Merge pull request #278147 from MicrosoftDocs/main

6/13/2024 AM Publish

Author: Taojunshen

articles/ai-services/openai/assistants-reference.md

@@ -5,7 +5,7 @@ description: Learn how to use Azure OpenAI's Python & REST API with Assistants.
 manager: nitinme
 ms.service: azure-ai-openai
 ms.topic: conceptual
-ms.date: 05/22/2024
+ms.date: 06/13/2024
 author: mrbullwinkle
 ms.author: mbullwin
 recommendations: false
@@ -35,7 +35,7 @@ Create an assistant with a model and instructions.
 | name | string or null | Optional | The name of the assistant. The maximum length is 256 characters.|
 | description| string or null | Optional | The description of the assistant. The maximum length is 512 characters.|
 | instructions | string or null | Optional | The system instructions that the assistant uses. The maximum length is 256,000 characters.|
-| tools | array | Optional | Defaults to []. A list of tools enabled on the assistant. There can be a maximum of 128 tools per assistant. Tools can currently be of types `code_interpreter`, or `function`.|
+| tools | array | Optional | Defaults to []. A list of tools enabled on the assistant. There can be a maximum of 128 tools per assistant. Tools can currently be of types `code_interpreter`, or `function`. A `function` description can be a maximum of 1,024 characters. |
 | file_ids | array | Optional | Defaults to []. A list of file IDs attached to this assistant. There can be a maximum of 20 files attached to the assistant. Files are ordered by their creation date in ascending order.|
 | metadata | map | Optional | Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format. Keys can be a maximum of 64 characters long and values can be a maximum of 512 characters long.|
 | temperature | number or null | Optional | Defaults to 1. Determines what sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. |
@@ -360,7 +360,7 @@ Modifies an assistant.
 | `name` | string or null | Optional | The name of the assistant. The maximum length is 256 characters. |
 | `description` | string or null | Optional | The description of the assistant. The maximum length is 512 characters. |
 | `instructions` | string or null | Optional | The system instructions that the assistant uses. The maximum length is 32768 characters. |
-| `tools` | array | Optional | Defaults to []. A list of tools enabled on the assistant. There can be a maximum of 128 tools per assistant. Tools can be of types code_interpreter, or function. |
+| `tools` | array | Optional | Defaults to []. A list of tools enabled on the assistant. There can be a maximum of 128 tools per assistant. Tools can be of types code_interpreter, or function. A `function` description can be a maximum of 1,024 characters. |
 | `file_ids` | array | Optional | Defaults to []. A list of File IDs attached to this assistant. There can be a maximum of 20 files attached to the assistant. Files are ordered by their creation date in ascending order. If a file was previously attached to the list but does not show up in the list, it will be deleted from the assistant. |
 | `metadata` | map | Optional | Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format. Keys can be a maximum of 64 characters long and values can be a maximum of 512 characters long. |
 
@@ -517,7 +517,7 @@ Assistants use the [same API for file upload as fine-tuning](/rest/api/azureopen
 | `description` | string or null | The description of the assistant. The maximum length is 512 characters.|
 | `model` | string | Name of the model deployment name to use.|
 | `instructions` | string or null | The system instructions that the assistant uses. The maximum length is 32768 characters.|
-| `tools` | array | A list of tool enabled on the assistant. There can be a maximum of 128 tools per assistant. Tools can be of types code_interpreter, or function.|
+| `tools` | array | A list of tool enabled on the assistant. There can be a maximum of 128 tools per assistant. Tools can be of types code_interpreter, or function. A `function` description can be a maximum of 1,024 characters.|
 | `file_ids` | array | A list of file IDs attached to this assistant. There can be a maximum of 20 files attached to the assistant. Files are ordered by their creation date in ascending order.|
 | `metadata` | map | Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format. Keys can be a maximum of 64 characters long and values can be a maximum of 512 characters long.|
 

articles/ai-services/openai/quotas-limits.md

@@ -27,6 +27,7 @@ The following sections provide you with a quick guide to the default quotas and
 | OpenAI resources per region per Azure subscription | 30 |
 | Default DALL-E 2 quota limits | 2 concurrent requests |
 | Default DALL-E 3 quota limits| 2 capacity units (6 requests per minute)|
+| Default Whisper quota limits | 3 requests per minute |
 | Maximum prompt tokens per request | Varies per model. For more information, see [Azure OpenAI Service models](./concepts/models.md)|
 | Max fine-tuned model deployments | 5 |
 | Total number of training jobs per resource | 100 |
@@ -48,6 +49,7 @@ The following sections provide you with a quick guide to the default quotas and
 | GPT-4o max images per request (# of images in the messages array/conversation history) | 10 |
 | GPT-4 `vision-preview` & GPT-4 `turbo-2024-04-09` default max tokens | 16 <br><br> Increase the `max_tokens` parameter value to avoid truncated responses. GPT-4o max tokens defaults to 4096. |
 
+
 ## Regional quota limits
 
 [!INCLUDE [Quota](./includes/model-matrix/quota.md)]
@@ -99,7 +101,7 @@ If your Azure subscription is linked to certain [offer types](https://azure.micr
 |Azure for Students, Free Trials | 1 K (all models)|
 | Monthly credit card based accounts <sup>1</sup> | GPT 3.5 Turbo Series: 30 K <br> GPT-4 series: 8 K  <br> |
 
-<sup>1</sup>This currently applies to [offer type 0003P](https://azure.microsoft.com/support/legal/offer-details/)
+<sup>1</sup> This currently applies to [offer type 0003P](https://azure.microsoft.com/support/legal/offer-details/)
 
 In the Azure portal you can view what offer type is associated with your subscription by navigating to your subscription and checking the subscriptions overview pane. Offer type corresponds to the plan field in the subscription overview.
 

articles/ai-services/openai/whats-new.md

@@ -10,7 +10,7 @@ ms.custom:
   - ignite-2023
   - references_regions
 ms.topic: whats-new
-ms.date: 06/11/2024
+ms.date: 06/13/2024
 recommendations: false
 ---
 
@@ -20,6 +20,10 @@ This article provides a summary of the latest releases and major documentation u
 
 ## June 2024
 
+### Token based billing for fine-tuning
+
+* Azure OpenAI fine-tuning billing is now based on the number of tokens in your training file – instead of the total elapsed training time. This can result in a significant cost reduction for some training runs, and makes estimating fine-tuning costs much easier. To learn more, you can consult the [official announcement](https://techcommunity.microsoft.com/t5/ai-azure-ai-services-blog/pricing-update-token-based-billing-for-fine-tuning-training/ba-p/4164465).
+
 ### GPT-4o released in new regions
 
 * GPT-4o is now also available in:

articles/azure-arc/resource-bridge/includes/network-requirements.md

@@ -45,11 +45,13 @@ The firewall and proxy URLs below must be allowlisted in order to enable communi
 
 ## Inbound connectivity requirements
 
-The following ports must be allowlisted in your firewall/proxy to enable communication between the management machine, Appliance VM IPs, and Control Plane IPs. Ensure these ports are open to facilitate the deployment and maintenance of Arc resource bridge.
+Communication between the following ports must be allowed from the management machine, Appliance VM IPs, and Control Plane IPs. Ensure these ports are open and that traffic is not being routed through a proxy to facilitate the deployment and maintenance of Arc resource bridge. 
 
-|**Service**|**Port**|**URL**|**Direction**|**Notes**|
+|**Service**|**Port**|**IP/machine**|**Direction**|**Notes**|
 |--|--|--|--|--|
 |SSH| 22 | `appliance VM IPs` and `Management machine` | Bidirectional | Used for deploying and maintaining the appliance VM.|
 |Kubernetes API server| 6443 | `appliance VM IPs` and `Management machine` | Bidirectional | Management of the appliance VM.|
-|HTTPS | 443 | `private cloud management console` | Management machine needs outbound connection. | Communication with management console (for example, VMware vCenter Server).|
+|SSH| 22 | `control plane IP` and `Management machine` | Bidirectional | Used for deploying and maintaining the appliance VM.|
+|Kubernetes API server| 6443 | `control plane IP` and `Management machine` | Bidirectional | Management of the appliance VM.|
+|HTTPS | 443 | `private cloud control plane address` and `Management machine` | Management machine needs outbound connection. | Communication with control plane (ex: VMware vCenter address).|
 

articles/azure-arc/resource-bridge/troubleshoot-resource-bridge.md

@@ -41,6 +41,22 @@ az arcappliance get-credentials -n <Arc resource bridge name> -g <resource group
 az arcappliance logs vmware --kubeconfig kubeconfig --out-dir <path to specified output directory>
    ```
 
+### Download/upload connectivity was not successful
+If your network speed is slow you may be unable to successfully download the Arc resource bridge VM image and this error may occur: `ErrorCode: ValidateKvaError, Error: Pre-deployment validation of your download/upload connectivity was not successful. Timeout error occurred during download and preparation of appliance image to the on-premises fabric storage. Common causes of this timeout error are slow network download/upload speeds, a proxy limiting the network speed or slow storage performance.`
+
+If the error is due to slow network speed impacting upload, a workaround is to create a VM directly on the on-premises private cloud and then run the Arc resource bridge deployment script from that VM. This workaround ensures a faster upload of the image to the datastore.
+
+
+### Context timed out during phase `ApplyingKvaImageOperator`
+You may receive the following error while deploying Arc resource bridge: `Deployment of the Arc resource bridge appliance VM timed out. Please collect logs with _az arcappliance logs_ and create a support ticket for help. To troubleshoot the error, refer to aka.ms/arc-rb-error   { _errorCode_: _ContextError_, _errorResponse_: _{\n\_message\_: \_Context timed out during phase _ApplyingKvaImageOperator_\_\n}_ }`
+
+This error typically occurs when trying to download the `KVAIO` image (400 MB compressed) over a network that is slow or experiencing intermittent connectivity. The `KVAIO` controller manager is waiting for the image download to complete and times out. You may want to check that your network speed between the Arc resource bridge VM and Microsoft Container Registry (`mcr.microsoft.com`) is stable and at least 2 Mbps. If your network connectivity and speed are stable and you are still getting this error, wait at least 30 minutes before you re-try as Microsoft Container Registry may be receiving a high volume of traffic.
+
+### Context timed out during phase `WaitingForAPIServer`
+When deploying Arc resource bridge, you may receive the error: `Deployment of the Arc resource bridge appliance VM timed out. Please collect logs with _az arcappliance logs_ and create a support ticket for help. To troubleshoot the error, refer to aka.ms/arc-rb-error   { _errorCode_: _ContextError_, _errorResponse_: _{\n\_message\_: \_Context timed out during phase _WaitingForAPIServer`
+
+This error indicates that the deployment machine is unable to contact the control plane IP for Arc resource bridge within the time limit. Common causes of the error are often networking related, such as communication between the deployment machine and control plane IP being routed through a proxy. Traffic from the deployment machine to the control plane and the appliance VM IPs should not pass through proxy even if there is one. Another cause for this error is if a firewall is closing access to port 6443 and port 22 between the deployment machine and control plane IP or the deployment machine and appliance VM IPs.
+
 ### Arc resource bridge is offline
 
 If the resource bridge is offline, this is typically due to a networking change in the infrastructure, environment or cluster that stops the appliance VM from being able to  communicate with its counterpart Azure resource. If you're unable to determine what changed, you can reboot the appliance VM, collect logs and submit a support ticket for further investigation. 
@@ -55,7 +71,7 @@ In this release, all the parameters are specified at time of creation. To update
 
 ### Appliance Network Unavailable 
 
-If Arc resource bridge is experiencing a network problem, you may see an "Appliance Network Unavailable" error. In general, any network or infrastructure connectivity issue to the appliance VM may cause this error. This error can also surface as "Error while dialing dial tcp xx.xx.xxx.xx:55000: connect: no route to host". The problem could be that communication from the host to the Arc resource bridge VM needs to be opened over TCP port 22 with the help of your network administrator. It could be that there was a temporary network issue not allowing the host to reach the Arc resource bridge VM and once the network issue is resolved, you can retry the operation. You can also check that the appliance VM for Arc resource bridge isn't stopped or offline. In the case of Azure Stack HCI, the host storage may be full and the storage needs to be addressed. 
+If Arc resource bridge is experiencing a network problem, you may see an "Appliance Network Unavailable" error. In general, any network or infrastructure connectivity issue to the appliance VM may cause this error. This error can also surface as "Error while dialing dial tcp xx.xx.xxx.xx:55000: connect: no route to host". The problem could be that communication from the host to the Arc resource bridge VM needs to be opened over TCP port 22 with the help of your network administrator. A temporary network issue may not allow the host to reach the Arc resource bridge VM. Once the network issue is resolved, you can retry the operation. You can also check that the appliance VM for Arc resource bridge isn't stopped or offline. In the case of Azure Stack HCI, the host storage may be full and the storage needs to be addressed. 
 
 ### Token refresh error
 
@@ -216,9 +232,9 @@ To install Azure Arc resource bridge on an Azure Stack HCI cluster, `az arcappli
 
 ## Azure Arc-enabled VMware VCenter issues
 
-### errorCode: CreateConfigKvaCustomerError, errorResponse: error getting the vsphere sdk
+### errorCode: CreateConfigKvaCustomerError, errorResponse: error getting the vsphere sdk client
 
-For errors with errorCode `CreateConfigKvaCustomerError` and errorResponse `error getting the vsphere sdk`, these errors occur when your deployment machine is trying to establish a TCP connection to your vCenter address but encounters a problem. You receive this errorCode and errorResponse if your vCenter address is incorrect (403 or 404 error) or if there's a network/proxy/firewall configuration blocking it (connection attempt failed). If you enter your vCenter address as a hostname and receive the error `no such host`, then your deployment machine isn't able to resolve the vCenter hostname via the client DNS. You may receive an error if the deployment machine is able to resolve the vCenter hostname but the deployment machine can't reach the IP address it received from DNS. Continuing along this flow, you may receive an error if the endpoint returned by DNS isn't your vCenter address, or if the traffic was intercepted by proxy. Finally, you may get an error if your deployment machine is able to communicate with your vCenter address, but the username or password is incorrect.
+For errors with errorCode `CreateConfigKvaCustomerError` and errorResponse `error getting the vsphere sdk client`, these errors occur when your deployment machine is trying to establish a TCP connection to your vCenter address but encounters a problem. You receive this errorCode and errorResponse if your vCenter address is incorrect (403 or 404 error) or if there's a network/proxy/firewall configuration blocking it (connection attempt failed). If you enter your vCenter address as a hostname and receive the error `no such host`, then your deployment machine isn't able to resolve the vCenter hostname via the client DNS. You may receive an error if the deployment machine is able to resolve the vCenter hostname but the deployment machine can't reach the IP address it received from DNS. You may receive an error if the endpoint returned by DNS isn't your vCenter address, or if the traffic was intercepted by proxy. Finally, you may get an error if your deployment machine is able to communicate with your vCenter address, but the username or password is incorrect.
 
 ### vSphere SDK client - Connection attempt failed
 

articles/azure-monitor/app/java-standalone-sampling-overrides.md

@@ -15,7 +15,7 @@ ms.reviewer: mmcc
 
 Sampling overrides allow you to override the [default sampling percentage](./java-standalone-config.md#sampling),
 for example:
- * Set the sampling percentage to 0 (or some small value) for noisy health checks.
+* Set the sampling percentage to 0 (or some small value) for noisy health checks.
  * Set the sampling percentage to 0 (or some small value) for noisy dependency calls.
  * Set the sampling percentage to 100 for an important request type (for example, `/login`)
    even though you have the default sampling configured to something lower.
@@ -42,7 +42,7 @@ To begin, create a configuration file named *applicationinsights.json*. Save it
 {
   "connectionString": "...",
   "sampling": {
-    "percentage": 10
+    "percentage": 10,
     "overrides": [
       {
         "telemetryType": "request",

articles/azure-monitor/essentials/diagnostic-settings.md

@@ -6,7 +6,7 @@ ms.author: robb
 services: azure-monitor
 ms.topic: conceptual
 ms.custom:
-ms.date: 03/12/2024
+ms.date: 06/13/2024
 ms.reviewer: lualderm
 ---
 
@@ -39,9 +39,9 @@ Information on these newer features is included in this article.
 
 There are three sources for diagnostic information:
 
-- **[Platform metrics](./metrics-supported.md)** are sent automatically to [Azure Monitor Metrics](./data-platform-metrics.md) by default and without configuration.
-- **[Platform logs](./platform-logs-overview.md)**  - provide detailed diagnostic and auditing information for Azure resources and the Azure platform they depend on.
-   - **Resource logs**  aren't collected until they're routed to a destination.
+- Platform metrics are sent automatically to [Azure Monitor Metrics](./data-platform-metrics.md) by default and without configuration. For more information on supported metrics, see [Supported metrics with Azure Monitor](./metrics-supported.md)
+- Platform logs provide detailed diagnostic and auditing information for Azure resources and the Azure platform they depend on.
+   - **Resource logs**  aren't collected until they're routed to a destination. For more information on supported logs, see [Supported Resource log categories for Azure Monitor](/azure/azure-monitor/reference/supported-logs/logs-index)
    - The **Activity log** provides information about resources from outside the resource, such as when the resource was created or deleted. Entries exist on their own but can be routed to other locations.
 
 ### Metrics