@@ -620,8 +620,8 @@ import * as dotenv from "dotenv";
 dotenv.config();
 
 // You will need to set these environment variables or edit the following values
-const endpoint = process.env["ENDPOINT"] || "<endpoint>";
-const azureApiKey = process.env["AZURE_API_KEY"] || "<api key>";
+const endpoint = process.env["ENDPOINT"] || "Your endpoint";
+const azureApiKey = process.env["AZURE_API_KEY"] || "Your API key";
 
 const messages = [
   { role: "system", content: "You are a helpful assistant. You will talk like a pirate." },

@@ -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: 02/20/2025
+ms.date: 02/25/2025
 ms.custom: 
 manager: nitinme
 author: mrbullwinkle
@@ -93,18 +93,16 @@ These models are currently available for use in Azure OpenAI Service.
 
 | Model | Version | Retirement date | Suggested replacements |
 | ---- | ---- | ---- | --- |
-| `dall-e-3` | 3 | No earlier than April 30, 2025 | |
-| `gpt-35-turbo` | 0301 | February 13, 2025<br><br> Deployments set to [**Auto-update to default**](/azure/ai-services/openai/how-to/working-with-models?tabs=powershell#auto-update-to-default) will be automatically upgraded to version: `0125`, starting on January 21, 2025.   | `gpt-35-turbo` (0125) <br><br> `gpt-4o-mini`  |
-| `gpt-35-turbo` | 0613 | February 13, 2025 <br><br> Deployments set to [**Auto-update to default**](/azure/ai-services/openai/how-to/working-with-models?tabs=powershell#auto-update-to-default) will be automatically upgraded to version: `0125`, starting on January 21, 2025.  | `gpt-35-turbo` (0125) <br><br> `gpt-4o-mini`|
+| `dall-e-3` | 3 | No earlier than June 30, 2025 | |
 | `gpt-35-turbo-16k`| 0613 | April, 30, 2025 | `gpt-35-turbo` (0125) <br><br> `gpt-4o-mini`|
 | `gpt-35-turbo` | 1106 | No earlier than May 31, 2025 <br><br> Deployments set to [**Auto-update to default**](/azure/ai-services/openai/how-to/working-with-models?tabs=powershell#auto-update-to-default) will be automatically upgraded to version: `0125`, starting on January 21, 2025. | `gpt-35-turbo` (0125) <br><br> `gpt-4o-mini` |
 | `gpt-35-turbo` | 0125 | No earlier than May 31, 2025 | `gpt-4o-mini` |
 | `gpt-4`<br>`gpt-4-32k` | 0314 | June 6, 2025 | `gpt-4o` |
 | `gpt-4`<br>`gpt-4-32k` | 0613 | June 6, 2025 | `gpt-4o` |
 | `gpt-4` | turbo-2024-04-09 | No earlier than June 6, 2025 | `gpt-4o`|
-| `gpt-4` | 1106-preview | To be upgraded to `gpt-4` version: `turbo-2024-04-09`, starting no sooner than February 10, 2025 **<sup>1</sup>** <br>Retirement date: February 28, 2025  | `gpt-4o`|
-| `gpt-4` | 0125-preview |To be upgraded to `gpt-4` version: `turbo-2024-04-09`, starting no sooner than February 10, 2025 **<sup>1</sup>** <br>Retirement date: February 28, 2025  | `gpt-4o` |
-| `gpt-4` | vision-preview | To be upgraded to `gpt-4` version: `turbo-2024-04-09`, starting no sooner than February 10, 2025  **<sup>1</sup>** <br>Retirement date: February 28, 2025 | `gpt-4o`|
+| `gpt-4` | 1106-preview | To be upgraded to `gpt-4` version: `turbo-2024-04-09`, starting no sooner than February 10, 2025 **<sup>1</sup>** <br>Retirement date: April 02, 2025  | `gpt-4o`|
+| `gpt-4` | 0125-preview |To be upgraded to `gpt-4` version: `turbo-2024-04-09`, starting no sooner than February 10, 2025 **<sup>1</sup>** <br>Retirement date: April 02, 2025  | `gpt-4o` |
+| `gpt-4` | vision-preview | To be upgraded to `gpt-4` version: `turbo-2024-04-09`, starting no sooner than February 10, 2025  **<sup>1</sup>** <br>Retirement date: April 02, 2025 | `gpt-4o`|
 | `gpt-4o` | 2024-05-13 | No earlier than May 20, 2025 <br><br>Deployments set to [**Auto-update to default**](/azure/ai-services/openai/how-to/working-with-models?tabs=powershell#auto-update-to-default) will be automatically upgraded to version: `2024-08-06`, starting on February 13, 2025. | |
 | `gpt-4o` | 2024-08-06 | No earlier than August 6, 2025  | |
 | `gpt-4o` | 2024-11-20 | No earlier than November 20, 2025  | |
@@ -138,6 +136,8 @@ If you're an existing customer looking for information about these models, see [
 
 | Model | Deprecation date | Retirement date | Suggested replacement |
 | --------- | --------------------- | ------------------- | -------------------- |
+| `gpt-35-turbo` - 0301 | | February 13, 2025   | `gpt-35-turbo` (0125) <br><br> `gpt-4o-mini`  |
+| `gpt-35-turbo` - 0613 | | February 13, 2025 | `gpt-35-turbo` (0125) <br><br> `gpt-4o-mini`  |
 | babbage-002 | | January 27, 2025 |  |
 | davinci-002 | | January 27, 2025 | |
 | dall-e-2|  | January 27, 2025 | dalle-3 |
@@ -171,6 +171,10 @@ If you're an existing customer looking for information about these models, see [
 
 ## Retirement and deprecation history
 
+## February 25, 2025
+
+-  `dalle-3` updated to no earlier than June 30, 2025.
+
 ## February 20, 2025
 
 - `o1-preview` updated to no earlier than April 2, 2025.

@@ -46,6 +46,7 @@ In this article, you review examples for creating and deploying resources in the
 
 ## Next steps
 
+- [Get started with the Azure OpenAI security building block](/azure/developer/ai/get-started-securing-your-ai-app?tabs=github-codespaces&pivots=python)
 - Make API calls and generate text with [Azure OpenAI Service quickstarts](../quickstart.md).
 - Learn more about the [Azure OpenAI Service models](../concepts/models.md).
 - For information on pricing visit the [Azure OpenAI pricing page](https://azure.microsoft.com/pricing/details/cognitive-services/openai-service/)

@@ -1,24 +1,118 @@
 ---
 title: Fine-tuning function calls with Azure OpenAI Service
-description: Learn how to improve function calling performance with Azure OpenAI fine-tuning
+description: Learn how to improve tool calling performance with Azure OpenAI fine-tuning
 #services: cognitive-services
 manager: nitinme
 ms.service: azure-ai-openai
 ms.topic: how-to
-ms.date: 09/05/2024
+ms.date: 02/20/2025
 author: mrbullwinkle
 ms.author: mbullwin
 ---
 
 
-# Fine-tuning and function calling
+# Fine-tuning and tool calling
 
-Models that use the chat completions API support [function calling](../how-to/function-calling.md). Unfortunately, functions defined in your chat completion calls don't always perform as expected. Fine-tuning your model with function calling examples can improve model output by enabling you to:
+Models that use the chat completions API support [tool calling](../how-to/function-calling.md). Unfortunately, functions defined in your chat completion calls don't always perform as expected. Fine-tuning your model with tool calling examples can improve model output by enabling you to:
 
 * Get similarly formatted responses even when the full function definition isn't present. (Allowing you to potentially save money on prompt tokens.)
 * Get more accurate and consistent outputs.
 
-## Constructing a training file
+> [!NOTE]
+> `function_call` and `functions` have been deprecated in favor of `tools`. 
+> It is recommended to use the `tools` parameter instead.
+
+
+## Tool calling (recommended)
+### Constructing a training file
+
+When constructing a training file of tool calling examples, you would take a function definition like this:
+
+```json
+{
+    "messages": [
+        { "role": "user", "content": "What is the weather in San Francisco?" },
+        {
+            "role": "assistant",
+            "tool_calls": [
+                {
+                    "id": "call_id",
+                    "type": "function",
+                    "function": {
+                        "name": "get_current_weather",
+                        "arguments": "{\"location\": \"San Francisco, USA\", \"format\": \"celsius\"}"
+                    }
+                }
+            ]
+        }
+    ],
+    "tools": [
+        {
+            "type": "function",
+            "function": {
+                "name": "get_current_weather",
+                "description": "Get the current weather",
+                "parameters": {
+                    "type": "object",
+                    "properties": {
+                        "location": {
+                            "type": "string",
+                            "description": "The city and country, eg. San Francisco, USA"
+                        },
+                        "format": { "type": "string", "enum": ["celsius", "fahrenheit"] }
+                    },
+                    "required": ["location", "format"]
+                }
+            }
+        }
+    ]
+}
+```
+
+And express the information as a single line within your `.jsonl` training file as below:
+
+```jsonl
+{"messages":[{"role":"user","content":"What is the weather in San Francisco?"},{"role":"assistant","tool_calls":[{"id":"call_id","type":"function","function":{"name":"get_current_weather","arguments":"{\"location\": \"San Francisco, USA\", \"format\": \"celsius\"}"}}]}],"tools":[{"type":"function","function":{"name":"get_current_weather","description":"Get the current weather","parameters":{"type":"object","properties":{"location":{"type":"string","description":"The city and country, eg. San Francisco, USA"},"format":{"type":"string","enum":["celsius","fahrenheit"]}},"required":["location","format"]}}}]}
+```
+
+As with all fine-tuning training your example file requires at least 10 examples.
+
+### Optimize for cost
+
+OpenAI recommends that if you're trying to optimize to use fewer prompt tokens post fine-tuning your model on the full function definitions you can experiment with:
+
+* Omit function and parameter descriptions: remove the description field from function and parameters.
+* Omit parameters: remove the entire properties field from the parameters object.
+* Omit function entirely: remove the entire function object from the functions array.
+
+### Optimize for quality
+
+Alternatively, if you're trying to improve the quality of the tool calling output, it's recommended that the function definitions present in the fine-tuning training dataset and subsequent chat completion calls remain identical.
+
+### Customize model responses to function outputs
+
+Fine-tuning based on tool calling examples can also be used to improve the model's response to function outputs. To accomplish this, you include examples consisting of function response messages and assistant response messages where the function response is interpreted and put into context by the assistant.
+
+```json
+{
+    "messages": [
+        {"role": "user", "content": "What is the weather in San Francisco?"},
+        {"role": "assistant", "tool_calls": [{"id": "call_id", "type": "function", "function": {"name": "get_current_weather", "arguments": "{\"location\": \"San Francisco, USA\", \"format\": \"celsius\"}"}}]}
+        {"role": "tool", "tool_call_id": "call_id", "content": "21.0"},
+        {"role": "assistant", "content": "It is 21 degrees celsius in San Francisco, CA"}
+    ],
+    "tools": [] // same as before
+}
+```
+
+As with the example before, this example is artificially expanded for readability. The actual entry in the `.jsonl` training file would be a single line:
+
+```jsonl
+{"messages":[{"role":"user","content":"What is the weather in San Francisco?"},{"role":"assistant","tool_calls":[{"id":"call_id","type":"function","function":{"name":"get_current_weather","arguments":"{\"location\": \"San Francisco, USA\", \"format\": \"celsius\"}"}}]},{"role":"tool","tool_call_id":"call_id","content":"21.0"},{"role":"assistant","content":"It is 21 degrees celsius in San Francisco, CA"}],"tools":[]}
+```
+
+## Function calling
+### Constructing a training file
 
 When constructing a training file of function calling examples, you would take a function definition like this:
 
@@ -51,19 +145,19 @@ And express the information as a single line within your `.jsonl` training file
 
 As with all fine-tuning training your example file requires at least 10 examples.
 
-## Optimize for cost
+### Optimize for cost
 
 OpenAI recommends that if you're trying to optimize to use fewer prompt tokens post fine-tuning your model on the full function definitions you can experiment with:
 
 * Omit function and parameter descriptions: remove the description field from function and parameters.
 * Omit parameters: remove the entire properties field from the parameters object.
 * Omit function entirely: remove the entire function object from the functions array.
 
-## Optimize for quality
+### Optimize for quality
 
 Alternatively, if you're trying to improve the quality of the function calling output, it's recommended that the function definitions present in the fine-tuning training dataset and subsequent chat completion calls remain identical.
 
-## Customize model responses to function outputs
+### Customize model responses to function outputs
 
 Fine-tuning based on function calling examples can also be used to improve the model's response to function outputs. To accomplish this, you include examples consisting of function response messages and assistant response messages where the function response is interpreted and put into context by the assistant.
 
@@ -85,6 +179,7 @@ As with the example before, this example is artificially expanded for readabilit
 {"messages": [{"role": "user", "content": "What is the weather in San Francisco?"}, {"role": "assistant", "function_call": {"name": "get_current_weather", "arguments": "{\"location\": \"San Francisco, USA\", \"format\": \"celcius\"}"}}, {"role": "function", "name": "get_current_weather", "content": "21.0"}, {"role": "assistant", "content": "It is 21 degrees celsius in San Francisco, CA"}], "functions": []}
 ```
 
+
 ## Next steps
 
 * [Function calling fine-tuning scenarios](https://techcommunity.microsoft.com/t5/ai-azure-ai-services-blog/fine-tuning-with-function-calling-on-azure-openai-service/ba-p/4065968).

@@ -208,5 +208,6 @@ Possible reasons why the user may **not** have permissions:
 
 ## Next steps
 
+- [Get started with the Azure OpenAI security building block](/azure/developer/ai/get-started-securing-your-ai-app?tabs=github-codespaces&pivots=python)
 - Learn more about [Azure-role based access control (Azure RBAC)](/azure/role-based-access-control/).
 - Also check out[assign Azure roles using the Azure portal](/azure/role-based-access-control/role-assignments-portal).

@@ -6,7 +6,7 @@ manager: nitinme
 ms.service: azure-ai-openai
 ms.topic: how-to
 ms.custom: references_regions
-ms.date: 02/24/2025
+ms.date: 02/25/2025
 author: mrbullwinkle
 ms.author: mbullwin
 recommendations: false
@@ -20,7 +20,7 @@ Stored completions allow you to capture the conversation history from chat compl
 
 ### API support
 
-Support first added in `2024-10-01-preview`
+Support first added in `2024-10-01-preview`, use `2025-02-01-preview` or later for access to the latest features.
 
 ### Deployment type
 
@@ -38,7 +38,6 @@ Currently only `Standard` model deployments support stored completions.
 
 To enable stored completions for your Azure OpenAI deployment set the `store` parameter to `True`. Use the `metadata` parameter to enrich your stored completion dataset with additional information.
 
-
 # [Python (Microsoft Entra ID)](#tab/python-secure)
 
 ```python
@@ -53,7 +52,7 @@ token_provider = get_bearer_token_provider(
 client = AzureOpenAI(
   azure_endpoint = os.getenv("AZURE_OPENAI_ENDPOINT"), 
   azure_ad_token_provider=token_provider,
-  api_version="2024-10-01-preview"
+  api_version="2025-02-01-preview"
 )
 
 completion = client.chat.completions.create(
@@ -85,7 +84,7 @@ from openai import AzureOpenAI
     
 client = AzureOpenAI(
     api_key=os.getenv("AZURE_OPENAI_API_KEY"),  
-    api_version="2024-10-01-preview",
+    api_version="2025-02-01-preview",
     azure_endpoint = os.getenv("AZURE_OPENAI_ENDPOINT")
     )
 
@@ -105,6 +104,149 @@ ompletion = client.chat.completions.create(
 
 print(completion.choices[0].message)
 ```
+
+# [REST API](#tab/rest-api)
+
+### Microsoft Entra ID
+
+```bash
+curl $AZURE_OPENAI_ENDPOINT/openai/deployments/gpt-4o/chat/completions?api-version=2025-02-01-preview \
+  -H "Content-Type: application/json" \
+  -H "Authorization: Bearer $AZURE_OPENAI_AUTH_TOKEN" \
+  -d '{
+    "model": "gpt-4o",
+    "store": True,
+    "messages": [
+      {
+        "role": "system",
+        "content": "You are a helpful assistant."
+      },
+      {
+        "role": "user",
+        "content": "Hello!"
+      }
+    ]
+  }'
+```
+
+### API Key
+
+```bash
+curl $AZURE_OPENAI_ENDPOINT/openai/deployments/gpt-4o/chat/completions?api-version=2025-02-01-preview \
+  -H "Content-Type: application/json" \
+  -H "api-key: $AZURE_OPENAI_API_KEY" \
+  -d '{
+    "model": "gpt-4o",
+    "store": True,
+    "messages": [
+      {
+        "role": "system",
+        "content": "You are a helpful assistant."
+      },
+      {
+        "role": "user",
+        "content": "Hello!"
+      }
+    ]
+  }'
+```
+
+# [Output](#tab/output)
+
+```json
+{
+  "id": "chatcmpl-B4eQ716S5wGUyFpGgX2MXnJEC5AW5",
+  "choices": [
+    {
+      "finish_reason": "stop",
+      "index": 0,
+      "logprobs": null,
+      "message": {
+        "content": "Ensemble methods enhance machine learning performance by combining multiple models to create a more robust and accurate predictor. The key techniques include:\n\n1. **Bagging (Bootstrap Aggregating)**: Involves training multiple models on random subsets of the data to reduce variance and overfitting. A popular method within bagging is Random Forests, which build numerous decision trees using random subsets of features and data samples.\n\n2. **Boosting**: Focuses on sequentially training models, where each new model attempts to correct the errors made by previous ones. Gradient Boosting is a common boosting technique that builds trees sequentially, concentrating on the mistakes of earlier trees to improve accuracy.\n\n3. **Stacking**: Uses a meta-model to combine predictions from various base models, leveraging their strengths to enhance overall predictions.\n\nThese ensemble methods generally outperform individual models because they effectively handle overfitting, reduce variance, and capture diverse aspects of the data. In practical applications, they are valued for their ability to improve model accuracy and stability.",
+        "refusal": null,
+        "role": "assistant",
+        "audio": null,
+        "function_call": null,
+        "tool_calls": null
+      },
+      "content_filter_results": {
+        "hate": {
+          "filtered": false,
+          "severity": "safe"
+        },
+        "protected_material_code": {
+          "filtered": false,
+          "detected": false
+        },
+        "protected_material_text": {
+          "filtered": false,
+          "detected": false
+        },
+        "self_harm": {
+          "filtered": false,
+          "severity": "safe"
+        },
+        "sexual": {
+          "filtered": false,
+          "severity": "safe"
+        },
+        "violence": {
+          "filtered": false,
+          "severity": "safe"
+        }
+      }
+    }
+  ],
+  "created": 1740448387,
+  "model": "gpt-4o-2024-08-06",
+  "object": "chat.completion",
+  "service_tier": null,
+  "system_fingerprint": "fp_b705f0c291",
+  "usage": {
+    "completion_tokens": 205,
+    "prompt_tokens": 157,
+    "total_tokens": 362,
+    "completion_tokens_details": {
+      "accepted_prediction_tokens": 0,
+      "audio_tokens": 0,
+      "reasoning_tokens": 0,
+      "rejected_prediction_tokens": 0
+    },
+    "prompt_tokens_details": {
+      "audio_tokens": 0,
+      "cached_tokens": 0
+    }
+  },
+  "prompt_filter_results": [
+    {
+      "prompt_index": 0,
+      "content_filter_results": {
+        "hate": {
+          "filtered": false,
+          "severity": "safe"
+        },
+        "jailbreak": {
+          "filtered": false,
+          "detected": false
+        },
+        "self_harm": {
+          "filtered": false,
+          "severity": "safe"
+        },
+        "sexual": {
+          "filtered": false,
+          "severity": "safe"
+        },
+        "violence": {
+          "filtered": false,
+          "severity": "safe"
+        }
+      }
+    }
+  ]
+}
+```
+
 ---
 
 Once stored completions are enabled for an Azure OpenAI deployment, they'll begin to show up in the [Azure AI Foundry portal](https://oai.azure.com) in the **Stored Completions** pane.
@@ -161,6 +303,529 @@ Stored completions can be used as a dataset for running evaluations.
 
 To learn more about evaluation see, [getting started with evaluations](./evaluations.md)
 
+## Stored completions API
+
+To access the stored completions API commands you may need to upgrade your version of the OpenAI library.
+
+```cmd
+pip install --upgrade openai
+```
+
+### List stored completions
+
+# [Python (Microsoft Entra ID)](#tab/python-secure)
+
+Additional parameters:
+
+* `metadata`: Filter by the key/value pair in the stored completions
+* `after`: Identifier for the last stored completion message from the previous pagination request.
+* `limit`: Number of stored completions messages to retrieve.
+* `order`: Order of the results by index (ascending or descending).
+
+```python
+from openai import AzureOpenAI
+from azure.identity import DefaultAzureCredential, get_bearer_token_provider
+
+token_provider = get_bearer_token_provider(
+    DefaultAzureCredential(), "https://cognitiveservices.azure.com/.default"
+)
+
+client = AzureOpenAI(
+  azure_endpoint = "https://YOUR-RESOURCE-NAME.openai.azure.com", 
+  azure_ad_token_provider=token_provider,
+  api_version="2025-02-01-preview"
+)
+
+response = client.chat.completions.list()
+
+print(response.model_dump_json(indent=2))
+```
+
+# [Python (API Key)](#tab/python-key)
+
+```python
+from openai import AzureOpenAI
+
+client = AzureOpenAI(
+  azure_endpoint = "https://YOUR-RESOURCE-NAME.openai.azure.com", 
+  api_key=os.getenv("AZURE_OPENAI_API_KEY"), 
+  api_version="2025-02-01-preview"
+)
+
+response = client.chat.completions.list()
+
+print(response.model_dump_json(indent=2))
+```
+
+# [REST API](#tab/rest-api)
+
+### Microsoft Entra ID
+
+```bash
+curl https://YOUR-RESOURCE-NAME.openai.azure.com/openai/chat/completions?api-version=2025-02-01-preview \
+  -H "Content-Type: application/json" \
+  -H "Authorization: Bearer $AZURE_OPENAI_AUTH_TOKEN" \
+```
+
+### API Key
+
+```bash
+curl https://YOUR-RESOURCE-NAME.openai.azure.com/openai/chat/completions?api-version=2025-02-01-preview \
+  -H "Content-Type: application/json" \
+  -H "api-key: $AZURE_OPENAI_API_KEY" \
+```
+
+# [Output](#tab/output)
+
+```json
+{
+  "data": [
+    {
+      "id": "chatcmpl-A1bC2dE3fH4iJ5kL6mN7oP8qR9sT0u",
+      "choices": [
+        {
+          "finish_reason": null,
+          "index": 0,
+          "logprobs": null,
+          "message": {
+            "content": "Ensemble methods enhance machine learning performance by combining multiple models to create a more robust and accurate predictor. The key techniques include:\n\n1. **Bagging (Bootstrap Aggregating):** This involves training models on random subsets of the data to reduce variance and prevent overfitting. Random Forests, a popular bagging method, build multiple decision trees using random feature subsets, leading to robust predictions.\n\n2. **Boosting:** This sequential approach trains models to correct the errors of their predecessors, thereby focusing on difficult-to-predict data points. Gradient Boosting is a common implementation that sequentially builds decision trees, each improving upon the prediction errors of the previous ones.\n\n3. **Stacking:** This technique uses a meta-model to combine the predictions of multiple base models, leveraging their diverse strengths to enhance overall prediction accuracy.\n\nThe practical implications of ensemble methods include achieving superior model performance compared to single models by capturing various data patterns and reducing overfitting and variance. These methods are widely used in applications where high accuracy and model reliability are critical.",
+            "refusal": null,
+            "role": "assistant",
+            "audio": null,
+            "function_call": null,
+            "tool_calls": null
+          }
+        }
+      ],
+      "created": 1740447656,
+      "model": "gpt-4o-2024-08-06",
+      "object": null,
+      "service_tier": null,
+      "system_fingerprint": "fp_b705f0c291",
+      "usage": {
+        "completion_tokens": 208,
+        "prompt_tokens": 157,
+        "total_tokens": 365,
+        "completion_tokens_details": null,
+        "prompt_tokens_details": null
+      },
+      "request_id": "0000aaaa-11bb-cccc-dd22-eeeeee333333",
+      "seed": -430976584126747957,
+      "top_p": 1,
+      "temperature": 1,
+      "presence_penalty": 0,
+      "frequency_penalty": 0,
+      "metadata": {
+        "user": "admin",
+        "category": "docs-test"
+      }
+    }
+  ],
+  "has_more": false,
+  "object": "list",
+  "total": 1,
+  "first_id": "chatcmpl-A1bC2dE3fH4iJ5kL6mN7oP8qR9sT0u",
+  "last_id": "chatcmpl-A1bC2dE3fH4iJ5kL6mN7oP8qR9sT0u"
+}
+```
+
+---
+
+### Get stored completion
+
+Get stored completion by ID.
+
+# [Python (Microsoft Entra ID)](#tab/python-secure)
+
+```python
+from openai import AzureOpenAI
+from azure.identity import DefaultAzureCredential, get_bearer_token_provider
+
+token_provider = get_bearer_token_provider(
+    DefaultAzureCredential(), "https://cognitiveservices.azure.com/.default"
+)
+
+client = AzureOpenAI(
+  azure_endpoint = "https://YOUR-RESOURCE-NAME.openai.azure.com/", 
+  azure_ad_token_provider=token_provider,
+  api_version="2025-02-01-preview"
+)
+
+response = client.chat.completions.retrieve("chatcmpl-A1bC2dE3fH4iJ5kL6mN7oP8qR9sT0u")
+
+print(response.model_dump_json(indent=2))
+```
+
+# [Python (API Key)](#tab/python-key)
+
+```python
+from openai import AzureOpenAI
+
+client = AzureOpenAI(
+  azure_endpoint = "https://YOUR-RESOURCE-NAME.openai.azure.com", 
+  api_key=os.getenv("AZURE_OPENAI_API_KEY"), 
+  api_version="2025-02-01-preview"
+)
+
+response = client.chat.completions.retrieve("chatcmpl-A1bC2dE3fH4iJ5kL6mN7oP8qR9sT0u")
+
+print(response.model_dump_json(indent=2))
+```
+
+# [REST API](#tab/rest-api)
+
+### Microsoft Entra ID
+
+```bash
+curl https://YOUR-RESOURCE-NAME.openai.azure.com/openai/chat/completions/chatcmpl-A1bC2dE3fH4iJ5kL6mN7oP8qR9sT0u?api-version=2025-02-01-preview \
+  -H "Content-Type: application/json" \
+  -H "Authorization: Bearer $AZURE_OPENAI_AUTH_TOKEN" \
+```
+
+### API Key
+
+```bash
+curl https://YOUR-RESOURCE-NAME.openai.azure.com/openai/chat/completions/chatcmpl-A1bC2dE3fH4iJ5kL6mN7oP8qR9sT0u?api-version=2025-02-01-preview \
+  -H "Content-Type: application/json" \
+  -H "api-key: $AZURE_OPENAI_API_KEY" \
+```
+
+# [Output](#tab/output)
+
+```json
+{
+  "id": "chatcmpl-A1bC2dE3fH4iJ5kL6mN7oP8qR9sT0u",
+  "choices": [
+    {
+      "finish_reason": null,
+      "index": 0,
+      "logprobs": null,
+      "message": {
+        "content": "Ensemble methods enhance machine learning performance by combining multiple models to create a more robust and accurate predictor. The key techniques include:\n\n1. **Bagging (Bootstrap Aggregating):** This involves training models on random subsets of the data to reduce variance and prevent overfitting. Random Forests, a popular bagging method, build multiple decision trees using random feature subsets, leading to robust predictions.\n\n2. **Boosting:** This sequential approach trains models to correct the errors of their predecessors, thereby focusing on difficult-to-predict data points. Gradient Boosting is a common implementation that sequentially builds decision trees, each improving upon the prediction errors of the previous ones.\n\n3. **Stacking:** This technique uses a meta-model to combine the predictions of multiple base models, leveraging their diverse strengths to enhance overall prediction accuracy.\n\nThe practical implications of ensemble methods include achieving superior model performance compared to single models by capturing various data patterns and reducing overfitting and variance. These methods are widely used in applications where high accuracy and model reliability are critical.",
+        "refusal": null,
+        "role": "assistant",
+        "audio": null,
+        "function_call": null,
+        "tool_calls": null
+      }
+    }
+  ],
+  "created": 1740447656,
+  "model": "gpt-4o-2024-08-06",
+  "object": "chat.completion",
+  "service_tier": null,
+  "system_fingerprint": "fp_b705f0c291",
+  "usage": {
+    "completion_tokens": 208,
+    "prompt_tokens": 157,
+    "total_tokens": 365,
+    "completion_tokens_details": null,
+    "prompt_tokens_details": null
+  },
+  "request_id": "0000aaaa-11bb-cccc-dd22-eeeeee333333",
+  "seed": -430976584126747957,
+  "top_p": 1,
+  "temperature": 1,
+  "presence_penalty": 0,
+  "frequency_penalty": 0,
+  "metadata": {
+    "user": "admin",
+    "category": "docs-test"
+  }
+}
+```
+
+---
+
+### Get stored chat completion messages
+
+Additional parameters:
+
+* `after`: Identifier for the last stored completion message from the previous pagination request.
+* `limit`: Number of stored completions messages to retrieve.
+* `order`: Order of the results by index (ascending or descending).
+
+# [Python (Microsoft Entra ID)](#tab/python-secure)
+
+```python
+from openai import AzureOpenAI
+from azure.identity import DefaultAzureCredential, get_bearer_token_provider
+
+token_provider = get_bearer_token_provider(
+    DefaultAzureCredential(), "https://cognitiveservices.azure.com/.default"
+)
+
+client = AzureOpenAI(
+  azure_endpoint = "https://YOUR-RESOURCE-NAME.openai.azure.com/", 
+  azure_ad_token_provider=token_provider,
+  api_version="2025-02-01-preview"
+)
+
+response = client.chat.completions.messages.list("chatcmpl-A1bC2dE3fH4iJ5kL6mN7oP8qR9sT0u", limit=2)
+
+print(response.model_dump_json(indent=2))
+```
+
+# [Python (API Key)](#tab/python-key)
+
+```python
+from openai import AzureOpenAI
+
+client = AzureOpenAI(
+  azure_endpoint = "https://YOUR-RESOURCE-NAME.openai.azure.com", 
+  api_key=os.getenv("AZURE_OPENAI_API_KEY"), 
+  api_version="2025-02-01-preview"
+)
+
+response = client.chat.completions.messages.list("chatcmpl-A1bC2dE3fH4iJ5kL6mN7oP8qR9sT0u", limit=2)
+
+print(response.model_dump_json(indent=2))
+```
+
+# [REST API](#tab/rest-api)
+
+### Microsoft Entra ID
+
+```bash
+curl https://YOUR-RESOURCE-NAME.openai.azure.com/openai/chat/completions/chatcmpl-A1bC2dE3fH4iJ5kL6mN7oP8qR9sT0u/messages?api-version=2025-02-01-preview \
+  -H "Content-Type: application/json" \
+  -H "Authorization: Bearer $AZURE_OPENAI_AUTH_TOKEN" \
+```
+
+### API Key
+
+```bash
+curl https://YOUR-RESOURCE-NAME.openai.azure.com/openai/chat/completions/chatcmpl-A1bC2dE3fH4iJ5kL6mN7oP8qR9sT0u/messages?api-version=2025-02-01-preview \
+  -H "Content-Type: application/json" \
+  -H "api-key: $AZURE_OPENAI_API_KEY" \
+```
+
+# [Output](#tab/output)
+
+```json
+{
+  "data": [
+    {
+      "content": "Provide a clear and concise summary of the technical content, highlighting key concepts and their relationships. Focus on the main ideas and practical implications.",
+      "refusal": null,
+      "role": "system",
+      "audio": null,
+      "function_call": null,
+      "tool_calls": null,
+      "id": "chatcmpl-A1bC2dE3fH4iJ5kL6mN7oP8qR9sT0u-0"
+    },
+    {
+      "content": "Ensemble methods combine multiple machine learning models to create a more robust and accurate predictor. Common techniques include bagging (training models on random subsets of data), boosting (sequentially training models to correct previous errors), and stacking (using a meta-model to combine base model predictions). Random Forests, a popular bagging method, create multiple decision trees using random feature subsets. Gradient Boosting builds trees sequentially, with each tree focusing on correcting the errors of previous trees. These methods often achieve better performance than single models by reducing overfitting and variance while capturing different aspects of the data.",
+      "refusal": null,
+      "role": "user",
+      "audio": null,
+      "function_call": null,
+      "tool_calls": null,
+      "id": "chatcmpl-A1bC2dE3fH4iJ5kL6mN7oP8qR9sT0u-1"
+    }
+  ],
+  "has_more": false,
+  "object": "list",
+  "total": 2,
+  "first_id": "chatcmpl-A1bC2dE3fH4iJ5kL6mN7oP8qR9sT0u-0",
+  "last_id": "chatcmpl-A1bC2dE3fH4iJ5kL6mN7oP8qR9sT0u-1"
+}
+```
+
+---
+
+### Update stored chat completion
+
+Add metadata key:value pairs to an existing stored completion.
+
+# [Python (Microsoft Entra ID)](#tab/python-secure)
+
+```python
+from openai import AzureOpenAI
+from azure.identity import DefaultAzureCredential, get_bearer_token_provider
+
+token_provider = get_bearer_token_provider(
+    DefaultAzureCredential(), "https://cognitiveservices.azure.com/.default"
+)
+
+client = AzureOpenAI(
+  azure_endpoint = "https://YOUR-RESOURCE-NAME.openai.azure.com/", 
+  azure_ad_token_provider=token_provider,
+  api_version="2025-02-01-preview"
+)
+
+response = client.chat.completions.update(
+    "chatcmpl-C2dE3fH4iJ5kL6mN7oP8qR9sT0uV1w",
+    metadata={"fizz": "buzz"}
+)
+
+print(response.model_dump_json(indent=2))
+```
+
+# [Python (API Key)](#tab/python-key)
+
+```python
+from openai import AzureOpenAI
+
+client = AzureOpenAI(
+  azure_endpoint = "https://YOUR-RESOURCE-NAME.openai.azure.com", 
+  api_key=os.getenv("AZURE_OPENAI_API_KEY"), 
+  api_version="2025-02-01-preview"
+)
+
+response = client.chat.completions.update(
+    "chatcmpl-C2dE3fH4iJ5kL6mN7oP8qR9sT0uV1w",
+    metadata={"fizz": "buzz"}
+)
+
+print(response.model_dump_json(indent=2))
+```
+
+# [REST API](#tab/rest-api)
+
+### Microsoft Entra ID
+
+```bash
+curl -X https://YOUR-RESOURCE-NAME.openai.azure.com/openai/chat/completions/chatcmpl-A1bC2dE3fH4iJ5kL6mN7oP8qR9sT0u?api-version=2025-02-01-preview \
+  -H "Content-Type: application/json" \
+  -H "Authorization: Bearer $AZURE_OPENAI_AUTH_TOKEN"
+  -d '{
+    "metadata": {
+      "fizz": "buzz"
+    }
+  }' 
+```
+
+### API Key
+
+```bash
+curl -X https://YOUR-RESOURCE-NAME.openai.azure.com/openai/chat/completions/chatcmpl-A1bC2dE3fH4iJ5kL6mN7oP8qR9sT0u?api-version=2025-02-01-preview \
+  -H "Content-Type: application/json" \
+  -H "api-key: $AZURE_OPENAI_API_KEY" 
+  -d '{
+    "metadata": {
+      "fizz": "buzz"
+    }
+  }'
+```
+
+# [Output](#tab/output)
+
+```json
+  "id": "chatcmpl-A1bC2dE3fH4iJ5kL6mN7oP8qR9sT0u",
+  "choices": [
+    {
+      "finish_reason": null,
+      "index": 0,
+      "logprobs": null,
+      "message": {
+        "content": "Ensemble methods enhance machine learning performance by combining multiple models to create a more robust and accurate predictor. The key techniques include:\n\n1. **Bagging (Bootstrap Aggregating):** This involves training models on random subsets of the data to reduce variance and prevent overfitting. Random Forests, a popular bagging method, build multiple decision trees using random feature subsets, leading to robust predictions.\n\n2. **Boosting:** This sequential approach trains models to correct the errors of their predecessors, thereby focusing on difficult-to-predict data points. Gradient Boosting is a common implementation that sequentially builds decision trees, each improving upon the prediction errors of the previous ones.\n\n3. **Stacking:** This technique uses a meta-model to combine the predictions of multiple base models, leveraging their diverse strengths to enhance overall prediction accuracy.\n\nThe practical implications of ensemble methods include achieving superior model performance compared to single models by capturing various data patterns and reducing overfitting and variance. These methods are widely used in applications where high accuracy and model reliability are critical.",
+        "refusal": null,
+        "role": "assistant",
+        "audio": null,
+        "function_call": null,
+        "tool_calls": null
+      }
+    }
+  ],
+  "created": 1740447656,
+  "model": "gpt-4o-2024-08-06",
+  "object": "chat.completion",
+  "service_tier": null,
+  "system_fingerprint": "fp_b705f0c291",
+  "usage": {
+    "completion_tokens": 208,
+    "prompt_tokens": 157,
+    "total_tokens": 365,
+    "completion_tokens_details": null,
+    "prompt_tokens_details": null
+  },
+  "request_id": "0000aaaa-11bb-cccc-dd22-eeeeee333333",
+  "seed": -430976584126747957,
+  "top_p": 1,
+  "temperature": 1,
+  "presence_penalty": 0,
+  "frequency_penalty": 0,
+  "metadata": {
+    "user": "admin",
+    "category": "docs-test"
+    "fizz": "buzz"
+  }
+}
+```
+
+---
+
+### Delete stored chat completion
+
+Delete stored completion by completion ID.
+
+### Microsoft Entra ID
+
+# [Python (Microsoft Entra ID)](#tab/python-secure)
+
+```python
+from openai import AzureOpenAI
+from azure.identity import DefaultAzureCredential, get_bearer_token_provider
+
+token_provider = get_bearer_token_provider(
+    DefaultAzureCredential(), "https://cognitiveservices.azure.com/.default"
+)
+
+client = AzureOpenAI(
+  azure_endpoint = "https://YOUR-RESOURCE-NAME.openai.azure.com/", 
+  azure_ad_token_provider=token_provider,
+  api_version="2025-02-01-preview"
+)
+
+response = client.chat.completions.delete("chatcmpl-A1bC2dE3fH4iJ5kL6mN7oP8qR9sT0u")
+
+print(response.model_dump_json(indent=2))
+
+```
+
+# [Python (API Key)](#tab/python-key)
+
+```python
+from openai import AzureOpenAI
+
+client = AzureOpenAI(
+  azure_endpoint = "https://YOUR-RESOURCE-NAME.openai.azure.com", 
+  api_key=os.getenv("AZURE_OPENAI_API_KEY"), 
+  api_version="2025-02-01-preview"
+)
+
+response = client.chat.completions.delete("chatcmpl-A1bC2dE3fH4iJ5kL6mN7oP8qR9sT0u")
+
+print(response.model_dump_json(indent=2))
+```
+
+# [REST API](#tab/rest-api)
+
+```bash
+curl -X DELETE -D - https://YOUR-RESOURCE-NAME.openai.azure.com/openai/chat/completions/chatcmpl-A1bC2dE3fH4iJ5kL6mN7oP8qR9sT0u?api-version=2025-02-01-preview \
+  -H "Content-Type: application/json" \
+  -H "Authorization: Bearer $AZURE_OPENAI_AUTH_TOKEN"
+```
+
+### API Key
+
+```bash
+curl -X DELETE -D - https://YOUR-RESOURCE-NAME.openai.azure.com/openai/chat/completions/chatcmpl-A1bC2dE3fH4iJ5kL6mN7oP8qR9sT0u?api-version=2025-02-01-preview \
+  -H "Content-Type: application/json" \
+  -H "api-key: $AZURE_OPENAI_API_KEY" 
+```
+
+# [Output](#tab/output)
+
+```json
+"id"• "chatcmp1-A1bC2dE3fH4iJ5kL6mN7oP8qR9sT0u", 
+"deleted": true, 
+"object": "chat. completion. deleted" 
+```
+
+---
+
 ## Troubleshooting
 
 ### Do I need special permissions to use stored completions?

@@ -33,24 +33,17 @@ For the recommended keyless authentication with Microsoft Entra ID, you need to:
 1. Create a new folder `assistants-quickstart` to contain the application and open Visual Studio Code in that folder with the following command:
 
     ```shell
-    mkdir assistants-quickstart && code assistants-quickstart
+    mkdir assistants-quickstart && cd assistants-quickstart
     ```
     
 
 1. Create the `package.json` with the following command:
 
     ```shell
     npm init -y
-    ```
-
-1. Update the `package.json` to ECMAScript with the following command: 
-
-    ```shell
-    npm pkg set type=module
-    ```
-    
+    ```   
 
-1. Install the OpenAI Assistants client library for JavaScript with:
+1. Install the OpenAI client library for JavaScript with:
 
     ```console
     npm install openai
@@ -100,14 +93,14 @@ An individual assistant can access up to 128 tools including `code interpreter`,
     } = require("@azure/identity");
     
     // Get environment variables
-    const azureOpenAIEndpoint = process.env.AZURE_OPENAI_ENDPOINT;
-    const azureOpenAIDeployment = process.env.AZURE_OPENAI_DEPLOYMENT_NAME;
-    const azureOpenAIVersion = process.env.OPENAI_API_VERSION;
+    const azureOpenAIEndpoint = process.env.AZURE_OPENAI_ENDPOINT || "Your endpoint";
+    const azureOpenAIDeployment = process.env.AZURE_OPENAI_DEPLOYMENT_NAME || "Your deployment name";
+    const azureOpenAIVersion = process.env.OPENAI_API_VERSION || "A supported API version";
     
     // Check env variables
     if (!azureOpenAIEndpoint || !azureOpenAIDeployment || !azureOpenAIVersion) {
       throw new Error(
-        "Please ensure to set AZURE_OPENAI_DEPLOYMENT_NAME and AZURE_OPENAI_ENDPOINT in your environment variables."
+        "You need to set the endpoint, deployment name, and API version."
       );
     }
     
@@ -193,8 +186,6 @@ An individual assistant can access up to 128 tools including `code interpreter`,
     node index.js
     ```
 
-
-
 #### [API key](#tab/api-key)
 
 1. Create the `index.js` file with the following code:
@@ -203,15 +194,15 @@ An individual assistant can access up to 128 tools including `code interpreter`,
     const { AzureOpenAI } = require("openai");
     
     // Get environment variables
-    const azureOpenAIKey = process.env.AZURE_OPENAI_KEY;
-    const azureOpenAIEndpoint = process.env.AZURE_OPENAI_ENDPOINT;
-    const azureOpenAIDeployment = process.env.AZURE_OPENAI_DEPLOYMENT_NAME;
-    const azureOpenAIVersion = process.env.OPENAI_API_VERSION;
+    const azureOpenAIKey = process.env.AZURE_OPENAI_KEY || "Your API key";
+    const azureOpenAIEndpoint = process.env.AZURE_OPENAI_ENDPOINT || "Your endpoint";
+    const azureOpenAIDeployment = process.env.AZURE_OPENAI_DEPLOYMENT_NAME || "Your deployment name";
+    const azureOpenAIVersion = process.env.OPENAI_API_VERSION || "A supported API version";
     
     // Check env variables
     if (!azureOpenAIKey || !azureOpenAIEndpoint || !azureOpenAIDeployment || !azureOpenAIVersion) {
       throw new Error(
-        "Please set AZURE_OPENAI_KEY and AZURE_OPENAI_ENDPOINT and AZURE_OPENAI_DEPLOYMENT_NAME in your environment variables."
+        "You need to set the endpoint, deployment name, and API version."
       );
     }
     

@@ -34,7 +34,7 @@ For the recommended keyless authentication with Microsoft Entra ID, you need to:
 1. Create a new folder `assistants-quickstart` to contain the application and open Visual Studio Code in that folder with the following command:
 
     ```shell
-    mkdir assistants-quickstart && code assistants-quickstart
+    mkdir assistants-quickstart && cd assistants-quickstart
     ```
     
 
@@ -51,7 +51,7 @@ For the recommended keyless authentication with Microsoft Entra ID, you need to:
     ```
     
 
-1. Install the OpenAI Assistants client library for JavaScript with:
+1. Install the OpenAI client library for JavaScript with:
 
     ```console
     npm install openai
@@ -110,15 +110,15 @@ An individual assistant can access up to 128 tools including `code interpreter`,
     } from "@azure/identity";
     
     // Get environment variables
-    const azureOpenAIEndpoint = process.env.AZURE_OPENAI_ENDPOINT as string;
+    const azureOpenAIEndpoint = process.env.AZURE_OPENAI_ENDPOINT || "Your endpoint" as string;
     const azureOpenAIDeployment = process.env
-      .AZURE_OPENAI_DEPLOYMENT_NAME as string;
-    const openAIVersion = process.env.OPENAI_API_VERSION as string;
+      .AZURE_OPENAI_DEPLOYMENT_NAME  || "Your deployment name" as string;
+    const openAIVersion = process.env.OPENAI_API_VERSION || "A supported API version" as string;
     
     // Check env variables
     if (!azureOpenAIEndpoint || !azureOpenAIDeployment || !openAIVersion) {
       throw new Error(
-        "Please ensure to set AZURE_OPENAI_DEPLOYMENT_NAME and AZURE_OPENAI_ENDPOINT in your environment variables."
+        "You need to set the endpoint, deployment name, and API version."
       );
     }
     
@@ -186,8 +186,6 @@ An individual assistant can access up to 128 tools including `code interpreter`,
       }
     }
     ```
-    
-
 
 1. Create the `tsconfig.json` file to transpile the TypeScript code and copy the following code for ECMAScript.
 
@@ -222,8 +220,6 @@ An individual assistant can access up to 128 tools including `code interpreter`,
     node index.js
     ```
 
-
-
 #### [API key](#tab/typescript-key)
 
 1. Create the `index.ts` file with the following code:
@@ -240,16 +236,16 @@ An individual assistant can access up to 128 tools including `code interpreter`,
     import { Thread } from "openai/resources/beta/threads/threads";
     
     // Get environment variables
-    const azureOpenAIKey = process.env.AZURE_OPENAI_KEY as string;
-    const azureOpenAIEndpoint = process.env.AZURE_OPENAI_ENDPOINT as string;
+    const azureOpenAIKey = process.env.AZURE_OPENAI_KEY || "Your API key" as string;
+    const azureOpenAIEndpoint = process.env.AZURE_OPENAI_ENDPOINT || "Your endpoint" as string;
     const azureOpenAIDeployment = process.env
-      .AZURE_OPENAI_DEPLOYMENT_NAME as string;
-    const openAIVersion = process.env.OPENAI_API_VERSION as string;
+      .AZURE_OPENAI_DEPLOYMENT_NAME || "Your deployment name" as string;
+    const openAIVersion = process.env.OPENAI_API_VERSION || "A supported API version" as string;
     
     // Check env variables
     if (!azureOpenAIKey || !azureOpenAIEndpoint || !azureOpenAIDeployment || !openAIVersion) {
       throw new Error(
-        "Please set AZURE_OPENAI_KEY and AZURE_OPENAI_ENDPOINT and AZURE_OPENAI_DEPLOYMENT_NAME in your environment variables."
+        "You need to set the endpoint, deployment name, and API version."
       );
     }
     
@@ -314,7 +310,6 @@ An individual assistant can access up to 128 tools including `code interpreter`,
       }
     }
     ```
-    
 
 1. Create the `tsconfig.json` file to transpile the TypeScript code and copy the following code for ECMAScript.
 

@@ -29,7 +29,7 @@ For the recommended keyless authentication with Microsoft Entra ID, you need to:
 1. Create a new folder `audio-completions-quickstart` to contain the application and open Visual Studio Code in that folder with the following command:
 
     ```shell
-    mkdir audio-completions-quickstart && code audio-completions-quickstart
+    mkdir audio-completions-quickstart && cd audio-completions-quickstart
     ```
     
 1. Create the `package.json` with the following command:
@@ -38,13 +38,6 @@ For the recommended keyless authentication with Microsoft Entra ID, you need to:
     npm init -y
     ```
 
-1. Update the `package.json` to ECMAScript with the following command: 
-
-    ```shell
-    npm pkg set type=module
-    ```
-    
-
 1. Install the OpenAI client library for JavaScript with:
 
     ```console
@@ -83,9 +76,9 @@ For the recommended keyless authentication with Microsoft Entra ID, you need to:
     const azureADTokenProvider = getBearerTokenProvider(credential, scope);
     
     // Set environment variables or edit the corresponding values here.
-    const endpoint = process.env["AZURE_OPENAI_ENDPOINT"] || "AZURE_OPENAI_ENDPOINT";
-    const apiVersion = "2025-01-01-preview"; 
-    const deployment = "gpt-4o-mini-audio-preview"; 
+    const endpoint = process.env.AZURE_OPENAI_ENDPOINT || "AZURE_OPENAI_ENDPOINT";
+    const deployment = process.env.AZURE_OPENAI_DEPLOYMENT_NAME || "gpt-4o-mini-audio-preview"; 
+    const apiVersion = process.env.OPENAI_API_VERSION || "2025-01-01-preview"; 
     
     const client = new AzureOpenAI({ 
         endpoint, 
@@ -150,8 +143,8 @@ For the recommended keyless authentication with Microsoft Entra ID, you need to:
     const { writeFileSync } = require("node:fs");
     
     // Set environment variables or edit the corresponding values here.
-    const endpoint = process.env["AZURE_OPENAI_ENDPOINT"] || "AZURE_OPENAI_ENDPOINT";
-    const apiKey = process.env["AZURE_OPENAI_API_KEY"] || "AZURE_OPENAI_API_KEY";
+    const endpoint = process.env.AZURE_OPENAI_ENDPOINT || "AZURE_OPENAI_ENDPOINT";
+    const apiKey = process.env.AZURE_OPENAI_API_KEY || "AZURE_OPENAI_API_KEY";
     const apiVersion = "2025-01-01-preview"; 
     const deployment = "gpt-4o-mini-audio-preview"; 
     
@@ -229,7 +222,7 @@ The script generates an audio file named _dog.wav_ in the same directory as the
     const azureADTokenProvider = getBearerTokenProvider(credential, scope);
     
     // Set environment variables or edit the corresponding values here.
-    const endpoint = process.env["AZURE_OPENAI_ENDPOINT"] || "AZURE_OPENAI_ENDPOINT";
+    const endpoint = process.env.AZURE_OPENAI_ENDPOINT || "AZURE_OPENAI_ENDPOINT";
     const apiVersion = "2025-01-01-preview"; 
     const deployment = "gpt-4o-mini-audio-preview"; 
     
@@ -312,8 +305,8 @@ The script generates an audio file named _dog.wav_ in the same directory as the
     const { writeFileSync } = require("node:fs");
     
     // Set environment variables or edit the corresponding values here.
-    const endpoint = process.env["AZURE_OPENAI_ENDPOINT"] || "AZURE_OPENAI_ENDPOINT";
-    const apiKey = process.env["AZURE_OPENAI_API_KEY"] || "AZURE_OPENAI_API_KEY";
+    const endpoint = process.env.AZURE_OPENAI_ENDPOINT || "AZURE_OPENAI_ENDPOINT";
+    const apiKey = process.env.AZURE_OPENAI_API_KEY || "AZURE_OPENAI_API_KEY";
     const apiVersion = "2025-01-01-preview"; 
     const deployment = "gpt-4o-mini-audio-preview"; 
     
@@ -404,7 +397,7 @@ The script generates a transcript of the summary of the spoken audio input. It a
     const azureADTokenProvider = getBearerTokenProvider(credential, scope);
     
     // Set environment variables or edit the corresponding values here.
-    const endpoint = process.env["AZURE_OPENAI_ENDPOINT"] || "AZURE_OPENAI_ENDPOINT";
+    const endpoint = process.env.AZURE_OPENAI_ENDPOINT || "AZURE_OPENAI_ENDPOINT";
     const apiVersion = "2025-01-01-preview"; 
     const deployment = "gpt-4o-mini-audio-preview"; 
     
@@ -508,8 +501,8 @@ The script generates a transcript of the summary of the spoken audio input. It a
     const fs = require('fs').promises;
     
     // Set environment variables or edit the corresponding values here.
-    const endpoint = process.env["AZURE_OPENAI_ENDPOINT"] || "AZURE_OPENAI_ENDPOINT";
-    const apiKey = process.env["AZURE_OPENAI_API_KEY"] || "AZURE_OPENAI_API_KEY";
+    const endpoint = process.env.AZURE_OPENAI_ENDPOINT || "AZURE_OPENAI_ENDPOINT";
+    const apiKey = process.env.AZURE_OPENAI_API_KEY || "AZURE_OPENAI_API_KEY";
     const apiVersion = "2025-01-01-preview"; 
     const deployment = "gpt-4o-mini-audio-preview"; 
     

@@ -31,7 +31,7 @@ For the recommended keyless authentication with Microsoft Entra ID, you need to:
 1. Create a new folder `audio-completions-quickstart` to contain the application and open Visual Studio Code in that folder with the following command:
 
     ```shell
-    mkdir audio-completions-quickstart && code audio-completions-quickstart
+    mkdir audio-completions-quickstart && cd audio-completions-quickstart
     ```
     
 1. Create a virtual environment. If you already have Python 3.10 or higher installed, you can create a virtual environment using the following commands:

@@ -29,7 +29,7 @@ For the recommended keyless authentication with Microsoft Entra ID, you need to:
 1. Create a new folder `audio-completions-quickstart` to contain the application and open Visual Studio Code in that folder with the following command:
 
     ```shell
-    mkdir audio-completions-quickstart && code audio-completions-quickstart
+    mkdir audio-completions-quickstart && cd audio-completions-quickstart
     ```
     
 1. Create a virtual environment. If you already have Python 3.10 or higher installed, you can create a virtual environment using the following commands:

@@ -30,7 +30,7 @@ For the recommended keyless authentication with Microsoft Entra ID, you need to:
 1. Create a new folder `audio-completions-quickstart` to contain the application and open Visual Studio Code in that folder with the following command:
 
     ```shell
-    mkdir audio-completions-quickstart && code audio-completions-quickstart
+    mkdir audio-completions-quickstart && cd audio-completions-quickstart
     ```
     
 
@@ -82,9 +82,9 @@ For the recommended keyless authentication with Microsoft Entra ID, you need to:
       } from "@azure/identity";
     
     // Set environment variables or edit the corresponding values here.
-    const endpoint: string = process.env["AZURE_OPENAI_ENDPOINT"] || "AZURE_OPENAI_ENDPOINT";
-    const apiVersion: string = "2025-01-01-preview"; 
-    const deployment: string = "gpt-4o-mini-audio-preview"; 
+    const endpoint: string = process.env.AZURE_OPENAI_ENDPOINT || "AZURE_OPENAI_ENDPOINT";
+    const deployment: string = process.env.AZURE_OPENAI_DEPLOYMENT_NAME || "gpt-4o-mini-audio-preview"; 
+    const apiVersion: string = process.env.OPENAI_API_VERSION || "2025-01-01-preview"; 
     
     // Keyless authentication 
     const getClient = (): AzureOpenAI => {
@@ -180,8 +180,8 @@ For the recommended keyless authentication with Microsoft Entra ID, you need to:
     import { AzureOpenAI } from "openai/index.mjs";
     
     // Set environment variables or edit the corresponding values here.
-    const endpoint: string = process.env["AZURE_OPENAI_ENDPOINT"] || "AZURE_OPENAI_ENDPOINT";
-    const apiKey: string = process.env["AZURE_OPENAI_API_KEY"] || "AZURE_OPENAI_API_KEY";
+    const endpoint: string = process.env.AZURE_OPENAI_ENDPOINT || "AZURE_OPENAI_ENDPOINT";
+    const apiKey: string = process.env.AZURE_OPENAI_API_KEY || "AZURE_OPENAI_API_KEY";
     const apiVersion: string = "2025-01-01-preview"; 
     const deployment: string = "gpt-4o-mini-audio-preview"; 
     
@@ -280,7 +280,7 @@ The script generates an audio file named _dog.wav_ in the same directory as the
       } from "@azure/identity";
     
     // Set environment variables or edit the corresponding values here.
-    const endpoint: string = process.env["AZURE_OPENAI_ENDPOINT"] || "AZURE_OPENAI_ENDPOINT";
+    const endpoint: string = process.env.AZURE_OPENAI_ENDPOINT || "AZURE_OPENAI_ENDPOINT";
     const apiVersion: string = "2025-01-01-preview"; 
     const deployment: string = "gpt-4o-mini-audio-preview"; 
     
@@ -391,8 +391,8 @@ The script generates an audio file named _dog.wav_ in the same directory as the
     import { promises as fs } from 'fs';
     
     // Set environment variables or edit the corresponding values here.
-    const endpoint: string = process.env["AZURE_OPENAI_ENDPOINT"] || "AZURE_OPENAI_ENDPOINT";
-    const apiKey: string = process.env["AZURE_OPENAI_API_KEY"] || "AZURE_OPENAI_API_KEY";
+    const endpoint: string = process.env.AZURE_OPENAI_ENDPOINT || "AZURE_OPENAI_ENDPOINT";
+    const apiKey: string = process.env.AZURE_OPENAI_API_KEY || "AZURE_OPENAI_API_KEY";
     const apiVersion: string = "2025-01-01-preview"; 
     const deployment: string = "gpt-4o-mini-audio-preview"; 
     
@@ -503,7 +503,7 @@ The script generates a transcript of the summary of the spoken audio input. It a
       } from "@azure/identity";
     
     // Set environment variables or edit the corresponding values here.
-    const endpoint: string = process.env["AZURE_OPENAI_ENDPOINT"] || "AZURE_OPENAI_ENDPOINT";
+    const endpoint: string = process.env.AZURE_OPENAI_ENDPOINT || "AZURE_OPENAI_ENDPOINT";
     const apiVersion: string = "2025-01-01-preview"; 
     const deployment: string = "gpt-4o-mini-audio-preview"; 
     
@@ -635,8 +635,8 @@ The script generates a transcript of the summary of the spoken audio input. It a
     import { ChatCompletionMessageParam } from "openai/resources/index.mjs";
     
     // Set environment variables or edit the corresponding values here.
-    const endpoint: string = process.env["AZURE_OPENAI_ENDPOINT"] || "AZURE_OPENAI_ENDPOINT" as string;
-    const apiKey: string = process.env["AZURE_OPENAI_API_KEY"] || "AZURE_OPENAI_API_KEY";
+    const endpoint: string = process.env.AZURE_OPENAI_ENDPOINT || "AZURE_OPENAI_ENDPOINT" as string;
+    const apiKey: string = process.env.AZURE_OPENAI_API_KEY || "AZURE_OPENAI_API_KEY";
     const apiVersion: string = "2025-01-01-preview"; 
     const deployment: string = "gpt-4o-mini-audio-preview"; 
     

@@ -29,127 +29,144 @@ For the recommended keyless authentication with Microsoft Entra ID, you need to:
 - Install the [Azure CLI](/cli/azure/install-azure-cli) used for keyless authentication with Microsoft Entra ID.
 - Assign the `Cognitive Services User` role to your user account. You can assign roles in the Azure portal under **Access control (IAM)** > **Add role assignment**.
 
-## Retrieve resource information
+## Set up
+ 
+1. Create a new folder `chat-quickstart` to contain the application and open Visual Studio Code in that folder with the following command:
 
-[!INCLUDE [resource authentication](resource-authentication.md)]
+    ```shell
+    mkdir chat-quickstart && cd chat-quickstart
+    ```
 
-> [!CAUTION]
-> To use the recommended keyless authentication with the SDK, make sure that the `AZURE_OPENAI_API_KEY` environment variable isn't set. 
+1. Create the `package.json` with the following command:
 
+    ```shell
+    npm init -y
+    ```   
 
-## Create a Node application
+1. Install the OpenAI client library for JavaScript with:
 
-In a console window (such as cmd, PowerShell, or Bash), create a new directory for your app, and navigate to it. 
+    ```console
+    npm install openai
+    ```
 
-## Install the client library
+1. For the **recommended** passwordless authentication:
 
-Install the required packages for JavaScript with npm from within the context of your new directory:
+    ```console
+    npm install @azure/identity
+    ```
 
-```console
-npm install openai @azure/identity
-```
-
-Your app's _package.json_ file is updated with the dependencies.
+## Retrieve resource information
 
-## Create a sample application
+[!INCLUDE [resource authentication](resource-authentication.md)]
 
-Open a command prompt where you want the new project, and create a new file named ChatCompletion.js. Copy the following code into the ChatCompletion.js file.
+> [!CAUTION]
+> To use the recommended keyless authentication with the SDK, make sure that the `AZURE_OPENAI_API_KEY` environment variable isn't set. 
 
+## Create a sample application
 
 ## [Microsoft Entra ID](#tab/keyless)
 
-```javascript
-const { AzureOpenAI } = require("openai");
-const { 
-  DefaultAzureCredential, 
-  getBearerTokenProvider 
-} = require("@azure/identity");
-
-// You will need to set these environment variables or edit the following values
-const endpoint = process.env["AZURE_OPENAI_ENDPOINT"] || "<endpoint>";
-const apiVersion = "2024-05-01-preview";
-const deployment = "gpt-4o"; //This must match your deployment name.
-
-
-// keyless authentication    
-const credential = new DefaultAzureCredential();
-const scope = "https://cognitiveservices.azure.com/.default";
-const azureADTokenProvider = getBearerTokenProvider(credential, scope);
-
-async function main() {
-
-  const client = new AzureOpenAI({ endpoint, apiKey, azureADTokenProvider, deployment });
-  const result = await client.chat.completions.create({
-    messages: [
-    { role: "system", content: "You are a helpful assistant." },
-    { role: "user", content: "Does Azure OpenAI support customer managed keys?" },
-    { role: "assistant", content: "Yes, customer managed keys are supported by Azure OpenAI?" },
-    { role: "user", content: "Do other Azure AI services support this too?" },
-    ],
-    model: "",
-  });
-
-  for (const choice of result.choices) {
-    console.log(choice.message);
-  }
-}
-
-main().catch((err) => {
-  console.error("The sample encountered an error:", err);
-});
-
-module.exports = { main };
-```
-
-Run the script with the following command:
-
-```cmd
-node.exe ChatCompletion.js
-```
+1. Create the `index.js` file with the following code:
+    
+    ```javascript
+    const { AzureOpenAI } = require("openai");
+    const { 
+      DefaultAzureCredential, 
+      getBearerTokenProvider 
+    } = require("@azure/identity");
+    
+    // You will need to set these environment variables or edit the following values
+    const endpoint = process.env.AZURE_OPENAI_ENDPOINT || "Your endpoint";
+    const apiVersion = process.env.OPENAI_API_VERSION || "2024-05-01-preview";
+    const deployment = process.env.AZURE_OPENAI_DEPLOYMENT_NAME || "gpt-4o"; //This must match your deployment name.
+    
+    // keyless authentication    
+    const credential = new DefaultAzureCredential();
+    const scope = "https://cognitiveservices.azure.com/.default";
+    const azureADTokenProvider = getBearerTokenProvider(credential, scope);
+    
+    async function main() {
+    
+      const client = new AzureOpenAI({ endpoint, apiKey, azureADTokenProvider, deployment });
+      const result = await client.chat.completions.create({
+        messages: [
+        { role: "system", content: "You are a helpful assistant." },
+        { role: "user", content: "Does Azure OpenAI support customer managed keys?" },
+        { role: "assistant", content: "Yes, customer managed keys are supported by Azure OpenAI?" },
+        { role: "user", content: "Do other Azure AI services support this too?" },
+        ],
+        model: "",
+      });
+    
+      for (const choice of result.choices) {
+        console.log(choice.message);
+      }
+    }
+    
+    main().catch((err) => {
+      console.error("The sample encountered an error:", err);
+    });
+    
+    module.exports = { main };
+    ```
+
+1. Sign in to Azure with the following command:
+
+    ```shell
+    az login
+    ```
+
+1. Run the JavaScript file.
+
+    ```shell
+    node index.js
+    ```
 
 
 ## [API key](#tab/api-key)
 
-```javascript
-const { AzureOpenAI } = require("openai");
-
-// You will need to set these environment variables or edit the following values
-const endpoint = process.env["AZURE_OPENAI_ENDPOINT"] || "<endpoint>";
-const apiKey = process.env["AZURE_OPENAI_API_KEY"] || "<api key>";
-const apiVersion = "2024-05-01-preview";
-const deployment = "gpt-4o"; //This must match your deployment name.
-
-async function main() {
-
-  const client = new AzureOpenAI({ endpoint, apiKey, apiVersion, deployment });
-  const result = await client.chat.completions.create({
-    messages: [
-    { role: "system", content: "You are a helpful assistant." },
-    { role: "user", content: "Does Azure OpenAI support customer managed keys?" },
-    { role: "assistant", content: "Yes, customer managed keys are supported by Azure OpenAI?" },
-    { role: "user", content: "Do other Azure AI services support this too?" },
-    ],
-    model: "",
-  });
-
-  for (const choice of result.choices) {
-    console.log(choice.message);
-  }
-}
-
-main().catch((err) => {
-  console.error("The sample encountered an error:", err);
-});
-
-module.exports = { main };
-```
-
-Run the script with the following command:
-
-```cmd
-node.exe ChatCompletion.js
-```
-
+1. Create the `index.js` file with the following code:
+    
+    ```javascript
+    const { AzureOpenAI } = require("openai");
+    
+    // You will need to set these environment variables or edit the following values
+    const endpoint = process.env.AZURE_OPENAI_ENDPOINT || "Your endpoint";
+    const apiKey = process.env.AZURE_OPENAI_API_KEY || "Your API key";
+    const apiVersion = process.env.OPENAI_API_VERSION || "2024-05-01-preview";
+    const deployment = process.env.AZURE_OPENAI_DEPLOYMENT_NAME || "gpt-4o"; //This must match your deployment name.
+    
+    async function main() {
+    
+      const client = new AzureOpenAI({ endpoint, apiKey, apiVersion, deployment });
+      const result = await client.chat.completions.create({
+        messages: [
+        { role: "system", content: "You are a helpful assistant." },
+        { role: "user", content: "Does Azure OpenAI support customer managed keys?" },
+        { role: "assistant", content: "Yes, customer managed keys are supported by Azure OpenAI?" },
+        { role: "user", content: "Do other Azure AI services support this too?" },
+        ],
+        model: "",
+      });
+    
+      for (const choice of result.choices) {
+        console.log(choice.message);
+      }
+    }
+    
+    main().catch((err) => {
+      console.error("The sample encountered an error:", err);
+    });
+    
+    module.exports = { main };
+    ```
+    
+1. Run the JavaScript file.
+
+    ```shell
+    node index.js
+    ```
+    
 ---
 
 ## Output

@@ -30,183 +30,233 @@ For the recommended keyless authentication with Microsoft Entra ID, you need to:
 - Install the [Azure CLI](/cli/azure/install-azure-cli) used for keyless authentication with Microsoft Entra ID.
 - Assign the `Cognitive Services User` role to your user account. You can assign roles in the Azure portal under **Access control (IAM)** > **Add role assignment**.
 
-## Retrieve resource information
-
-[!INCLUDE [resource authentication](resource-authentication.md)]
-
-> [!CAUTION]
-> To use the recommended keyless authentication with the SDK, make sure that the `AZURE_OPENAI_API_KEY` environment variable isn't set. 
+## Set up
 
-## Create a Node application
+1. Create a new folder `chat-quickstart` to contain the application and open Visual Studio Code in that folder with the following command:
 
-In a console window (such as cmd, PowerShell, or Bash), create a new directory for your app, and navigate to it. 
+    ```shell
+    mkdir chat-quickstart && cd chat-quickstart
+    ```
+    
+1. Create the `package.json` with the following command:
 
-## Install the client library
+    ```shell
+    npm init -y
+    ```
 
-Install the required packages for JavaScript with npm from within the context of your new directory:
+1. Update the `package.json` to ECMAScript with the following command: 
 
-```console
-npm install openai @azure/identity
-```
+    ```shell
+    npm pkg set type=module
+    ```
+    
 
-Your app's _package.json_ file is updated with the dependencies.
+1. Install the OpenAI client library for JavaScript with:
 
+    ```console
+    npm install openai
+    ```
 
-## Create a sample application
+1. For the **recommended** passwordless authentication:
 
-Open a command prompt where you want the new project, and create a new file named ChatCompletion.ts. Copy the following code into the ChatCompletion.ts file.
-
-## [Microsoft Entra ID](#tab/typescript-keyless)
+    ```console
+    npm install @azure/identity
+    ```
 
-```typescript
-import { AzureOpenAI } from "openai";
-import { 
-  DefaultAzureCredential, 
-  getBearerTokenProvider 
-} from "@azure/identity";
-import type {
-  ChatCompletion,
-  ChatCompletionCreateParamsNonStreaming,
-} from "openai/resources/index";
-
-// You will need to set these environment variables or edit the following values
-const endpoint = process.env["AZURE_OPENAI_ENDPOINT"] || "<endpoint>";
-
-// Required Azure OpenAI deployment name and API version
-const apiVersion = "2024-08-01-preview";
-const deploymentName = "gpt-4o-mini"; //This must match your deployment name.
-
-// keyless authentication    
-const credential = new DefaultAzureCredential();
-const scope = "https://cognitiveservices.azure.com/.default";
-const azureADTokenProvider = getBearerTokenProvider(credential, scope);
-
-function getClient(): AzureOpenAI {
-  return new AzureOpenAI({
-    endpoint,
-    azureADTokenProvider,
-    apiVersion,
-    deployment: deploymentName,
-  });
-}
-
-function createMessages(): ChatCompletionCreateParamsNonStreaming {
-  return {
-    messages: [
-      { role: "system", content: "You are a helpful assistant." },
-      {
-        role: "user",
-        content: "Does Azure OpenAI support customer managed keys?",
-      },
-      {
-        role: "assistant",
-        content: "Yes, customer managed keys are supported by Azure OpenAI?",
-      },
-      { role: "user", content: "Do other Azure AI services support this too?" },
-    ],
-    model: "",
-  };
-}
-async function printChoices(completion: ChatCompletion): Promise<void> {
-  for (const choice of completion.choices) {
-    console.log(choice.message);
-  }
-}
-export async function main() {
-  const client = getClient();
-  const messages = createMessages();
-  const result = await client.chat.completions.create(messages);
-  await printChoices(result);
-}
-
-main().catch((err) => {
-  console.error("The sample encountered an error:", err);
-});
-```
+## Retrieve resource information
 
-Build the script with the following command:
+[!INCLUDE [resource authentication](resource-authentication.md)]
 
-```cmd
-tsc
-```
+> [!CAUTION]
+> To use the recommended keyless authentication with the SDK, make sure that the `AZURE_OPENAI_API_KEY` environment variable isn't set. 
 
-Run the script with the following command:
+## Create a sample application
 
-```cmd
-node.exe ChatCompletion.js
-```
+## [Microsoft Entra ID](#tab/typescript-keyless)
+   
+1. Create the `index.ts` file with the following code:
+ 
+    ```typescript
+    import { AzureOpenAI } from "openai";
+    import { 
+      DefaultAzureCredential, 
+      getBearerTokenProvider 
+    } from "@azure/identity";
+    import type {
+      ChatCompletion,
+      ChatCompletionCreateParamsNonStreaming,
+    } from "openai/resources/index";
+    
+    // You will need to set these environment variables or edit the following values
+    const endpoint = process.env.AZURE_OPENAI_ENDPOINT || "Your endpoint";
+    
+    // Required Azure OpenAI deployment name and API version
+    const apiVersion = process.env.OPENAI_API_VERSION || "2024-08-01-preview";
+    const deploymentName = process.env.AZURE_OPENAI_DEPLOYMENT_NAME || "gpt-4o-mini"; //This must match your deployment name.
+    
+    // keyless authentication    
+    const credential = new DefaultAzureCredential();
+    const scope = "https://cognitiveservices.azure.com/.default";
+    const azureADTokenProvider = getBearerTokenProvider(credential, scope);
+    
+    function getClient(): AzureOpenAI {
+      return new AzureOpenAI({
+        endpoint,
+        azureADTokenProvider,
+        apiVersion,
+        deployment: deploymentName,
+      });
+    }
+    
+    function createMessages(): ChatCompletionCreateParamsNonStreaming {
+      return {
+        messages: [
+          { role: "system", content: "You are a helpful assistant." },
+          {
+            role: "user",
+            content: "Does Azure OpenAI support customer managed keys?",
+          },
+          {
+            role: "assistant",
+            content: "Yes, customer managed keys are supported by Azure OpenAI?",
+          },
+          { role: "user", content: "Do other Azure AI services support this too?" },
+        ],
+        model: "",
+      };
+    }
+    async function printChoices(completion: ChatCompletion): Promise<void> {
+      for (const choice of completion.choices) {
+        console.log(choice.message);
+      }
+    }
+    export async function main() {
+      const client = getClient();
+      const messages = createMessages();
+      const result = await client.chat.completions.create(messages);
+      await printChoices(result);
+    }
+    
+    main().catch((err) => {
+      console.error("The sample encountered an error:", err);
+    });
+    ```
+
+1. Create the `tsconfig.json` file to transpile the TypeScript code and copy the following code for ECMAScript.
+
+    ```json
+    {
+        "compilerOptions": {
+          "module": "NodeNext",
+          "target": "ES2022", // Supports top-level await
+          "moduleResolution": "NodeNext",
+          "skipLibCheck": true, // Avoid type errors from node_modules
+          "strict": true // Enable strict type-checking options
+        },
+        "include": ["*.ts"]
+    }
+    ```
+
+1. Transpile from TypeScript to JavaScript.
+
+    ```shell
+    tsc
+    ```
+    
+1. Run the code with the following command:
+
+    ```shell
+    node index.js
+    ```
 
 ## [API Key](#tab/typescript-key)
 
-```typescript
-import { AzureOpenAI } from "openai";
-import type {
-  ChatCompletion,
-  ChatCompletionCreateParamsNonStreaming,
-} from "openai/resources/index";
-
-// You will need to set these environment variables or edit the following values
-const endpoint = process.env["AZURE_OPENAI_ENDPOINT"] || "<endpoint>";
-const apiKey = process.env["AZURE_OPENAI_API_KEY"] || "<api key>";
-
-// Required Azure OpenAI deployment name and API version
-const apiVersion = "2024-08-01-preview";
-const deploymentName = "gpt-4o-mini"; //This must match your deployment name.
-
-function getClient(): AzureOpenAI {
-  return new AzureOpenAI({
-    endpoint,
-    apiKey,
-    apiVersion,
-    deployment: deploymentName,
-  });
-}
-
-function createMessages(): ChatCompletionCreateParamsNonStreaming {
-  return {
-    messages: [
-      { role: "system", content: "You are a helpful assistant." },
-      {
-        role: "user",
-        content: "Does Azure OpenAI support customer managed keys?",
-      },
-      {
-        role: "assistant",
-        content: "Yes, customer managed keys are supported by Azure OpenAI?",
-      },
-      { role: "user", content: "Do other Azure AI services support this too?" },
-    ],
-    model: "",
-  };
-}
-async function printChoices(completion: ChatCompletion): Promise<void> {
-  for (const choice of completion.choices) {
-    console.log(choice.message);
-  }
-}
-export async function main() {
-  const client = getClient();
-  const messages = createMessages();
-  const result = await client.chat.completions.create(messages);
-  await printChoices(result);
-}
-
-main().catch((err) => {
-  console.error("The sample encountered an error:", err);
-});
-```
-
-Build the script with the following command:
-
-```cmd
-tsc
-```
-
-Run the script with the following command:
-
-```cmd
-node.exe ChatCompletion.js
-```
+1. Create the `index.ts` file with the following code:
+    
+    ```typescript
+    import { AzureOpenAI } from "openai";
+    import type {
+      ChatCompletion,
+      ChatCompletionCreateParamsNonStreaming,
+    } from "openai/resources/index";
+    
+    // You will need to set these environment variables or edit the following values
+    const endpoint = process.env.AZURE_OPENAI_ENDPOINT || "Your endpoint";
+    const apiKey = process.env.AZURE_OPENAI_API_KEY || "Your API key";
+    
+    // Required Azure OpenAI deployment name and API version
+    const apiVersion = process.env.OPENAI_API_KEY || "2024-08-01-preview";
+    const deploymentName = process.env.AZURE_OPENAI_DEPLOYMENT_NAME || "gpt-4o-mini"; //This must match your deployment name.
+    
+    function getClient(): AzureOpenAI {
+      return new AzureOpenAI({
+        endpoint,
+        apiKey,
+        apiVersion,
+        deployment: deploymentName,
+      });
+    }
+    
+    function createMessages(): ChatCompletionCreateParamsNonStreaming {
+      return {
+        messages: [
+          { role: "system", content: "You are a helpful assistant." },
+          {
+            role: "user",
+            content: "Does Azure OpenAI support customer managed keys?",
+          },
+          {
+            role: "assistant",
+            content: "Yes, customer managed keys are supported by Azure OpenAI?",
+          },
+          { role: "user", content: "Do other Azure AI services support this too?" },
+        ],
+        model: "",
+      };
+    }
+    async function printChoices(completion: ChatCompletion): Promise<void> {
+      for (const choice of completion.choices) {
+        console.log(choice.message);
+      }
+    }
+    export async function main() {
+      const client = getClient();
+      const messages = createMessages();
+      const result = await client.chat.completions.create(messages);
+      await printChoices(result);
+    }
+    
+    main().catch((err) => {
+      console.error("The sample encountered an error:", err);
+    });
+    ```
+
+1. Create the `tsconfig.json` file to transpile the TypeScript code and copy the following code for ECMAScript.
+
+    ```json
+    {
+        "compilerOptions": {
+          "module": "NodeNext",
+          "target": "ES2022", // Supports top-level await
+          "moduleResolution": "NodeNext",
+          "skipLibCheck": true, // Avoid type errors from node_modules
+          "strict": true // Enable strict type-checking options
+        },
+        "include": ["*.ts"]
+    }
+    ```
+
+1. Transpile from TypeScript to JavaScript.
+
+    ```shell
+    tsc
+    ```
+
+1. Run the code with the following command:
+
+    ```shell
+    node index.js
+    ```
 
 ---
 

@@ -104,7 +104,7 @@ dotnet run
 The URL of the generated image is printed to the console.
 
 ```console
-https://dalleproduse.blob.core.windows.net/private/images/b7ac5e55-f1f8-497a-8d0e-8f51446bf538/generated_00.png?se=2024-07-12T13%3A47%3A56Z&sig=Zri37iYVTVtc52qzTFBOqPgSHvXwEhcO86Smv2ojB%2FE%3D&ske=2024-07-17T12%3A15%3A44Z&skoid=09ba021e-c417-441c-b203-c81e5dcd7b7f&sks=b&skt=2024-07-10T12%3A15%3A44Z&sktid=33e01921-4d64-4f8c-a055-5bdaffd5e33d&skv=2020-10-02&sp=r&spr=https&sr=b&sv=2020-10-02
+<SAS URL>
 ```
 
 > [!NOTE]

@@ -121,7 +121,7 @@ The URL of the generated image is printed to the console.
 
 ```console
 Image generated, HEAD request on URL returned 200
-Image URL: https://dalleproduse.blob.core.windows.net/private/images/d7b28a5c-ca32-4792-8c2a-6a5d8d8e5e45/generated_00.png?se=2023-08-29T17%3A05%3A37Z&sig=loqntaPypYVr9VTT5vpbsjsCz31g1GsdoQi0smbGkks%3D&ske=2023-09-02T18%3A53%3A23Z&skoid=09ba021e-c417-441c-b203-c81e5dcd7b7f&sks=b&skt=2023-08-26T18%3A53%3A23Z&sktid=33e01921-4d64-4f8c-a055-5bdaffd5e33d&skv=2020-10-02&sp=r&spr=https&sr=b&sv=2020-10-02
+Image URL: <SAS URL>
 ```
 > [!NOTE]
 > The image generation APIs come with a content moderation filter. If the service recognizes your prompt as harmful content, it won't return a generated image. For more information, see the [content filter](../concepts/content-filter.md) article.

@@ -163,7 +163,7 @@ dependencies {
 The URL of the generated image is printed to the console.
 
 ```console
-Image location URL that provides temporary access to download the generated image is https://dalleproduse.blob.core.windows.net/private/images/d2ea917f-8802-4ad6-8ef6-3fb7a15c8482/generated_00.png?se=2023-08-25T23%3A11%3A28Z&sig=%2BKa5Mkb9U88DfvxoBpyAjamYRzwb7aVCEucM6XJC3wQ%3D&ske=2023-08-31T15%3A27%3A47Z&skoid=09ba021e-c417-441c-b203-c81e5dcd7b7f&sks=b&skt=2023-08-24T15%3A27%3A47Z&sktid=33e01921-4d64-4f8c-a055-5bdaffd5e33d&skv=2020-10-02&sp=r&spr=https&sr=b&sv=2020-10-02.
+Image location URL that provides temporary access to download the generated image is <SAS URL>.
 Completed getImages.
 ```
 

@@ -28,154 +28,167 @@ For the recommended keyless authentication with Microsoft Entra ID, you need to:
 - Install the [Azure CLI](/cli/azure/install-azure-cli) used for keyless authentication with Microsoft Entra ID.
 - Assign the `Cognitive Services User` role to your user account. You can assign roles in the Azure portal under **Access control (IAM)** > **Add role assignment**.
 
-## Retrieve resource information
-
-[!INCLUDE [resource authentication](resource-authentication.md)]
-
-> [!CAUTION]
-> To use the recommended keyless authentication with the SDK, make sure that the `AZURE_OPENAI_API_KEY` environment variable isn't set. 
+## Set up
+ 
+1. Create a new folder `image-quickstart` to contain the application and open Visual Studio Code in that folder with the following command:
 
-## Create a Node application
+    ```shell
+    mkdir image-quickstart && cd image-quickstart
+    ```
 
-In a console window (such as cmd, PowerShell, or Bash), create a new directory for your app, and navigate to it. Then run the `npm init` command to create a node application with a _package.json_ file.
+1. Create the `package.json` with the following command:
 
-```console
-npm init
-```
+    ```shell
+    npm init -y
+    ```   
 
-## Install the client library
+1. Install the OpenAI client library for JavaScript with:
 
-Install the client libraries with:
+    ```console
+    npm install openai
+    ```
 
-```console
-npm install openai @azure/identity
-```
+1. For the **recommended** passwordless authentication:
 
-Your app's _package.json_ file will be updated with the dependencies.
+    ```console
+    npm install @azure/identity
+    ```
 
-## Generate images with DALL-E
+## Retrieve resource information
 
-Create a new file named _ImageGeneration.js_ and open it in your preferred code editor. Copy the following code into the _ImageGeneration.js_ file:
+[!INCLUDE [resource authentication](resource-authentication.md)]
 
+> [!CAUTION]
+> To use the recommended keyless authentication with the SDK, make sure that the `AZURE_OPENAI_API_KEY` environment variable isn't set. 
 
+## Generate images with DALL-E
 
 #### [Microsoft Entra ID](#tab/keyless)
 
-```javascript
-const { AzureOpenAI } = require("openai");
-const { 
-    DefaultAzureCredential, 
-    getBearerTokenProvider 
-} = require("@azure/identity");
-
-// You will need to set these environment variables or edit the following values
-const endpoint = process.env["AZURE_OPENAI_ENDPOINT"];
-
-// Required Azure OpenAI deployment name and API version
-const apiVersion = "2024-07-01";
-const deploymentName = "dall-e-3";
-
-// The prompt to generate images from
-const prompt = "a monkey eating a banana";
-const numberOfImagesToGenerate = 1;
-
-// keyless authentication    
-const credential = new DefaultAzureCredential();
-const scope = "https://cognitiveservices.azure.com/.default";
-const azureADTokenProvider = getBearerTokenProvider(credential, scope);
-
-function getClient(): AzureOpenAI {
-  return new AzureOpenAI({
-    endpoint,
-    azureADTokenProvider,
-    apiVersion,
-    deployment: deploymentName,
-  });
-}
-async function main() {
-  console.log("== Image Generation ==");
-
-  const client = getClient();
-
-  const results = await client.images.generate({
-    prompt,
-    size: "1024x1024",
-    n: numberOfImagesToGenerate,
-    model: "",
-    style: "vivid", // or "natural"
-  });
-
-  for (const image of results.data) {
-    console.log(`Image generation result URL: ${image.url}`);
-  }
-}
-
-main().catch((err) => {
-  console.error("The sample encountered an error:", err);
-});
-```
-
-Run the script with the following command:
-
-```console
-node ImageGeneration.js
-```
-
-
-
-#### [API key](#tab/api-key)
-
-```javascript
-const { AzureOpenAI } = require("openai");
-
-// You will need to set these environment variables or edit the following values
-const endpoint = process.env["AZURE_OPENAI_ENDPOINT"];
-const apiKey = process.env["AZURE_OPENAI_API_KEY"];
-
-// Required Azure OpenAI deployment name and API version
-const apiVersion = "2024-07-01";
-const deploymentName = "dall-e-3";
-
-// The prompt to generate images from
-const prompt = "a monkey eating a banana";
-const numberOfImagesToGenerate = 1;
-
-function getClient() {
-  return new AzureOpenAI({
-    endpoint,
-    apiKey,
-    apiVersion,
-    deployment: deploymentName,
-  });
-}
-async function main() {
-  console.log("== Image Generation ==");
-
-  const client = getClient();
-
-  const results = await client.images.generate({
-    prompt,
-    size: "1024x1024",
-    n: numberOfImagesToGenerate,
-    model: "",
-    style: "vivid", // or "natural"
-  });
-
-  for (const image of results.data) {
-    console.log(`Image generation result URL: ${image.url}`);
-  }
-}
-
-main().catch((err) => {
-  console.error("The sample encountered an error:", err);
-});
-```
-
-Run the script with the following command:
-
-```console
-node ImageGeneration.js
-```
+1. Create the `index.js` file with the following code:
+
+    ```javascript
+    const { AzureOpenAI } = require("openai");
+    const { 
+        DefaultAzureCredential, 
+        getBearerTokenProvider 
+    } = require("@azure/identity");
+    
+    // You will need to set these environment variables or edit the following values
+    const endpoint = process.env.AZURE_OPENAI_ENDPOINT || "Your endpoint";
+    
+    // Required Azure OpenAI deployment name and API version
+    const apiVersion = process.env.OPENAI_API_VERSION || "2024-07-01";
+    const deploymentName = process.env.AZURE_OPENAI_DEPLOYMENT_NAME || "dall-e-3";
+    
+    // The prompt to generate images from
+    const prompt = "a monkey eating a banana";
+    const numberOfImagesToGenerate = 1;
+    
+    // keyless authentication    
+    const credential = new DefaultAzureCredential();
+    const scope = "https://cognitiveservices.azure.com/.default";
+    const azureADTokenProvider = getBearerTokenProvider(credential, scope);
+    
+    function getClient(): AzureOpenAI {
+      return new AzureOpenAI({
+        endpoint,
+        azureADTokenProvider,
+        apiVersion,
+        deployment: deploymentName,
+      });
+    }
+    async function main() {
+      console.log("== Image Generation ==");
+    
+      const client = getClient();
+    
+      const results = await client.images.generate({
+        prompt,
+        size: "1024x1024",
+        n: numberOfImagesToGenerate,
+        model: "",
+        style: "vivid", // or "natural"
+      });
+    
+      for (const image of results.data) {
+        console.log(`Image generation result URL: ${image.url}`);
+      }
+    }
+    
+    main().catch((err) => {
+      console.error("The sample encountered an error:", err);
+    });
+    ```
+
+1. Sign in to Azure with the following command:
+
+    ```shell
+    az login
+    ```
+
+1. Run the JavaScript file.
+
+    ```shell
+    node index.js
+    ```
+
+
+## [API key](#tab/api-key)
+
+1. Create the `index.js` file with the following code:
+    
+    ```javascript
+    const { AzureOpenAI } = require("openai");
+    
+    // You will need to set these environment variables or edit the following values
+    const endpoint = process.env.AZURE_OPENAI_ENDPOINT || "Your endpoint";
+    const apiKey = process.env.AZURE_OPENAI_API_KEY || "Your API key";
+    
+    // Required Azure OpenAI deployment name and API version
+    const apiVersion = process.env.OPENAI_API_VERSION || "2024-07-01";
+    const deploymentName = process.env.AZURE_OPENAI_DEPLOYMENT_NAME || "dall-e-3";
+    
+    // The prompt to generate images from
+    const prompt = "a monkey eating a banana";
+    const numberOfImagesToGenerate = 1;
+    
+    function getClient() {
+      return new AzureOpenAI({
+        endpoint,
+        apiKey,
+        apiVersion,
+        deployment: deploymentName,
+      });
+    }
+    async function main() {
+      console.log("== Image Generation ==");
+    
+      const client = getClient();
+    
+      const results = await client.images.generate({
+        prompt,
+        size: "1024x1024",
+        n: numberOfImagesToGenerate,
+        model: "",
+        style: "vivid", // or "natural"
+      });
+    
+      for (const image of results.data) {
+        console.log(`Image generation result URL: ${image.url}`);
+      }
+    }
+    
+    main().catch((err) => {
+      console.error("The sample encountered an error:", err);
+    });
+    ```
+    
+1. Run the JavaScript file.
+
+    ```shell
+    node index.js
+    ```
 
 ---
 
@@ -185,8 +198,8 @@ The URL of the generated image is printed to the console.
 
 ```console
 == Batch Image Generation ==
-Image generation result URL: https://dalleproduse.blob.core.windows.net/private/images/5e7536a9-a0b5-4260-8769-2d54106f2913/generated_00.png?se=2023-08-29T19%3A12%3A57Z&sig=655GkWajOZ9ALjFykZF%2FBMZRPQALRhf4UPDImWCQoGI%3D&ske=2023-09-02T18%3A53%3A23Z&skoid=09ba021e-c417-441c-b203-c81e5dcd7b7f&sks=b&skt=2023-08-26T18%3A53%3A23Z&sktid=33e01921-4d64-4f8c-a055-5bdaffd5e33d&skv=2020-10-02&sp=r&spr=https&sr=b&sv=2020-10-02
-Image generation result URL: https://dalleproduse.blob.core.windows.net/private/images/5e7536a9-a0b5-4260-8769-2d54106f2913/generated_01.png?se=2023-08-29T19%3A12%3A57Z&sig=B24ymPLSZ3HfG23uojOD9VlRFGxjvgcNmvFo4yPUbEc%3D&ske=2023-09-02T18%3A53%3A23Z&skoid=09ba021e-c417-441c-b203-c81e5dcd7b7f&sks=b&skt=2023-08-26T18%3A53%3A23Z&sktid=33e01921-4d64-4f8c-a055-5bdaffd5e33d&skv=2020-10-02&sp=r&spr=https&sr=b&sv=2020-10-02
+Image generation result URL: <SAS URL>
+Image generation result URL: <SAS URL>
 ```
 
 > [!NOTE]

@@ -29,157 +29,211 @@ For the recommended keyless authentication with Microsoft Entra ID, you need to:
 - Install the [Azure CLI](/cli/azure/install-azure-cli) used for keyless authentication with Microsoft Entra ID.
 - Assign the `Cognitive Services User` role to your user account. You can assign roles in the Azure portal under **Access control (IAM)** > **Add role assignment**.
 
-## Retrieve resource information
+## Set up
 
-[!INCLUDE [resource authentication](resource-authentication.md)]
+1. Create a new folder `image-quickstart` to contain the application and open Visual Studio Code in that folder with the following command:
 
-> [!CAUTION]
-> To use the recommended keyless authentication with the SDK, make sure that the `AZURE_OPENAI_API_KEY` environment variable isn't set. 
+    ```shell
+    mkdir image-quickstart && cd image-quickstart
+    ```
+    
+1. Create the `package.json` with the following command:
 
-## Create a Node application
+    ```shell
+    npm init -y
+    ```
 
-In a console window (such as cmd, PowerShell, or Bash), create a new directory for your app, and navigate to it. Then run the `npm init` command to create a node application with a _package.json_ file.
+1. Update the `package.json` to ECMAScript with the following command: 
 
-```console
-npm init
-```
+    ```shell
+    npm pkg set type=module
+    ```
+    
+
+1. Install the OpenAI client library for JavaScript with:
 
-## Install the client library
+    ```console
+    npm install openai
+    ```
 
-Install the client libraries with:
+1. For the **recommended** passwordless authentication:
 
-```console
-npm install openai @azure/identity
-```
+    ```console
+    npm install @azure/identity
+    ```
 
-Your app's _package.json_ file will be updated with the dependencies.
+## Retrieve resource information
 
-## Generate images with DALL-E
+[!INCLUDE [resource authentication](resource-authentication.md)]
+
+> [!CAUTION]
+> To use the recommended keyless authentication with the SDK, make sure that the `AZURE_OPENAI_API_KEY` environment variable isn't set. 
 
-Create a new file named _ImageGeneration.ts_ and open it in your preferred code editor. Copy the following code into the _ImageGeneration.ts_ file:
+## Generate images with DALL-E
 
 #### [Microsoft Entra ID](#tab/typescript-keyless)
 
-```typescript
-import { AzureOpenAI } from "openai";
-import { 
-    DefaultAzureCredential, 
-    getBearerTokenProvider 
-} from "@azure/identity";
-
-// You will need to set these environment variables or edit the following values
-const endpoint = process.env["AZURE_OPENAI_ENDPOINT"];
-
-// Required Azure OpenAI deployment name and API version
-const apiVersion = "2024-07-01";
-const deploymentName = "dall-e-3";
-
-// keyless authentication    
-const credential = new DefaultAzureCredential();
-const scope = "https://cognitiveservices.azure.com/.default";
-const azureADTokenProvider = getBearerTokenProvider(credential, scope);
-
-function getClient(): AzureOpenAI {
-  return new AzureOpenAI({
-    endpoint,
-    azureADTokenProvider,
-    apiVersion,
-    deployment: deploymentName,
-  });
-}
-async function main() {
-  console.log("== Image Generation ==");
-
-  const client = getClient();
-
-  const results = await client.images.generate({
-    prompt,
-    size: "1024x1024",
-    n: numberOfImagesToGenerate,
-    model: "",
-    style: "vivid", // or "natural"
-  });
-
-  for (const image of results.data) {
-    console.log(`Image generation result URL: ${image.url}`);
-  }
-}
-
-main().catch((err) => {
-  console.error("The sample encountered an error:", err);
-});
-```
+1. Create the `index.ts` file with the following code:
+
+    ```typescript
+    import { AzureOpenAI } from "openai";
+    import { 
+        DefaultAzureCredential, 
+        getBearerTokenProvider 
+    } from "@azure/identity";
+    
+    // You will need to set these environment variables or edit the following values
+    const endpoint = process.env.AZURE_OPENAI_ENDPOINT || "Your endpoint";
+    
+    // Required Azure OpenAI deployment name and API version
+    const apiVersion = process.env.OPENAI_API_VERSION || "2024-07-01";
+    const deploymentName = process.env.AZURE_OPENAI_DEPLOYMENT_NAME || "dall-e-3";
+    
+    // keyless authentication    
+    const credential = new DefaultAzureCredential();
+    const scope = "https://cognitiveservices.azure.com/.default";
+    const azureADTokenProvider = getBearerTokenProvider(credential, scope);
+    
+    function getClient(): AzureOpenAI {
+      return new AzureOpenAI({
+        endpoint,
+        azureADTokenProvider,
+        apiVersion,
+        deployment: deploymentName,
+      });
+    }
+    async function main() {
+      console.log("== Image Generation ==");
+    
+      const client = getClient();
+    
+      const results = await client.images.generate({
+        prompt,
+        size: "1024x1024",
+        n: numberOfImagesToGenerate,
+        model: "",
+        style: "vivid", // or "natural"
+      });
+    
+      for (const image of results.data) {
+        console.log(`Image generation result URL: ${image.url}`);
+      }
+    }
+    
+    main().catch((err) => {
+      console.error("The sample encountered an error:", err);
+    });
+    ```
 
-1. Build the application with the following command:
+1. Create the `tsconfig.json` file to transpile the TypeScript code and copy the following code for ECMAScript.
+
+    ```json
+    {
+        "compilerOptions": {
+          "module": "NodeNext",
+          "target": "ES2022", // Supports top-level await
+          "moduleResolution": "NodeNext",
+          "skipLibCheck": true, // Avoid type errors from node_modules
+          "strict": true // Enable strict type-checking options
+        },
+        "include": ["*.ts"]
+    }
+    ```
 
-    ```console
+1. Transpile from TypeScript to JavaScript.
+
+    ```shell
     tsc
     ```
+    
+1. Sign in to Azure with the following command:
 
-1. Run the application with the following command:
+    ```shell
+    az login
+    ```
 
-    ```console
-    node ImageGeneration.js
+1. Run the code with the following command:
+
+    ```shell
+    node index.js
     ```
 
-#### [API key](#tab/typescript-key)
-
-```typescript
-import { AzureOpenAI } from "openai";
-
-// You will need to set these environment variables or edit the following values
-const endpoint = process.env["AZURE_OPENAI_ENDPOINT"];
-const apiKey = process.env["AZURE_OPENAI_API_KEY"];
-
-// Required Azure OpenAI deployment name and API version
-const apiVersion = "2024-07-01";
-const deploymentName = "dall-e-3";
-
-// The prompt to generate images from
-const prompt = "a monkey eating a banana";
-const numberOfImagesToGenerate = 1;
-
-function getClient(): AzureOpenAI {
-  return new AzureOpenAI({
-    endpoint,
-    apiKey,
-    apiVersion,
-    deployment: deploymentName,
-  });
-}
-async function main() {
-  console.log("== Image Generation ==");
-
-  const client = getClient();
-
-  const results = await client.images.generate({
-    prompt,
-    size: "1024x1024",
-    n: numberOfImagesToGenerate,
-    model: "",
-    style: "vivid", // or "natural"
-  });
-
-  for (const image of results.data) {
-    console.log(`Image generation result URL: ${image.url}`);
-  }
-}
-
-main().catch((err) => {
-  console.error("The sample encountered an error:", err);
-});
-```
+## [API key](#tab/typescript-key)
+
+1. Create the `index.ts` file with the following code:
+
+    ```typescript
+    import { AzureOpenAI } from "openai";
+    
+    // You will need to set these environment variables or edit the following values
+    const endpoint = process.env.AZURE_OPENAI_ENDPOINT || "Your endpoint";
+    const apiKey = process.env.AZURE_OPENAI_API_KEY || "Your API key";
+    
+    // Required Azure OpenAI deployment name and API version
+    const apiVersion = process.env.OPENAI_API_VERSION || "2024-07-01";
+    const deploymentName = process.env.AZURE_OPENAI_DEPLOYMENT_NAME || "dall-e-3";
+    
+    // The prompt to generate images from
+    const prompt = "a monkey eating a banana";
+    const numberOfImagesToGenerate = 1;
+    
+    function getClient(): AzureOpenAI {
+      return new AzureOpenAI({
+        endpoint,
+        apiKey,
+        apiVersion,
+        deployment: deploymentName,
+      });
+    }
+    async function main() {
+      console.log("== Image Generation ==");
+    
+      const client = getClient();
+    
+      const results = await client.images.generate({
+        prompt,
+        size: "1024x1024",
+        n: numberOfImagesToGenerate,
+        model: "",
+        style: "vivid", // or "natural"
+      });
+    
+      for (const image of results.data) {
+        console.log(`Image generation result URL: ${image.url}`);
+      }
+    }
+    
+    main().catch((err) => {
+      console.error("The sample encountered an error:", err);
+    });
+    ```
 
-1. Build the application with the following command:
 
-    ```console
-    tsc
+1. Create the `tsconfig.json` file to transpile the TypeScript code and copy the following code for ECMAScript.
+
+    ```json
+    {
+        "compilerOptions": {
+          "module": "NodeNext",
+          "target": "ES2022", // Supports top-level await
+          "moduleResolution": "NodeNext",
+          "skipLibCheck": true, // Avoid type errors from node_modules
+          "strict": true // Enable strict type-checking options
+        },
+        "include": ["*.ts"]
+    }
     ```
 
-1. Run the application with the following command:
+1. Transpile from TypeScript to JavaScript.
 
-    ```console
-    node ImageGeneration.js
+    ```shell
+    tsc
+    ```
+    
+1. Run the code with the following command:
+
+    ```shell
+    node index.js
     ```
 
 ---
@@ -190,8 +244,8 @@ The URL of the generated image is printed to the console.
 
 ```console
 == Batch Image Generation ==
-Image generation result URL: https://dalleproduse.blob.core.windows.net/private/images/5e7536a9-a0b5-4260-8769-2d54106f2913/generated_00.png?se=2023-08-29T19%3A12%3A57Z&sig=655GkWajOZ9ALjFykZF%2FBMZRPQALRhf4UPDImWCQoGI%3D&ske=2023-09-02T18%3A53%3A23Z&skoid=09ba021e-c417-441c-b203-c81e5dcd7b7f&sks=b&skt=2023-08-26T18%3A53%3A23Z&sktid=33e01921-4d64-4f8c-a055-5bdaffd5e33d&skv=2020-10-02&sp=r&spr=https&sr=b&sv=2020-10-02
-Image generation result URL: https://dalleproduse.blob.core.windows.net/private/images/5e7536a9-a0b5-4260-8769-2d54106f2913/generated_01.png?se=2023-08-29T19%3A12%3A57Z&sig=B24ymPLSZ3HfG23uojOD9VlRFGxjvgcNmvFo4yPUbEc%3D&ske=2023-09-02T18%3A53%3A23Z&skoid=09ba021e-c417-441c-b203-c81e5dcd7b7f&sks=b&skt=2023-08-26T18%3A53%3A23Z&sktid=33e01921-4d64-4f8c-a055-5bdaffd5e33d&skv=2020-10-02&sp=r&spr=https&sr=b&sv=2020-10-02
+Image generation result URL: <SAS URL>
+Image generation result URL: <SAS URL>
 ```
 
 > [!NOTE]