLine($"Response: {response.Value.Choices[0].Message.Content}");
 ```
 
 > [!WARNING]
-> Meta Llama doesn't support JSON output formatting (`response_format = { "type": "json_object" }`). You can always prompt the model to generate JSON outputs. However, such outputs are not guaranteed to be valid JSON.
+> Meta Llama models don't support JSON output formatting (`response_format = { "type": "json_object" }`). You can always prompt the model to generate JSON outputs. However, such outputs are not guaranteed to be valid JSON.
 
 If you want to pass a parameter that isn't in the list of supported parameters, you can pass it to the underlying model using *extra parameters*. See [Pass extra parameters to the model](#pass-extra-parameters-to-the-model).
 
@@ -1348,7 +1348,7 @@ Explore other parameters that you can specify in the inference client. For a ful
 ```
 
 > [!WARNING]
-> Meta Llama doesn't support JSON output formatting (`response_format = { "type": "json_object" }`). You can always prompt the model to generate JSON outputs. However, such outputs are not guaranteed to be valid JSON.
+> Meta Llama models don't support JSON output formatting (`response_format = { "type": "json_object" }`). You can always prompt the model to generate JSON outputs. However, such outputs are not guaranteed to be valid JSON.
 
 If you want to pass a parameter that isn't in the list of supported parameters, you can pass it to the underlying model using *extra parameters*. See [Pass extra parameters to the model](#pass-extra-parameters-to-the-model).
 
@@ -1441,7 +1441,7 @@ The following example shows how to handle events when the model detects harmful
 
 ## More inference examples
 
-For more examples of how to use Meta Llama, see the following examples and tutorials:
+For more examples of how to use Meta Llama models, see the following examples and tutorials:
 
 | Description                               | Language          | Sample                                                             |
 |-------------------------------------------|-------------------|------------------------------------------------------------------- |
@@ -1453,7 +1453,7 @@ For more examples of how to use Meta Llama, see the following examples and tutor
 | LangChain                                 | Python            | [Link](https://aka.ms/meta-llama-3.1-405B-instruct-langchain)      |
 | LiteLLM                                   | Python            | [Link](https://aka.ms/meta-llama-3.1-405B-instruct-litellm)        | 
 
-## Cost and quota considerations for Meta Llama family of models deployed as serverless API endpoints
+## Cost and quota considerations for Meta Llama models deployed as serverless API endpoints
 
 Quota is managed per deployment. Each deployment has a rate limit of 200,000 tokens per minute and 1,000 API requests per minute. However, we currently limit one deployment per model per project. Contact Microsoft Azure Support if the current rate limits aren't sufficient for your scenarios.
 
@@ -1463,7 +1463,7 @@ Each time a project subscribes to a given offer from the Azure Marketplace, a ne
 
 For more information on how to track costs, see [Monitor costs for models offered through the Azure Marketplace](costs-plan-manage.md#monitor-costs-for-models-offered-through-the-azure-marketplace).
 
-## Cost and quota considerations for Meta Llama family of models deployed to managed compute
+## Cost and quota considerations for Meta Llama models deployed to managed compute
 
 Meta Llama models deployed to managed compute are billed based on core hours of the associated compute instance. The cost of the compute instance is determined by the size of the instance, the number of instances running, and the run duration.
 

articles/ai-studio/how-to/deploy-models-mistral-nemo.md

@@ -5,7 +5,7 @@ description: Learn how to use Mistral Nemo chat model with Azure AI Studio.
 ms.service: azure-ai-studio
 manager: scottpolly
 ms.topic: how-to
-ms.date: 08/08/2024
+ms.date: 09/12/2024
 ms.reviewer: kritifaujdar
 reviewer: fkriti
 ms.author: mopeakande
@@ -209,7 +209,7 @@ print_stream(result)
 Explore other parameters that you can specify in the inference client. For a full list of all the supported parameters and their corresponding documentation, see [Azure AI Model Inference API reference](https://aka.ms/azureai/modelinference).
 
 ```python
-from azure.ai.inference.models import ChatCompletionsResponseFormatText
+from azure.ai.inference.models import ChatCompletionsResponseFormat
 
 response = client.complete(
     messages=[
@@ -222,7 +222,7 @@ response = client.complete(
     stop=["<|endoftext|>"],
     temperature=0,
     top_p=1,
-    response_format=ChatCompletionsResponseFormatText(),
+    response_format={ "type": ChatCompletionsResponseFormat.TEXT },
 )
 ```
 
@@ -234,15 +234,13 @@ Mistral Nemo chat model can create JSON outputs. Set `response_format` to `json_
 
 
 ```python
-from azure.ai.inference.models import ChatCompletionsResponseFormatJSON
-
 response = client.complete(
     messages=[
         SystemMessage(content="You are a helpful assistant that always generate responses in JSON format, using."
                       " the following format: { ""answer"": ""response"" }."),
         UserMessage(content="How many languages are in the world?"),
     ],
-    response_format=ChatCompletionsResponseFormatJSON()
+    response_format={ "type": ChatCompletionsResponseFormat.JSON_OBJECT }
 )
 ```
 
@@ -962,7 +960,7 @@ Deployment to a serverless API endpoint doesn't require quota from your subscrip
 
 ### The inference package installed
 
-You can consume predictions from this model by using the `Azure.AI.Inference` package from [Nuget](https://www.nuget.org/). To install this package, you need the following prerequisites:
+You can consume predictions from this model by using the `Azure.AI.Inference` package from [NuGet](https://www.nuget.org/). To install this package, you need the following prerequisites:
 
 * The endpoint URL. To construct the client library, you need to pass in the endpoint URL. The endpoint URL has the form `https://your-host-name.your-azure-region.inference.ai.azure.com`, where `your-host-name` is your unique model deployment host name and `your-azure-region` is the Azure region where the model is deployed (for example, eastus2).
 * Depending on your model deployment and authentication preference, you need either a key to authenticate against the service, or Microsoft Entra ID credentials. The key is a 32-character string.
@@ -988,7 +986,7 @@ using Azure.Identity;
 using Azure.AI.Inference;
 ```
 
-This example also use the following namespaces but you may not always need them:
+This example also uses the following namespaces but you may not always need them:
 
 
 ```csharp
@@ -2010,7 +2008,7 @@ The following example shows how to handle events when the model detects harmful
 
 ## More inference examples
 
-For more examples of how to use Mistral, see the following examples and tutorials:
+For more examples of how to use Mistral models, see the following examples and tutorials:
 
 | Description                               | Language          | Sample                                                          |
 |-------------------------------------------|-------------------|-----------------------------------------------------------------|
@@ -2024,7 +2022,7 @@ For more examples of how to use Mistral, see the following examples and tutorial
 | LiteLLM                                   | Python            | [Link](https://aka.ms/mistral-large/litellm-sample)             | 
 
 
-## Cost and quota considerations for Mistral family of models deployed as serverless API endpoints
+## Cost and quota considerations for Mistral models deployed as serverless API endpoints
 
 Quota is managed per deployment. Each deployment has a rate limit of 200,000 tokens per minute and 1,000 API requests per minute. However, we currently limit one deployment per model per project. Contact Microsoft Azure Support if the current rate limits aren't sufficient for your scenarios.
 
@@ -2041,4 +2039,4 @@ For more information on how to track costs, see [Monitor costs for models offere
 * [Deploy models as serverless APIs](deploy-models-serverless.md)
 * [Consume serverless API endpoints from a different Azure AI Studio project or hub](deploy-models-serverless-connect.md)
 * [Region availability for models in serverless API endpoints](deploy-models-serverless-availability.md)
-* [Plan and manage costs (marketplace)](costs-plan-manage.md#monitor-costs-for-models-offered-through-the-azure-marketplace)
+* [Plan and manage costs (marketplace)](costs-plan-manage.md#monitor-costs-for-models-offered-through-the-azure-marketplace)