Merge pull request #284207 from santiagxf/santiagxf-patch-3

Santiagxf patch 3

Author: prmerger-automator[bot]

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

@@ -135,7 +135,7 @@ The response is as follows:
 ```python
 print("Model name:", model_info.model_name)
 print("Model type:", model_info.model_type)
-print("Model provider name:", model_info.model_provider)
+print("Model provider name:", model_info.model_provider_name)
 ```
 
 ```console
@@ -209,14 +209,12 @@ To visualize the output, define a helper function to print the stream.
 ```python
 def print_stream(result):
     """
-    Prints the chat completion with streaming. Some delay is added to simulate 
-    a real-time conversation.
+    Prints the chat completion with streaming.
     """
     import time
     for update in result:
         if update.choices:
             print(update.choices[0].delta.content, end="")
-            time.sleep(0.05)
 ```
 
 You can visualize how streaming generates content:
@@ -1364,7 +1362,7 @@ catch (RequestFailedException ex)
 {
     if (ex.ErrorCode == "content_filter")
     {
-        Console.WriteLine($"Your query has trigger Azure Content Safeaty: {ex.Message}");
+        Console.WriteLine($"Your query has trigger Azure Content Safety: {ex.Message}");
     }
     else
     {

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

@@ -27,6 +27,8 @@ JAIS 30b Chat is an autoregressive bi-lingual LLM for **Arabic** & **English**.
 
 ::: zone pivot="programming-language-python"
 
+## Jais chat models
+
 
 
 You can learn more about the models in their respective model card:
@@ -103,7 +105,7 @@ The response is as follows:
 ```python
 print("Model name:", model_info.model_name)
 print("Model type:", model_info.model_type)
-print("Model provider name:", model_info.model_provider)
+print("Model provider name:", model_info.model_provider_name)
 ```
 
 ```console
@@ -177,14 +179,12 @@ To visualize the output, define a helper function to print the stream.
 ```python
 def print_stream(result):
     """
-    Prints the chat completion with streaming. Some delay is added to simulate 
-    a real-time conversation.
+    Prints the chat completion with streaming.
     """
     import time
     for update in result:
         if update.choices:
             print(update.choices[0].delta.content, end="")
-            time.sleep(0.05)
 ```
 
 You can visualize how streaming generates content:
@@ -278,6 +278,8 @@ except HttpResponseError as ex:
 
 ::: zone pivot="programming-language-javascript"
 
+## Jais chat models
+
 
 
 You can learn more about the models in their respective model card:
@@ -550,6 +552,8 @@ catch (error) {
 
 ::: zone pivot="programming-language-csharp"
 
+## Jais chat models
+
 
 
 You can learn more about the models in their respective model card:
@@ -821,7 +825,7 @@ catch (RequestFailedException ex)
 {
     if (ex.ErrorCode == "content_filter")
     {
-        Console.WriteLine($"Your query has trigger Azure Content Safeaty: {ex.Message}");
+        Console.WriteLine($"Your query has trigger Azure Content Safety: {ex.Message}");
     }
     else
     {
@@ -838,6 +842,8 @@ catch (RequestFailedException ex)
 
 ::: zone pivot="programming-language-rest"
 
+## Jais chat models
+
 
 
 You can learn more about the models in their respective model card:

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

@@ -26,6 +26,8 @@ The Jamba-Instruct model is AI21's production-grade Mamba-based large language m
 
 ::: zone pivot="programming-language-python"
 
+## Jamba-Instruct chat models
+
 
 
 You can learn more about the models in their respective model card:
@@ -102,7 +104,7 @@ The response is as follows:
 ```python
 print("Model name:", model_info.model_name)
 print("Model type:", model_info.model_type)
-print("Model provider name:", model_info.model_provider)
+print("Model provider name:", model_info.model_provider_name)
 ```
 
 ```console
@@ -176,14 +178,12 @@ To visualize the output, define a helper function to print the stream.
 ```python
 def print_stream(result):
     """
-    Prints the chat completion with streaming. Some delay is added to simulate 
-    a real-time conversation.
+    Prints the chat completion with streaming.
     """
     import time
     for update in result:
         if update.choices:
             print(update.choices[0].delta.content, end="")
-            time.sleep(0.05)
 ```
 
 You can visualize how streaming generates content:
@@ -277,6 +277,8 @@ except HttpResponseError as ex:
 
 ::: zone pivot="programming-language-javascript"
 
+## Jamba-Instruct chat models
+
 
 
 You can learn more about the models in their respective model card:
@@ -549,6 +551,8 @@ catch (error) {
 
 ::: zone pivot="programming-language-csharp"
 
+## Jamba-Instruct chat models
+
 
 
 You can learn more about the models in their respective model card:
@@ -820,7 +824,7 @@ catch (RequestFailedException ex)
 {
     if (ex.ErrorCode == "content_filter")
     {
-        Console.WriteLine($"Your query has trigger Azure Content Safeaty: {ex.Message}");
+        Console.WriteLine($"Your query has trigger Azure Content Safety: {ex.Message}");
     }
     else
     {
@@ -837,6 +841,8 @@ catch (RequestFailedException ex)
 
 ::: zone pivot="programming-language-rest"
 
+## Jamba-Instruct chat models
+
 
 
 You can learn more about the models in their respective model card:

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

@@ -159,7 +159,7 @@ The response is as follows:
 ```python
 print("Model name:", model_info.model_name)
 print("Model type:", model_info.model_type)
-print("Model provider name:", model_info.model_provider)
+print("Model provider name:", model_info.model_provider_name)
 ```
 
 ```console
@@ -233,14 +233,12 @@ To visualize the output, define a helper function to print the stream.
 ```python
 def print_stream(result):
     """
-    Prints the chat completion with streaming. Some delay is added to simulate 
-    a real-time conversation.
+    Prints the chat completion with streaming.
     """
     import time
     for update in result:
         if update.choices:
             print(update.choices[0].delta.content, end="")
-            time.sleep(0.05)
 ```
 
 You can visualize how streaming generates content:
@@ -1038,7 +1036,7 @@ catch (RequestFailedException ex)
 {
     if (ex.ErrorCode == "content_filter")
     {
-        Console.WriteLine($"Your query has trigger Azure Content Safeaty: {ex.Message}");
+        Console.WriteLine($"Your query has trigger Azure Content Safety: {ex.Message}");
     }
     else
     {

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

@@ -113,7 +113,7 @@ The response is as follows:
 ```python
 print("Model name:", model_info.model_name)
 print("Model type:", model_info.model_type)
-print("Model provider name:", model_info.model_provider)
+print("Model provider name:", model_info.model_provider_name)
 ```
 
 ```console
@@ -187,14 +187,12 @@ To visualize the output, define a helper function to print the stream.
 ```python
 def print_stream(result):
     """
-    Prints the chat completion with streaming. Some delay is added to simulate 
-    a real-time conversation.
+    Prints the chat completion with streaming.
     """
     import time
     for update in result:
         if update.choices:
             print(update.choices[0].delta.content, end="")
-            time.sleep(0.05)
 ```
 
 You can visualize how streaming generates content:
@@ -1385,7 +1383,7 @@ catch (RequestFailedException ex)
 {
     if (ex.ErrorCode == "content_filter")
     {
-        Console.WriteLine($"Your query has trigger Azure Content Safeaty: {ex.Message}");
+        Console.WriteLine($"Your query has trigger Azure Content Safety: {ex.Message}");
     }
     else
     {

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

@@ -158,7 +158,7 @@ The response is as follows:
 ```python
 print("Model name:", model_info.model_name)
 print("Model type:", model_info.model_type)
-print("Model provider name:", model_info.model_provider)
+print("Model provider name:", model_info.model_provider_name)
 ```
 
 ```console
@@ -235,14 +235,12 @@ To visualize the output, define a helper function to print the stream.
 ```python
 def print_stream(result):
     """
-    Prints the chat completion with streaming. Some delay is added to simulate 
-    a real-time conversation.
+    Prints the chat completion with streaming.
     """
     import time
     for update in result:
         if update.choices:
             print(update.choices[0].delta.content, end="")
-            time.sleep(0.05)
 ```
 
 You can visualize how streaming generates content:

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

@@ -143,7 +143,7 @@ The response is as follows:
 ```python
 print("Model name:", model_info.model_name)
 print("Model type:", model_info.model_type)
-print("Model provider name:", model_info.model_provider)
+print("Model provider name:", model_info.model_provider_name)
 ```
 
 ```console
@@ -217,14 +217,12 @@ To visualize the output, define a helper function to print the stream.
 ```python
 def print_stream(result):
     """
-    Prints the chat completion with streaming. Some delay is added to simulate 
-    a real-time conversation.
+    Prints the chat completion with streaming.
     """
     import time
     for update in result:
         if update.choices:
             print(update.choices[0].delta.content, end="")
-            time.sleep(0.05)
 ```
 
 You can visualize how streaming generates content:
@@ -1475,7 +1473,7 @@ catch (RequestFailedException ex)
 {
     if (ex.ErrorCode == "content_filter")
     {
-        Console.WriteLine($"Your query has trigger Azure Content Safeaty: {ex.Message}");
+        Console.WriteLine($"Your query has trigger Azure Content Safety: {ex.Message}");
     }
     else
     {

articles/ai-studio/how-to/deploy-models-phi-3-vision.md

@@ -23,6 +23,8 @@ The Phi-3 family of small language models (SLMs) is a collection of instruction-
 
 ::: zone pivot="programming-language-python"
 
+## Phi-3 chat models with vision
+
 Phi-3 Vision is a lightweight, state-of-the-art open multimodal model built upon datasets which include - synthetic data and filtered publicly available websites - with a focus on very high-quality, reasoning dense data both on text and vision. The model belongs to the Phi-3 model family, and the multimodal version comes with 128K context length (in tokens) it can support. The model underwent a rigorous enhancement process, incorporating both supervised fine-tuning and direct preference optimization to ensure precise instruction adherence and robust safety measures.
 
 
@@ -114,7 +116,7 @@ The response is as follows:
 ```python
 print("Model name:", model_info.model_name)
 print("Model type:", model_info.model_type)
-print("Model provider name:", model_info.model_provider)
+print("Model provider name:", model_info.model_provider_name)
 ```
 
 ```console
@@ -191,14 +193,12 @@ To visualize the output, define a helper function to print the stream.
 ```python
 def print_stream(result):
     """
-    Prints the chat completion with streaming. Some delay is added to simulate 
-    a real-time conversation.
+    Prints the chat completion with streaming.
     """
     import time
     for update in result:
         if update.choices:
             print(update.choices[0].delta.content, end="")
-            time.sleep(0.05)
 ```
 
 You can visualize how streaming generates content:
@@ -343,6 +343,8 @@ Usage:
 
 ::: zone pivot="programming-language-javascript"
 
+## Phi-3 chat models with vision
+
 Phi-3 Vision is a lightweight, state-of-the-art open multimodal model built upon datasets which include - synthetic data and filtered publicly available websites - with a focus on very high-quality, reasoning dense data both on text and vision. The model belongs to the Phi-3 model family, and the multimodal version comes with 128K context length (in tokens) it can support. The model underwent a rigorous enhancement process, incorporating both supervised fine-tuning and direct preference optimization to ensure precise instruction adherence and robust safety measures.
 
 
@@ -684,6 +686,8 @@ Usage:
 
 ::: zone pivot="programming-language-csharp"
 
+## Phi-3 chat models with vision
+
 Phi-3 Vision is a lightweight, state-of-the-art open multimodal model built upon datasets which include - synthetic data and filtered publicly available websites - with a focus on very high-quality, reasoning dense data both on text and vision. The model belongs to the Phi-3 model family, and the multimodal version comes with 128K context length (in tokens) it can support. The model underwent a rigorous enhancement process, incorporating both supervised fine-tuning and direct preference optimization to ensure precise instruction adherence and robust safety measures.
 
 
@@ -1022,6 +1026,8 @@ Usage:
 
 ::: zone pivot="programming-language-rest"
 
+## Phi-3 chat models with vision
+
 Phi-3 Vision is a lightweight, state-of-the-art open multimodal model built upon datasets which include - synthetic data and filtered publicly available websites - with a focus on very high-quality, reasoning dense data both on text and vision. The model belongs to the Phi-3 model family, and the multimodal version comes with 128K context length (in tokens) it can support. The model underwent a rigorous enhancement process, incorporating both supervised fine-tuning and direct preference optimization to ensure precise instruction adherence and robust safety measures.
 
 

articles/ai-studio/how-to/deploy-models-phi-3.md

@@ -169,7 +169,7 @@ The response is as follows:
 ```python
 print("Model name:", model_info.model_name)
 print("Model type:", model_info.model_type)
-print("Model provider name:", model_info.model_provider)
+print("Model provider name:", model_info.model_provider_name)
 ```
 
 ```console
@@ -246,14 +246,12 @@ To visualize the output, define a helper function to print the stream.
 ```python
 def print_stream(result):
     """
-    Prints the chat completion with streaming. Some delay is added to simulate 
-    a real-time conversation.
+    Prints the chat completion with streaming.
     """
     import time
     for update in result:
         if update.choices:
             print(update.choices[0].delta.content, end="")
-            time.sleep(0.05)
 ```
 
 You can visualize how streaming generates content:
@@ -1068,7 +1066,7 @@ catch (RequestFailedException ex)
 {
     if (ex.ErrorCode == "content_filter")
     {
-        Console.WriteLine($"Your query has trigger Azure Content Safeaty: {ex.Message}");
+        Console.WriteLine($"Your query has trigger Azure Content Safety: {ex.Message}");
     }
     else
     {