Merge pull request #308 from MicrosoftDocs/main

ttorble · web-flow · commit 90befd618b13 · 2024-09-17T12:03:54.000+01:00
Publish to live, Tuesday 4 AM PST, 9/17
diff --git a/articles/ai-services/custom-vision-service/overview.md b/articles/ai-services/custom-vision-service/overview.md
@@ -18,8 +18,7 @@ keywords: image recognition, image identifier, image recognition app, custom vis
 
 Azure AI Custom Vision is an image recognition service that lets you build, deploy, and improve your own **image identifier** models. An image identifier applies labels to images, according to their visual characteristics. Each label represents a classification or object. Custom Vision allows you to specify your own labels and train custom models to detect them.
 
-> [!TIP]
-> The Azure AI vision Image Analysis API, based on Florence foundational model, now supports custom models with few-shot learning capability. [Use Image Analysis 4.0](../computer-vision/how-to/model-customization.md) to create custom image identifier models using the latest technology from Azure. To migrate a Custom Vision project to the new Image Analysis 4.0 system, see the [Migration guide](../computer-vision/how-to/migrate-from-custom-vision.md). To compare the two services, see the [Comparison page](./concepts/compare-alternatives.md).
+
 
 
 You can use Custom Vision through a client library SDK, REST API, or through the [Custom Vision web portal](https://customvision.ai/). Follow a quickstart to get started.
diff --git a/articles/ai-services/openai/includes/fine-tuning-studio.md b/articles/ai-services/openai/includes/fine-tuning-studio.md
@@ -65,9 +65,9 @@ Different model types require a different format of training data.
 
 # [chat completion models](#tab/turbo)
 
-The training and validation data you use **must** be formatted as a JSON Lines (JSONL) document. For `gpt-35-turbo-0613` the fine-tuning dataset must be formatted in the conversational format that is used by the [Chat completions](../how-to/chatgpt.md) API.
+The training and validation data you use **must** be formatted as a JSON Lines (JSONL) document. For `gpt-35-turbo` (all versions), `gpt-4`, `gpt-4o`, and `gpt-4o-mini`, the fine-tuning dataset must be formatted in the conversational format that is used by the [Chat completions](../how-to/chatgpt.md) API.
 
-If you would like a step-by-step walk-through of fine-tuning a `gpt-35-turbo-0613` model please refer to the [Azure OpenAI fine-tuning tutorial.](../tutorials/fine-tune.md)
+If you would like a step-by-step walk-through of fine-tuning a `gpt-4o-mini` (2024-07-18) model please refer to the [Azure OpenAI fine-tuning tutorial.](../tutorials/fine-tune.md)
 
 ### Example file format
 
diff --git a/articles/ai-services/openai/media/tutorials/fine-tuning/studio-deployment-status.png b/articles/ai-services/openai/media/tutorials/fine-tuning/studio-deployment-status.png
diff --git a/articles/ai-services/openai/tutorials/fine-tune.md b/articles/ai-services/openai/tutorials/fine-tune.md
@@ -755,7 +755,7 @@ This command isn't available in the 0.28.1 OpenAI Python library. Upgrade to the
     {
       "id": "ftchkpt-148ab69f0a404cf9ab55a73d51b152de",
       "created_at": 1715743077,
-      "fine_tuned_model_checkpoint": "gpt-4o-mini-2024-07-18.ft-372c72db22c34e6f9ccb62c26ee0fbd9",
+      "fine_tuned_model_checkpoint": "gpt-4o-mini-2024-07-18.ft-0e208cf33a6a466994aff31a08aba678",
       "fine_tuning_job_id": "ftjob-372c72db22c34e6f9ccb62c26ee0fbd9",
       "metrics": {
         "full_valid_loss": 1.8258173013035255,
@@ -772,7 +772,7 @@ This command isn't available in the 0.28.1 OpenAI Python library. Upgrade to the
     {
       "id": "ftchkpt-e559c011ecc04fc68eaa339d8227d02d",
       "created_at": 1715743013,
-      "fine_tuned_model_checkpoint": "gpt-4o-mini-2024-07-18.ft-372c72db22c34e6f9ccb62c26ee0fbd9:ckpt-step-90",
+      "fine_tuned_model_checkpoint": "gpt-4o-mini-2024-07-18.ft-0e208cf33a6a466994aff31a08aba678:ckpt-step-90",
       "fine_tuning_job_id": "ftjob-372c72db22c34e6f9ccb62c26ee0fbd9",
       "metrics": {
         "full_valid_loss": 1.7958603267428241,
@@ -789,7 +789,7 @@ This command isn't available in the 0.28.1 OpenAI Python library. Upgrade to the
     {
       "id": "ftchkpt-8ae8beef3dcd4dfbbe9212e79bb53265",
       "created_at": 1715742984,
-      "fine_tuned_model_checkpoint": "gpt-4o-mini-2024-07-18.ft-372c72db22c34e6f9ccb62c26ee0fbd9:ckpt-step-80",
+      "fine_tuned_model_checkpoint": "gpt-4o-mini-2024-07-18.ft-0e208cf33a6a466994aff31a08aba678:ckpt-step-80",
       "fine_tuning_job_id": "ftjob-372c72db22c34e6f9ccb62c26ee0fbd9",
       "metrics": {
         "full_valid_loss": 1.6909511662736725,
@@ -850,7 +850,7 @@ Alternatively, you can deploy your fine-tuned model using any of the other commo
 | resource_group | The resource group name for your Azure OpenAI resource |
 | resource_name | The Azure OpenAI resource name |
 | model_deployment_name | The custom name for your new fine-tuned model deployment. This is the name that will be referenced in your code when making chat completion calls. |
-| fine_tuned_model | Retrieve this value from your fine-tuning job results in the previous step. It will look like `gpt-4o-mini-2024-07-18.ft-b044a9d3cf9c4228b5d393567f693b83`. You'll need to add that value to the deploy_data json. |
+| fine_tuned_model | Retrieve this value from your fine-tuning job results in the previous step. It will look like `gpt-4o-mini-2024-07-18.ft-0e208cf33a6a466994aff31a08aba678`. You'll need to add that value to the deploy_data json. |
 
 [!INCLUDE [Fine-tuning deletion](../includes/fine-tune.md)]
 
@@ -874,7 +874,7 @@ deploy_data = {
     "properties": {
         "model": {
             "format": "OpenAI",
-            "name": "<YOUR_FINE_TUNED_MODEL>", #retrieve this value from the previous call, it will look like gpt-4o-mini-2024-07-18.ft-b044a9d3cf9c4228b5d393567f693b83
+            "name": "<YOUR_FINE_TUNED_MODEL>", #retrieve this value from the previous call, it will look like gpt-4o-mini-2024-07-18.ft-0e208cf33a6a466994aff31a08aba678
             "version": "1"
         }
     }
@@ -894,7 +894,7 @@ print(r.json())
 
 You can check on your deployment progress in the Azure OpenAI Studio:
 
-:::image type="content" source="../media/tutorials/fine-tuning/status.png" alt-text="Screenshot of the initial DataFrame table results from the CSV file." lightbox="../media/tutorials/fine-tuning/status.png":::
+:::image type="content" source="../media/tutorials/fine-tuning/studio-deployment-status.png" alt-text="Screenshot of Deployment progress on Azure OpenAI Studio." lightbox="../media/tutorials/fine-tuning/studio-deployment-status.png":::
 
 It isn't uncommon for this process to take some time to complete when dealing with deploying fine-tuned models.
 
@@ -968,7 +968,7 @@ You can delete the deployment in [Azure OpenAI Studio](https://oai.azure.com/),
 
 ## Troubleshooting
 
-### How do I enable fine-tuning? Create a custom model is greyed out in Azure OpenAI Studio?
+### How do I enable fine-tuning? Create a custom model is grayed out in Azure OpenAI Studio
 
 In order to successfully access fine-tuning you need **Cognitive Services OpenAI Contributor assigned**. Even someone with high-level Service Administrator permissions would still need this account explicitly set in order to access fine-tuning. For more information please review the [role-based access control guidance](/azure/ai-services/openai/how-to/role-based-access-control#cognitive-services-openai-contributor).
 
diff --git a/articles/search/search-get-started-rag.md b/articles/search/search-get-started-rag.md
@@ -272,6 +272,28 @@ This section uses Visual Studio Code and Python to call the chat completion APIs
 
     You might also try the query without semantic ranking by setting `use_semantic_reranker=False` in the query parameters step. Semantic ranking can noticably improve the relevance of query results and the ability of the LLM to return useful information. Experimentation can help you decide whether it makes a difference for your content.
 
+## Troubleshooting errors
+
+To debug authentication errors, insert the following code before the step that calls the search engine and the LLM.
+
+```python
+import sys
+import logging # Set the logging level for all azure-storage-* libraries
+logger = logging.getLogger('azure.identity') 
+logger.setLevel(logging.DEBUG)
+
+handler = logging.StreamHandler(stream=sys.stdout)
+formatter = logging.Formatter('[%(levelname)s %(name)s] %(message)s')
+handler.setFormatter(formatter)
+logger.addHandler(handler)
+```
+
+Rerun the query script. You should now get INFO and DEBUG statements in the output that provide more detail about the issue.
+
+If you see output messages related to ManagedIdentityCredential and token acquisition failures, it could be that you have multiple tenants, and your Azure sign-in is using a tenant that doesn't have your search service. To get your tenant ID, search the Azure portal for "tenant properties".
+
+Run `az login --tenant <YOUR-TENANT-ID>` at a command prompt, and then rerun the script.
+
 ## Clean up
 
 When you're working in your own subscription, it's a good idea at the end of a project to identify whether you still need the resources you created. Resources left running can cost you money. You can delete resources individually or delete the resource group to delete the entire set of resources.
