Merge pull request #64 from MicrosoftDocs/main

8/30/2024 AM Publish

Author: Taojunshen

articles/ai-services/openai/concepts/fine-tuning-considerations.md

@@ -5,7 +5,7 @@ description: Learn more about what you should take into consideration before fin
 manager: nitinme
 ms.service: azure-ai-openai
 ms.topic: conceptual 
-ms.date: 10/23/2023
+ms.date: 08/29/2024
 author: mrbullwinkle
 ms.author: mbullwin
 recommendations: false
@@ -79,7 +79,7 @@ Even with a great use case, fine-tuning is only as good as the quality of the da
 
 Another important point is even with high quality data if your data isn't in the necessary format for fine-tuning you'll need to commit engineering resources in order to properly format the data.
 
-| Data  | Babbage-002 & Davinci-002 | GPT-3.5-Turbo |
+| Data  | Babbage-002 <br> Davinci-002 | GPT-3.5-Turbo <br> GPT-4o & GPT-4o mini <br> GPT-4 |
 |---|---|---|
 | Volume | Thousands of Examples | Thousands of Examples |
 | Format | Prompt/Completion | Conversational Chat |

articles/ai-services/openai/concepts/prompt-engineering.md

@@ -4,7 +4,7 @@ titleSuffix: Azure OpenAI
 description: Learn how to use prompt engineering to optimize your work with Azure OpenAI Service.
 ms.service: azure-ai-openai
 ms.topic: conceptual
-ms.date: 03/29/2024
+ms.date: 08/29/2024
 ms.custom: references_regions, build-2023, build-2023-dataai
 manager: nitinme
 author: mrbullwinkle
@@ -14,7 +14,7 @@ recommendations: false
 
 # Introduction to prompt engineering
 
-GPT-3, GPT-3.5, and GPT-4 models from OpenAI are prompt-based. With prompt-based models, the user interacts with the model by entering a text prompt, to which the model responds with a text completion. This completion is the model’s continuation of the input text.
+GPT-3, GPT-3.5, GPT-4, and GPT-4o models from OpenAI are prompt-based. With prompt-based models, the user interacts with the model by entering a text prompt, to which the model responds with a text completion. This completion is the model’s continuation of the input text.
 
 While these models are extremely powerful, their behavior is also very sensitive to the prompt. This makes prompt construction an important skill to develop.
 
@@ -24,7 +24,7 @@ Prompt construction can be difficult. In practice, the prompt acts to configure
 
 This section covers the basic concepts and elements of GPT prompts.
 
-Text prompts are how users interact with GPT models. As with all generative language models, GPT models attempt to produce the next series of words that are most likely to follow from the previous text. It's as if we're saying *What is the first thing that comes to your mind when I say `<prompt>`?*. The examples below demonstrate this behavior. Given the first words of famous content, the model is able to accurately continue the text.
+Text prompts are how users interact with GPT models. As with all generative language models, GPT models attempt to produce the next series of words that are most likely to follow from the previous text. It's as if we're saying *What is the first thing that comes to your mind when I say `<prompt>`?* The examples below demonstrate this behavior. Given the first words of famous content, the model is able to accurately continue the text.
 
 | Prompt                             |Completion |
 |------------------------------------|-----------|

articles/ai-services/openai/how-to/chatgpt.md

@@ -12,10 +12,10 @@ manager: nitinme
 keywords: ChatGPT
 ---
 
-# Work with the GPT-3.5-Turbo and GPT-4 models
+# Work with the GPT-3.5-Turbo, GPT-4 models, and GPT-4o models
 
-The GPT-3.5-Turbo and GPT-4 models are language models that are optimized for conversational interfaces. The models behave differently than the older GPT-3 models. Previous models were text-in and text-out, which means they accepted a prompt string and returned a completion to append to the prompt. However, the GPT-3.5-Turbo and GPT-4 models are conversation-in and message-out. The models expect input formatted in a specific chat-like transcript format. They return a completion that represents a model-written message in the chat. This format was designed specifically for multi-turn conversations, but it can also work well for nonchat scenarios.
+GPT-3.5-Turbo, GPT-4, and GPT-4o series models are language models that are optimized for conversational interfaces. The models behave differently than the older GPT-3 models. Previous models were text-in and text-out, which means they accepted a prompt string and returned a completion to append to the prompt. However, the latest models are conversation-in and message-out. The models expect input formatted in a specific chat-like transcript format. They return a completion that represents a model-written message in the chat. This format was designed specifically for multi-turn conversations, but it can also work well for nonchat scenarios.
 
-This article walks you through getting started with the GPT-3.5-Turbo and GPT-4 models. To get the best results, use the techniques described here. Don't try to interact with the models the same way you did with the older model series because the models are often verbose and provide less useful responses.
+This article walks you through getting started with chat completions models. To get the best results, use the techniques described here. Don't try to interact with the models the same way you did with the older model series because the models are often verbose and provide less useful responses.
 
 [!INCLUDE [Chat Completions](../includes/chat-completion.md)]

articles/ai-services/openai/how-to/completions.md

@@ -6,9 +6,9 @@ description: Learn how to generate or manipulate text, including code by using a
 manager: nitinme
 ms.service: azure-ai-openai
 ms.topic: how-to
-ms.date: 08/15/2023
-author: ChrisHMSFT
-ms.author: chrhoder
+ms.date: 08/29/2024
+author: mrbullwinkle
+ms.author: mbullwin
 recommendations: false
 
 ---
@@ -17,6 +17,9 @@ recommendations: false
 
 Azure OpenAI Service provides a **completion endpoint** that can be used for a wide variety of tasks. The endpoint supplies a simple yet powerful text-in, text-out interface to any [Azure OpenAI model](../concepts/models.md). To trigger the completion, you input some text as a prompt. The model generates the completion and attempts to match your context or pattern. Suppose you provide the prompt "As Descartes said, I think, therefore" to the API. For this prompt, Azure OpenAI returns the completion endpoint " I am" with high probability.
 
+> [!IMPORTANT]
+> Unless you have a specific use case that requires the completions endpoint, we recommend instead using the [chat completions endpoint](./chatgpt.md) which allows you to take advantage of the latest models like GPT-4o, GPT-4o mini, and GPT-4 Turbo. 
+
 The best way to start exploring completions is through the playground in [Azure OpenAI Studio](https://oai.azure.com). It's a simple text box where you enter a prompt to generate a completion. You can start with a simple prompt like this one:
 
 ```console

articles/ai-services/openai/how-to/embeddings.md

@@ -7,7 +7,7 @@ manager: nitinme
 ms.service: azure-ai-openai
 ms.custom: devx-track-python
 ms.topic: how-to
-ms.date: 01/16/2024
+ms.date: 08/29/2024
 author: mrbullwinkle
 ms.author: mbullwin
 recommendations: false
@@ -16,7 +16,6 @@ recommendations: false
 
 An embedding is a special format of data representation that can be easily utilized by machine learning models and algorithms. The embedding is an information dense representation of the semantic meaning of a piece of text. Each embedding is a vector of floating point numbers, such that the distance between two embeddings in the vector space is correlated with semantic similarity between two inputs in the original format. For example, if two texts are similar, then their vector representations should also be similar. Embeddings power vector similarity search in Azure Databases such as [Azure Cosmos DB for MongoDB vCore](/azure/cosmos-db/mongodb/vcore/vector-search) , [Azure SQL Database](/azure/azure-sql/database/ai-artificial-intelligence-intelligent-applications?view=azuresql&preserve-view=true#vector-search) or [Azure Database for PostgreSQL - Flexible Server](/azure/postgresql/flexible-server/how-to-use-pgvector).
 
-
 ## How to get embeddings
 
 To obtain an embedding vector for a piece of text, we make a request to the embeddings endpoint as shown in the following code snippets:
@@ -37,13 +36,13 @@ from openai import AzureOpenAI
 
 client = AzureOpenAI(
   api_key = os.getenv("AZURE_OPENAI_API_KEY"),  
-  api_version = "2024-02-01",
+  api_version = "2024-06-01",
   azure_endpoint =os.getenv("AZURE_OPENAI_ENDPOINT") 
 )
 
 response = client.embeddings.create(
     input = "Your text string goes here",
-    model= "text-embedding-ada-002"
+    model= "text-embedding-3-large"
 )
 
 print(response.model_dump_json(indent=2))
@@ -59,7 +58,7 @@ import openai
 openai.api_type = "azure"
 openai.api_key = YOUR_API_KEY
 openai.api_base = "https://YOUR_RESOURCE_NAME.openai.azure.com"
-openai.api_version = "2024-02-01"
+openai.api_version = "2024-06-01"
 
 response = openai.Embedding.create(
     input="Your text string goes here",
@@ -83,7 +82,7 @@ OpenAIClient openAIClient = new (oaiEndpoint, credentials);
 
 EmbeddingsOptions embeddingOptions = new()
 {
-    DeploymentName = "text-embedding-ada-002",
+    DeploymentName = "text-embedding-3-large",
     Input = { "Your text string goes here" },
 };
 

articles/ai-services/openai/how-to/role-based-access-control.md

@@ -7,7 +7,7 @@ author: mrbullwinkle
 manager: nitinme
 ms.service: azure-ai-language
 ms.topic: how-to
-ms.date: 04/03/2024
+ms.date: 08/29/2024
 ms.author: mbullwin
 recommendations: false
 ---

articles/ai-services/openai/how-to/switching-endpoints.yml

@@ -7,7 +7,7 @@ metadata:
   author: mrbullwinkle
   ms.author: mbullwin
   manager: nitinme
-  ms.date: 02/16/2024
+  ms.date: 08/29/2024
   ms.service: azure-ai-openai
   ms.topic: how-to
   ms.custom:
@@ -55,7 +55,7 @@ procedureSection:
           
       client = AzureOpenAI(
           api_key=os.getenv("AZURE_OPENAI_API_KEY"),  
-          api_version="2023-12-01-preview",
+          api_version="2024-07-01-preview",
           azure_endpoint=os.getenv("AZURE_OPENAI_ENDPOINT")
       )
       ```
@@ -103,7 +103,7 @@ procedureSection:
           DefaultAzureCredential(), "https://cognitiveservices.azure.com/.default"
       )
 
-      api_version = "2023-12-01-preview"
+      api_version = "2024-07-01-preview"
       endpoint = "https://my-resource.openai.azure.com"
 
       client = AzureOpenAI(
@@ -139,12 +139,12 @@ procedureSection:
       )
 
       chat_completion = client.chat.completions.create(
-          model="gpt-4",
+          model="gpt-4o",
           messages="<messages>"
       )
 
       embedding = client.embeddings.create(
-          model="text-embedding-ada-002",
+          model="text-embedding-3-large",
           input="<input>"
       )
       ```
@@ -159,12 +159,12 @@ procedureSection:
       )
 
       chat_completion = client.chat.completions.create(
-          model="gpt-35-turbo", # model = "deployment_name".
+          model="gpt-4o", # model = "deployment_name".
           messages="<messages>"
       )
 
       embedding = client.embeddings.create(
-          model="text-embedding-ada-002", # model = "deployment_name".
+          model="text-embedding-3-large", # model = "deployment_name".
           input="<input>"
       )
       ```
@@ -190,7 +190,7 @@ procedureSection:
 
       embedding = client.embeddings.create(
           input=inputs,
-          model="text-embedding-ada-002"
+          model="text-embedding-3-large"
       )
 
 
@@ -204,7 +204,7 @@ procedureSection:
 
       embedding = client.embeddings.create(
           input=inputs,
-          model="text-embedding-ada-002" # This must match the custom deployment name you chose for your model.
+          model="text-embedding-3-large" # This must match the custom deployment name you chose for your model.
           # engine="text-embedding-ada-002"
       )
 
@@ -215,7 +215,7 @@ procedureSection:
       </table>
 
 relatedContent:
-  - text: Learn more about how to work with GPT-35-Turbo and the GPT-4 models with our how-to guide
+  - text: Learn more about how to work with chat completions models with our how-to guide
     url: ../how-to/chatgpt.md
   - text: For more examples, check out the Azure OpenAI Samples GitHub repository
     url: https://aka.ms/AOAICodeSamples

articles/ai-services/openai/how-to/working-with-models.md

@@ -4,7 +4,7 @@ titleSuffix: Azure OpenAI
 description: Learn about managing model deployment life cycle, updates, & retirement.
 ms.service: azure-ai-openai
 ms.topic: conceptual
-ms.date: 06/18/2023
+ms.date: 08/29/2024
 ms.custom: references_regions, build-2023, build-2023-dataai, devx-track-azurepowershell
 manager: nitinme
 author: mrbullwinkle #ChrisHMSFT

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

@@ -6,15 +6,15 @@ author: mrbullwinkle #dereklegenzoff
 ms.author: mbullwin #delegenz
 ms.service: azure-ai-openai
 ms.topic: include
-ms.date: 04/25/2024
+ms.date: 08/29/2024
 manager: nitinme
 keywords: ChatGPT
 
 ---
 
-## Work with the GPT-3.5-Turbo and GPT-4 models
+## Work with chat completion models
 
-The following code snippet shows the most basic way to use the GPT-3.5-Turbo and GPT-4 models with the Chat Completion API. If this is your first time using these models programmatically, we recommend that you start with the [GPT-3.5-Turbo and GPT-4 quickstart](../chatgpt-quickstart.md).
+The following code snippet shows the most basic way to interact with models that use the Chat Completion API. If this is your first time using these models programmatically, we recommend that you start with the [chat completions quickstart](../chatgpt-quickstart.md).
 
 > [!NOTE]  
 > In the Azure OpenAI documentation, we refer to GPT-3.5-Turbo and GPT-35-Turbo interchangeably. The official name of the model on OpenAI is `gpt-3.5-turbo`. For Azure OpenAI, because of Azure-specific character constraints, the underlying model name is `gpt-35-turbo`.