fix

santiagxf · santiagxf · commit 1a1f66b0ac42 · 2025-04-08T15:09:10.000-04:00
diff --git a/articles/ai-foundry/model-inference/includes/code-create-chat-client-entra.md b/articles/ai-foundry/model-inference/includes/code-create-chat-client-entra.md
@@ -126,7 +126,7 @@ Use the reference section to explore the API design and which parameters are ava
 __Request__
 
 ```HTTP/1.1
-POST https://<resource>.services.ai.azure.com/models/chat/completions?api-version=2024-05-01-preview
+POST https://<resource>.services.ai.azure.com/models/chat/completions?api-version=2025-04-01
 Authorization: Bearer <bearer-token>
 Content-Type: application/json
 ```
diff --git a/articles/ai-foundry/model-inference/includes/code-create-chat-client.md b/articles/ai-foundry/model-inference/includes/code-create-chat-client.md
@@ -111,7 +111,7 @@ Use the reference section to explore the API design and which parameters are ava
 __Request__
 
 ```HTTP/1.1
-POST https://<resource>.services.ai.azure.com/models/chat/completions?api-version=2024-05-01-preview
+POST https://<resource>.services.ai.azure.com/models/chat/completions?api-version=2025-04-01
 api-key: <api-key>
 Content-Type: application/json
 ```
diff --git a/articles/ai-foundry/model-inference/includes/code-create-chat-completion.md b/articles/ai-foundry/model-inference/includes/code-create-chat-completion.md
@@ -17,7 +17,7 @@ response = client.complete(
         SystemMessage(content="You are a helpful assistant."),
         UserMessage(content="Explain Riemann's conjecture in 1 paragraph"),
     ],
-    model="mistral-large"
+    model="mistral-large-2405"
 )
 
 print(response.choices[0].message.content)
@@ -34,7 +34,7 @@ var messages = [
 var response = await client.path("/chat/completions").post({
     body: {
         messages: messages,
-        model: "mistral-large"
+        model: "mistral-large-2405"
     }
 });
 
@@ -50,7 +50,7 @@ requestOptions = new ChatCompletionsOptions()
         new ChatRequestSystemMessage("You are a helpful assistant."),
         new ChatRequestUserMessage("Explain Riemann's conjecture in 1 paragraph")
     },
-    Model = "mistral-large"
+    Model = "mistral-large-2405"
 };
 
 response = client.Complete(requestOptions);
@@ -77,7 +77,7 @@ for (ChatChoice choice : chatCompletions.getChoices()) {
 __Request__
 
 ```HTTP/1.1
-POST https://<resource>.services.ai.azure.com/models/chat/completions?api-version=2024-05-01-preview
+POST https://<resource>.services.ai.azure.com/models/chat/completions?api-version=2025-04-01
 api-key: <api-key>
 Content-Type: application/json
 ```
@@ -94,7 +94,7 @@ Content-Type: application/json
             "content": "Explain Riemann's conjecture in 1 paragraph"
         }
     ],
-    "model": "mistral-large"
+    "model": "mistral-large-2405"
 }
 ```
 
diff --git a/articles/ai-foundry/model-inference/includes/code-create-chat-reasoning.md b/articles/ai-foundry/model-inference/includes/code-create-chat-reasoning.md
@@ -73,7 +73,7 @@ for (ChatChoice choice : chatCompletions.getChoices()) {
 __Request__
 
 ```HTTP/1.1
-POST https://<resource>.services.ai.azure.com/models/chat/completions?api-version=2024-05-01-preview
+POST https://<resource>.services.ai.azure.com/models/chat/completions?api-version=2025-04-01
 api-key: <api-key>
 Content-Type: application/json
 ```
diff --git a/articles/ai-foundry/model-inference/includes/code-create-embeddings-client.md b/articles/ai-foundry/model-inference/includes/code-create-embeddings-client.md
@@ -128,7 +128,7 @@ Use the reference section to explore the API design and which parameters are ava
 __Request__
 
 ```HTTP/1.1
-POST https://<resource>.services.ai.azure.com/models/embeddings?api-version=2024-05-01-preview
+POST https://<resource>.services.ai.azure.com/models/embeddings?api-version=2025-04-01
 api-key: <api-key>
 Content-Type: application/json
 ```
diff --git a/articles/ai-foundry/model-inference/includes/code-create-embeddings.md b/articles/ai-foundry/model-inference/includes/code-create-embeddings.md
@@ -53,7 +53,7 @@ Console.WriteLine($"Response: {response.Data.Embeddings}");
 __Request__
 
 ```HTTP/1.1
-POST https://<resource>.services.ai.azure.com/models/embeddings?api-version=2024-05-01-preview
+POST https://<resource>.services.ai.azure.com/models/embeddings?api-version=2025-04-01
 api-key: <api-key>
 Content-Type: application/json
 ```
diff --git a/articles/ai-foundry/model-inference/includes/code-manage-content-filtering.md b/articles/ai-foundry/model-inference/includes/code-manage-content-filtering.md
@@ -122,7 +122,7 @@ try {
 __Request__
 
 ```HTTP/1.1
-POST https://<resource>.services.ai.azure.com/models/chat/completions?api-version=2024-05-01-preview
+POST https://<resource>.services.ai.azure.com/models/chat/completions?api-version=2025-04-01
 api-key: <api-key>
 Content-Type: application/json
 ```
diff --git a/articles/ai-foundry/model-inference/includes/use-chat-completions/csharp.md b/articles/ai-foundry/model-inference/includes/use-chat-completions/csharp.md
@@ -48,7 +48,7 @@ If you've configured the resource with **Microsoft Entra ID** support, you can u
 ```csharp
 TokenCredential credential = new DefaultAzureCredential(includeInteractiveCredentials: true);
 AzureAIInferenceClientOptions clientOptions = new AzureAIInferenceClientOptions();
-BearerTokenAuthenticationPolicy tokenPolicy = new BearerTokenAuthenticationPolicy(credential, new string[] { "https://cognitiveservices.azure.com/.default" });
+BearerTokenAuthenticationPolicy tokenPolicy = new BearerTokenAuthenticationPolicy(credential);
 
 clientOptions.AddPolicy(tokenPolicy, HttpPipelinePosition.PerRetry);
 
diff --git a/articles/ai-foundry/model-inference/includes/use-chat-completions/rest.md b/articles/ai-foundry/model-inference/includes/use-chat-completions/rest.md
@@ -33,15 +33,15 @@ To use chat completion models in your application, you need:
 To use chat completions API, use the route `/chat/completions` appended to the base URL along with your credential indicated in `api-key`. 
 
 ```http
-POST https://<resource>.services.ai.azure.com/models/chat/completions?api-version=2024-05-01-preview
+POST https://<resource>.services.ai.azure.com/models/chat/completions?api-version=2025-04-01
 Content-Type: application/json
 api-key: <key>
 ```
 
 If you've configured the resource with **Microsoft Entra ID** support, pass you token in the `Authorization` header with the format `Bearer <token>`. Use scope `https://cognitiveservices.azure.com/.default`. 
 
 ```http
-POST https://<resource>.services.ai.azure.com/models/chat/completions?api-version=2024-05-01-preview
+POST https://<resource>.services.ai.azure.com/models/chat/completions?api-version=2025-04-01
 Content-Type: application/json
 Authorization: Bearer <token>
 ```
@@ -291,7 +291,7 @@ Some models can create JSON outputs. Set `response_format` to `json_object` to e
 The Azure AI Model Inference API allows you to pass extra parameters to the model. The following code example shows how to pass the extra parameter `logprobs` to the model. 
 
 ```http
-POST https://<resource>.services.ai.azure.com/models/chat/completions?api-version=2024-05-01-preview
+POST https://<resource>.services.ai.azure.com/models/chat/completions?api-version=2025-04-01
 Authorization: Bearer <TOKEN>
 Content-Type: application/json
 extra-parameters: pass-through
diff --git a/articles/ai-foundry/model-inference/includes/use-chat-multi-modal/csharp.md b/articles/ai-foundry/model-inference/includes/use-chat-multi-modal/csharp.md
@@ -48,7 +48,7 @@ If you've configured the resource with **Microsoft Entra ID** support, you can u
 ```csharp
 TokenCredential credential = new DefaultAzureCredential(includeInteractiveCredentials: true);
 AzureAIInferenceClientOptions clientOptions = new AzureAIInferenceClientOptions();
-BearerTokenAuthenticationPolicy tokenPolicy = new BearerTokenAuthenticationPolicy(credential, new string[] { "https://cognitiveservices.azure.com/.default" });
+BearerTokenAuthenticationPolicy tokenPolicy = new BearerTokenAuthenticationPolicy(credential);
 
 clientOptions.AddPolicy(tokenPolicy, HttpPipelinePosition.PerRetry);
 
diff --git a/articles/ai-foundry/model-inference/includes/use-chat-multi-modal/rest.md b/articles/ai-foundry/model-inference/includes/use-chat-multi-modal/rest.md
@@ -34,15 +34,15 @@ To use chat completion models in your application, you need:
 To use chat completions API, use the route `/chat/completions` appended to the base URL along with your credential indicated in `api-key`. `Authorization` header is also supported with the format `Bearer <key>`.
 
 ```http
-POST https://<resource>.services.ai.azure.com/models/chat/completions?api-version=2024-05-01-preview
+POST https://<resource>.services.ai.azure.com/models/chat/completions?api-version=2025-04-01
 Content-Type: application/json
 api-key: <key>
 ```
 
 If you've configured the resource with **Microsoft Entra ID** support, pass your token in the `Authorization` header with the format `Bearer <token>`. Use scope `https://cognitiveservices.azure.com/.default`. 
 
 ```http
-POST https://<resource>.services.ai.azure.com/models/chat/completions?api-version=2024-05-01-preview
+POST https://<resource>.services.ai.azure.com/models/chat/completions?api-version=2025-04-01
 Content-Type: application/json
 Authorization: Bearer <token>
 ```
diff --git a/articles/ai-foundry/model-inference/includes/use-chat-reasoning/csharp.md b/articles/ai-foundry/model-inference/includes/use-chat-reasoning/csharp.md
@@ -29,18 +29,50 @@ To complete this tutorial, you need:
 
 First, create the client to consume the model. The following code uses an endpoint URL and key that are stored in environment variables.
 
+# [API version 2025-04-01](#tab/2025-04-01)
+
 ```csharp
 ChatCompletionsClient client = new ChatCompletionsClient(
     new Uri("https://<resource>.services.ai.azure.com/models"),
     new AzureKeyCredential(Environment.GetEnvironmentVariable("AZURE_INFERENCE_CREDENTIAL"))
 );
 ```
 
+# [API version 2024-05-01-preview](#tab/2024-05-01-preview)
+
+```csharp
+ChatCompletionsClient client = new ChatCompletionsClient(
+    new Uri("https://<resource>.services.ai.azure.com/models"),
+    new AzureKeyCredential(Environment.GetEnvironmentVariable("AZURE_INFERENCE_CREDENTIAL")),
+    new AzureAIInferenceClientOptions(ApiVersion="2024-05-01-preview");
+);
+```
+
+---
+
 > [!TIP]
 > Verify that you have deployed the model to Azure AI Services resource with the Azure AI model inference API. `Deepseek-R1` is also available as Serverless API Endpoints. However, those endpoints don't take the parameter `model` as explained in this tutorial. You can verify that by going to [Azure AI Foundry portal]() > Models + endpoints, and verify that the model is listed under the section **Azure AI Services**.
 
 If you have configured the resource to with **Microsoft Entra ID** support, you can use the following code snippet to create a client.
 
+# [API version 2025-04-01](#tab/2025-04-01)
+
+```csharp
+TokenCredential credential = new DefaultAzureCredential(includeInteractiveCredentials: true);
+AzureAIInferenceClientOptions clientOptions = new AzureAIInferenceClientOptions();
+BearerTokenAuthenticationPolicy tokenPolicy = new BearerTokenAuthenticationPolicy(credential);
+
+clientOptions.AddPolicy(tokenPolicy, HttpPipelinePosition.PerRetry);
+
+client = new ChatCompletionsClient(
+    new Uri("https://<resource>.services.ai.azure.com/models"),
+    credential,
+    clientOptions,
+);
+```
+
+# [API version 2024-05-01-preview](#tab/2024-05-01-preview)
+
 ```csharp
 TokenCredential credential = new DefaultAzureCredential(includeInteractiveCredentials: true);
 AzureAIInferenceClientOptions clientOptions = new AzureAIInferenceClientOptions();
@@ -55,6 +87,8 @@ client = new ChatCompletionsClient(
 );
 ```
 
+---
+
 ### Create a chat completion request
 
 The following example shows how you can create a basic chat request to the model.
@@ -75,6 +109,29 @@ Response<ChatCompletions> response = client.Complete(requestOptions);
 
 The response is as follows, where you can see the model's usage statistics:
 
+# [API version 2025-04-01](#tab/2025-04-01)
+
+```csharp
+Console.WriteLine($"Response: {response.Value.Content}");
+Console.WriteLine($"Model: {response.Value.Model}");
+Console.WriteLine("Usage:");
+Console.WriteLine($"\tPrompt tokens: {response.Value.Usage.PromptTokens}");
+Console.WriteLine($"\tTotal tokens: {response.Value.Usage.TotalTokens}");
+Console.WriteLine($"\tCompletion tokens: {response.Value.Usage.CompletionTokens}");
+```
+
+```console
+Response: The exact number of languages in the world is challenging to determine due to differences in definitions (e.g., distinguishing languages from dialects) and ongoing documentation efforts. However, widely cited estimates suggest there are approximately **7,000 languages** globally.
+Model: deepseek-r1
+Usage: 
+  Prompt tokens: 11
+  Total tokens: 897
+  Completion tokens: 886
+```
+
+
+# [API version 2024-05-01-preview](#tab/2024-05-01-preview)
+
 ```csharp
 Console.WriteLine($"Response: {response.Value.Content}");
 Console.WriteLine($"Model: {response.Value.Model}");
@@ -95,7 +152,24 @@ Usage:
 
 ### Reasoning content
 
-Some reasoning models, like DeepSeek-R1, generate completions and include the reasoning behind it. The reasoning associated with the completion is included in the response's content within the tags `<think>` and `</think>`. The model may select on which scenarios to generate reasoning content. You can extract the reasoning content from the response to understand the model's thought process as follows:
+Some reasoning models, like DeepSeek-R1, generate completions and include the reasoning behind it.
+
+# [API version 2025-04-01](#tab/2025-04-01)
+
+The reasoning associated with the completion is included in the response's `ReasoningContent` field. The model may select on which scenarios to generate reasoning content.
+
+```csharp
+Console.WriteLine($"Thinking: {response.Value.ReasoningContent}");
+```
+
+```console
+Thinking: Okay, the user is asking how many languages exist in the world. I need to provide a clear and accurate answer. Let's start by recalling the general consensus from linguistic sources. I remember that the number often cited is around 7,000, but maybe I should check some reputable organizations.\n\nEthnologue is a well-known resource for language data, and I think they list about 7,000 languages. But wait, do they update their numbers? It might be around 7,100 or so. Also, the exact count can vary because some sources might categorize dialects differently or have more recent data. \n\nAnother thing to consider is language endangerment. Many languages are endangered, with some having only a few speakers left. Organizations like UNESCO track endangered languages, so mentioning that adds context. Also, the distribution isn't even. Some countries have hundreds of languages, like Papua New Guinea with over 800, while others have just a few. \n\nA user might also wonder why the exact number is hard to pin down. It's because the distinction between a language and a dialect can be political or cultural. For example, Mandarin and Cantonese are considered dialects of Chinese by some, but they're mutually unintelligible, so others classify them as separate languages. Also, some regions are under-researched, making it hard to document all languages. \n\nI should also touch on language families. The 7,000 languages are grouped into families like Indo-European, Sino-Tibetan, Niger-Congo, etc. Maybe mention a few of the largest families. But wait, the question is just about the count, not the families. Still, it's good to provide a bit more context. \n\nI need to make sure the information is up-to-date. Let me think – recent estimates still hover around 7,000. However, languages are dying out rapidly, so the number decreases over time. Including that note about endangerment and language extinction rates could be helpful. For instance, it's often stated that a language dies every few weeks. \n\nAnother point is sign languages. Does the count include them? Ethnologue includes some, but not all sources might. If the user is including sign languages, that adds more to the count, but I think the 7,000 figure typically refers to spoken languages. For thoroughness, maybe mention that there are also over 300 sign languages. \n\nSummarizing, the answer should state around 7,000, mention Ethnologue's figure, explain why the exact number varies, touch on endangerment, and possibly note sign languages as a separate category. Also, a brief mention of Papua New Guinea as the most linguistically diverse country. \n\nWait, let me verify Ethnologue's current number. As of their latest edition (25th, 2022), they list 7,168 living languages. But I should check if that's the case. Some sources might round to 7,000. Also, SIL International publishes Ethnologue, so citing them as reference makes sense. \n\nOther sources, like Glottolog, might have a different count because they use different criteria. Glottolog might list around 7,000 as well, but exact numbers vary. It's important to highlight that the count isn't exact because of differing definitions and ongoing research. \n\nIn conclusion, the approximate number is 7,000, with Ethnologue being a key source, considerations of endangerment, and the challenges in counting due to dialect vs. language distinctions. I should make sure the answer is clear, acknowledges the variability, and provides key points succinctly.
+```
+
+
+# [API version 2024-05-01-preview](#tab/2024-05-01-preview)
+
+The reasoning associated with the completion is included in the response's content within the tags `<think>` and `</think>`. The model may select on which scenarios to generate reasoning content. You can extract the reasoning content from the response to understand the model's thought process as follows:
 
 ```csharp
 Regex regex = new Regex(pattern, RegexOptions.Singleline);
@@ -128,6 +202,8 @@ Usage:
   Completion tokens: 886
 ```
 
+---
+
 When making multi-turn conversations, it's useful to avoid sending the reasoning content in the chat history as reasoning tends to generate long explanations.
 
 ### Stream content
@@ -156,6 +232,41 @@ static async Task StreamMessageAsync(ChatCompletionsClient client)
 
 To visualize the output, define a helper function to print the stream. The following example implements a routing that stream only the answer without the reasoning content:
 
+# [API version 2025-04-01](#tab/2025-04-01)
+
+```csharp
+static void PrintStream(StreamingResponse<StreamingChatCompletionsUpdate> response)
+{
+    bool isThinking = false;
+    await foreach (StreamingChatCompletionsUpdate chatUpdate in response)
+    {
+        if (!string.IsNullOrEmpty(chatUpdate.ContentUpdate))
+        {
+            string content = chatUpdate.ContentUpdate;
+            string reasoningContent = chatUpdate.ReasoningContentUpdate;
+            if (!string.IsNullOrEmpty(reasoningContent))
+            {
+                isThinking = true;
+                Console.Write("🧠 Thinking...");
+                Console.Out.Flush();
+            }
+            else if (string.IsNullOrEmpty(reasoningContent))
+            {
+                isThinking = false;
+                Console.WriteLine("🛑\n\n");
+            }
+            else if (!string.IsNullOrEmpty(content))
+            {
+                Console.Write(content);
+                Console.Out.Flush();
+            }
+        }
+    }
+}
+```
+
+# [API version 2024-05-01-preview](#tab/2024-05-01-preview)
+
 ```csharp
 static void PrintStream(StreamingResponse<StreamingChatCompletionsUpdate> response)
 {
@@ -186,6 +297,8 @@ static void PrintStream(StreamingResponse<StreamingChatCompletionsUpdate> respon
 }
 ```
 
+---
+
 You can visualize how streaming generates content:
 
 
diff --git a/articles/ai-foundry/model-inference/includes/use-chat-reasoning/java.md b/articles/ai-foundry/model-inference/includes/use-chat-reasoning/java.md
@@ -34,6 +34,7 @@ First, create the client to consume the model. The following code uses an endpoi
 ChatCompletionsClient client = new ChatCompletionsClient(
         new URI("https://<resource>.services.ai.azure.com/models"),
         new AzureKeyCredential(System.getProperty("AZURE_INFERENCE_CREDENTIAL")),
+    );
 ```
 
 > [!TIP]
@@ -42,10 +43,10 @@ ChatCompletionsClient client = new ChatCompletionsClient(
 If you have configured the resource to with **Microsoft Entra ID** support, you can use the following code snippet to create a client.
 
 ```java
-client = new ChatCompletionsClient(
+ChatCompletionsClient client = new ChatCompletionsClient(
         new URI("https://<resource>.services.ai.azure.com/models"),
         new DefaultAzureCredentialBuilder().build()
-);
+    );
 ```
 
 ### Create a chat completion request
diff --git a/articles/ai-foundry/model-inference/includes/use-chat-reasoning/python.md b/articles/ai-foundry/model-inference/includes/use-chat-reasoning/python.md
diff --git a/articles/ai-foundry/model-inference/includes/use-embeddings/java.md b/articles/ai-foundry/model-inference/includes/use-embeddings/java.md
diff --git a/articles/ai-foundry/model-inference/includes/use-embeddings/rest.md b/articles/ai-foundry/model-inference/includes/use-embeddings/rest.md
diff --git a/articles/ai-foundry/model-inference/includes/use-image-embeddings/csharp.md b/articles/ai-foundry/model-inference/includes/use-image-embeddings/csharp.md
diff --git a/articles/ai-foundry/model-inference/includes/use-image-embeddings/rest.md b/articles/ai-foundry/model-inference/includes/use-image-embeddings/rest.md
