Skip to content

Commit 4a1251e

Browse files
authored
Merge branch 'MicrosoftDocs:main' into heidist-freshness
2 parents e608027 + 0019dfc commit 4a1251e

20 files changed

+262
-47
lines changed

articles/ai-foundry/agents/how-to/tools/azure-ai-search.md

Lines changed: 7 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -166,6 +166,13 @@ You can add the Azure AI Search tool to an agent programmatically using the code
166166

167167
1. The index is created and connected to the [Azure AI Search](/azure/search/) service. You can now use the index with the Azure AI Search tool in your agent. You can also use the index outside of the agent, such as the Azure AI Search REST API or SDKs.
168168

169+
170+
## Limitations
171+
172+
Currently, if you want to use the Azure AI Search tool in the Azure AI Foundry portal behind a virtual network, you must create an agent using the SDK or REST API. After creating the agent in a code-based manner, you can then use it in the portal.
173+
174+
The Azure AI Search tool can only include one search index. If you want to utilize multiple indexes, consider using [connected agents](../connected-agents.md) with an Azure AI search index configured with each agent.
175+
169176
## Next steps
170177

171178
* See examples on how to use the [Azure AI Search tool](azure-ai-search-samples.md).

articles/ai-foundry/concepts/prompt-flow.md

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -7,6 +7,7 @@ ms.custom:
77
- ignite-2023
88
- build-2024
99
- ignite-2024
10+
- hub-only
1011
ms.topic: concept-article
1112
ms.date: 06/30/2025
1213
ms.reviewer: none
@@ -24,6 +25,8 @@ Prompt flow is a development tool designed to streamline the entire development
2425

2526
Prompt flow is available independently as an open-source project on [GitHub](https://github.com/microsoft/promptflow), with its own SDK and [VS Code extension](https://marketplace.visualstudio.com/items?itemName=prompt-flow.prompt-flow). Prompt flow is also available and recommended to use as a feature within both [Azure AI Foundry](https://ai.azure.com/?cid=learnDocs) and [Azure Machine Learning studio](https://ml.azure.com). This set of documentation focuses on prompt flow in Azure AI Foundry portal.
2627

28+
[!INCLUDE [hub-only-prereq](../includes/uses-hub-only.md)]
29+
2730
Definitions:
2831

2932
- *Prompt flow* is a feature that can be used to generate, customize, or run a flow.

articles/ai-foundry/foundry-models/quotas-limits.md

Lines changed: 35 additions & 27 deletions
Original file line numberDiff line numberDiff line change
@@ -6,19 +6,19 @@ author: msakande
66
ms.service: azure-ai-model-inference
77
ms.custom: ignite-2024, github-universe-2024
88
ms.topic: concept-article
9-
ms.date: 05/19/2025
9+
ms.date: 08/14/2025
1010
ms.author: mopeakande
11-
ms.reviewer: fasantia
12-
reviewer: santiagxf
11+
ms.reviewer: shiyingfu
12+
reviewer: swingfu
1313
---
1414

1515
# Azure AI Foundry Models quotas and limits
1616

17-
This article contains a quick reference and a detailed description of the quotas and limits for Azure AI Foundry Models. For quotas and limits specific to the Azure OpenAI in Foundry Models, see [Quota and limits in Azure OpenAI](../openai/quotas-limits.md).
17+
This article provides a quick reference and detailed description of the quotas and limits for Azure AI Foundry Models. For quotas and limits specific to the Azure OpenAI in Foundry Models, see [Quota and limits in Azure OpenAI](../openai/quotas-limits.md).
1818

1919
## Quotas and limits reference
2020

21-
Azure uses quotas and limits to prevent budget overruns due to fraud, and to honor Azure capacity constraints. Consider these limits as you scale for production workloads. The following sections provide you with a quick guide to the default quotas and limits that apply to Azure AI model's inference service in Azure AI Foundry:
21+
Azure uses quotas and limits to prevent budget overruns due to fraud and to honor Azure capacity constraints. Consider these limits as you scale for production workloads. The following sections provide a quick guide to the default quotas and limits that apply to Azure AI model inference service in Azure AI Foundry:
2222

2323
### Resource limits
2424

@@ -30,58 +30,66 @@ Azure uses quotas and limits to prevent budget overruns due to fraud, and to hon
3030

3131
### Rate limits
3232

33-
| Limit name | Applies to | Limit value |
34-
| -------------------- | ------------------- | ----------- |
35-
| Tokens per minute | Azure OpenAI models | Varies per model and SKU. See [limits for Azure OpenAI](../openai/quotas-limits.md). |
36-
| Requests per minute | Azure OpenAI models | Varies per model and SKU. See [limits for Azure OpenAI](../openai/quotas-limits.md). |
37-
| Tokens per minute | DeepSeek-R1<br />DeepSeek-V3-0324 | 5,000,000 |
38-
| Requests per minute | DeepSeek-R1<br />DeepSeek-V3-0324 | 5,000 |
39-
| Concurrent requests | DeepSeek-R1<br />DeepSeek-V3-0324 | 300 |
40-
| Tokens per minute | Rest of models | 400,000 |
41-
| Requests per minute | Rest of models | 1,000 |
42-
| Concurrent requests | Rest of models | 300 |
33+
The following table lists limits for Foundry Models for the following rates:
4334

44-
You can [request increases to the default limits](#request-increases-to-the-default-limits). Due to high demand, limit increase requests can be submitted and evaluated per request.
35+
- Tokens per minute
36+
- Requests per minute
37+
- Concurrent request
38+
39+
| Models | Tokens per minute | Requests per minute | Concurrent requests |
40+
| ---------------------------------------------------------------------- | --------------------------------------------------- | ----------------------------------------------------- | -------------------- |
41+
| Azure OpenAI models | Varies per model and SKU. See [limits for Azure OpenAI](../openai/quotas-limits.md). | Varies per model and SKU. See [limits for Azure OpenAI](../openai/quotas-limits.md). | not applicable |
42+
| - DeepSeek-R1<br />- DeepSeek-V3-0324 | 5,000,000 | 5,000 | 300 |
43+
| - Llama 3.3 70B Instruct<br />- Llama-4-Maverick-17B-128E-Instruct-FP8<br />- Grok 3<br />- Grok 3 mini | 400,000 | 1,000 | 300 |
44+
| - Flux-Pro 1.1<br />- Flux.1-Kontext Pro | not applicable | 2 capacity units (6 requests per minute) | not applicable |
45+
| Rest of models | 400,000 | 1,000 | 300 |
46+
47+
To increase your quota:
48+
49+
- For Azure OpenAI, use [Azure AI Foundry Service: Request for Quota Increase](https://customervoice.microsoft.com/Pages/ResponsePage.aspx?id=v4j5cvGGr0GRqy180BHbR4xPXO648sJKt4GoXAed-0pUMFE1Rk9CU084RjA0TUlVSUlMWEQzVkJDNCQlQCN0PWcu) to submit your request.
50+
- For other models, see [request increases to the default limits](#request-increases-to-the-default-limits).
51+
52+
Due to high demand, we evaluate limit increase requests per request.
4553

4654
### Other limits
4755

4856
| Limit name | Limit value |
4957
|--|--|
5058
| Max number of custom headers in API requests<sup>1</sup> | 10 |
5159

52-
<sup>1</sup> Our current APIs allow up to 10 custom headers, which are passed through the pipeline, and returned. We have noticed some customers now exceed this header count resulting in HTTP 431 errors. There is no solution for this error, other than to reduce header volume. **In future API versions we will no longer pass through custom headers**. We recommend customers not depend on custom headers in future system architectures.
60+
<sup>1</sup> Our current APIs allow up to 10 custom headers, which the pipeline passes through and returns. If you exceed this header count, your request results in an HTTP 431 error. To resolve this error, reduce the header volume. **Future API versions won't pass through custom headers**. We recommend that you don't depend on custom headers in future system architectures.
5361

5462
## Usage tiers
5563

56-
Global Standard deployments use Azure's global infrastructure, dynamically routing customer traffic to the data center with best availability for the customer's inference requests. This enables more consistent latency for customers with low to medium levels of traffic. Customers with high sustained levels of usage might see more variabilities in response latency.
64+
Global Standard deployments use Azure's global infrastructure to dynamically route customer traffic to the data center with best availability for the customer's inference requests. This infrastructure enables more consistent latency for customers with low to medium levels of traffic. Customers with high sustained levels of usage might see more variabilities in response latency.
5765

5866
The Usage Limit determines the level of usage above which customers might see larger variability in response latency. A customer's usage is defined per model and is the total tokens consumed across all deployments in all subscriptions in all regions for a given tenant.
5967

6068
## Request increases to the default limits
6169

62-
Limit increase requests can be submitted and evaluated per request. [Open an online customer support request](https://portal.azure.com/#blade/Microsoft_Azure_Support/HelpAndSupportBlade/newsupportrequest/). When requesting for endpoint limit increase, provide the following information:
70+
You can submit limit increase requests, which we evaluate one at a time. [Open an online customer support request](https://portal.azure.com/#blade/Microsoft_Azure_Support/HelpAndSupportBlade/newsupportrequest/). When you request an endpoint limit increase, provide the following information:
6371

64-
1. When opening the support request, select **Service and subscription limits (quotas)** as the **Issue type**.
72+
1. Select **Service and subscription limits (quotas)** as the **Issue type** when you open the support request.
6573

66-
1. Select the subscription of your choice.
74+
1. Select the subscription you want to use.
6775

6876
1. Select **Cognitive Services** as **Quota type**.
6977

7078
1. Select **Next**.
7179

72-
1. On the **Additional details** tab, you need to provide detailed reasons for the limit increase in order for your request to be processed. Be sure to add the following information into the reason for limit increase:
80+
1. On the **Additional details** tab, provide detailed reasons for the limit increase so that your request can be processed. Be sure to add the following information to the reason for limit increase:
7381

7482
* Model name, model version (if applicable), and deployment type (SKU).
7583
* Description of your scenario and workload.
7684
* Rationale for the requested increase.
77-
* Provide the target throughput: Tokens per minute, requests per minute, etc.
78-
* Provide planned time plan (by when you need increased limits).
85+
* Target throughput: Tokens per minute, requests per minute, and other relevant metrics.
86+
* Planned time plan (by when you need increased limits).
7987

80-
1. Finally, select **Save and continue** to continue.
88+
1. Select **Save and continue**.
8189

82-
## General best practices to remain within rate limits
90+
## General best practices to stay within rate limits
8391

84-
To minimize issues related to rate limits, it's a good idea to use the following techniques:
92+
To minimize issues related to rate limits, use the following techniques:
8593

8694
- Implement retry logic in your application.
8795
- Avoid sharp changes in the workload. Increase the workload gradually.

articles/ai-foundry/how-to/flow-bulk-test-evaluation.md

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -6,6 +6,7 @@ ms.service: azure-ai-foundry
66
ms.custom:
77
- ignite-2023
88
- build-2024
9+
- hub-only
910
ms.topic: how-to
1011
ms.date: 5/21/2024
1112
ms.reviewer: none
@@ -32,6 +33,8 @@ In this article you learn to:
3233

3334
## Prerequisites
3435

36+
[!INCLUDE [hub-only-prereq](../includes/hub-only-prereq.md)]
37+
3538
For a batch run and to use an evaluation method, you need to have the following ready:
3639

3740
- A test dataset for batch run. Your dataset should be in one of these formats: `.csv`, `.tsv`, or `.jsonl`. Your data should also include headers that match the input names of your flow. If your flow inputs include a complex structure like a list or dictionary, use `jsonl` format to represent your data.

articles/ai-foundry/how-to/flow-develop-evaluation.md

Lines changed: 5 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -6,6 +6,7 @@ ms.service: azure-ai-foundry
66
ms.custom:
77
- ignite-2023
88
- build-2024
9+
- hub-only
910
ms.topic: how-to
1011
ms.date: 3/31/2025
1112
ms.reviewer: mithigpe
@@ -26,6 +27,10 @@ In prompt flow, you can customize or create your own evaluation flow tailored to
2627
- How to develop an evaluation method.
2728
- Understand inputs, outputs, and logging metrics for prompt flow evaluations.
2829

30+
## Prerequisites
31+
32+
[!INCLUDE [hub-only-prereq](../includes/hub-only-prereq.md)]
33+
2934
## Starting to develop an evaluation method
3035

3136
There are two ways to develop your own evaluation methods:

articles/ai-foundry/how-to/flow-process-image.md

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -5,6 +5,7 @@ description: Learn how to use images in prompt flow.
55
ms.service: azure-ai-foundry
66
ms.custom:
77
- build-2024
8+
- hub-only
89
ms.topic: how-to
910
ms.date: 06/30/2025
1011
ms.reviewer: none
@@ -28,6 +29,8 @@ In this article, you learn:
2829
> - How to create a batch run using image data.
2930
> - How to consume online endpoint with image data.
3031
32+
[!INCLUDE [uses-hub-only](../includes/uses-hub-only.md)]
33+
3134
## Image type in prompt flow
3235

3336
Prompt flow input and output support Image as a new data type.

articles/ai-foundry/how-to/flow-tune-prompts-using-variants.md

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -6,6 +6,7 @@ ms.service: azure-ai-foundry
66
ms.custom:
77
- ignite-2023
88
- build-2024
9+
- hub-only
910
ms.topic: how-to
1011
ms.date: 3/31/2025
1112
ms.reviewer: none
@@ -25,6 +26,8 @@ Crafting a good prompt is a challenging task that requires much creativity, clar
2526

2627
Variants can help you test the model’s behavior under different conditions, such as different wording, formatting, context, temperature, or top-k. You can compare and find the best prompt and configuration that maximizes the model's accuracy, diversity, or coherence.
2728

29+
[!INCLUDE [uses-hub-only](../includes/uses-hub-only.md)]
30+
2831
## Variants in Prompt flow
2932

3033
With prompt flow, you can use variants to tune your prompt. A variant refers to a specific version of a tool node that has distinct settings. Currently, variants are supported only in the [LLM tool](prompt-flow-tools/llm-tool.md). For example, in the LLM tool, a new variant can represent either a different prompt content or different connection settings.

articles/ai-foundry/how-to/prompt-flow-tools/embedding-tool.md

Lines changed: 6 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -6,6 +6,7 @@ ms.service: azure-ai-foundry
66
ms.custom:
77
- ignite-2023
88
- build-2024
9+
- hub-only
910
ms.topic: reference
1011
ms.date: 6/30/2025
1112
ms.reviewer: none
@@ -21,9 +22,13 @@ ms.update-cycle: 180-days
2122

2223
The prompt flow Embedding tool enables you to convert text into dense vector representations for various natural language processing tasks.
2324

24-
> [!NOTE]
25+
> [!TIP]
2526
> For chat and completion tools, learn more about the large language model [(LLM) tool](llm-tool.md).
2627
28+
## Prerequisites
29+
30+
[!INCLUDE [hub-only-prereq](../../includes/hub-only-prereq.md)]
31+
2732
## Build with the Embedding tool
2833

2934
1. Create or open a flow in [Azure AI Foundry](https://ai.azure.com/?cid=learnDocs). For more information, see [Create a flow](../flow-develop.md).

articles/ai-foundry/how-to/prompt-flow-tools/index-lookup-tool.md

Lines changed: 5 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -5,6 +5,7 @@ description: This article introduces you to the Index Lookup tool for flows in A
55
ms.service: azure-ai-foundry
66
ms.custom:
77
- build-2024
8+
- hub-only
89
ms.topic: reference
910
ms.date: 6/30/2025
1011
ms.reviewer: none
@@ -20,6 +21,10 @@ ms.update-cycle: 180-days
2021

2122
The prompt flow Index Lookup tool enables the use of common vector indices (such as Azure AI Search, Faiss, and Pinecone) for retrieval augmented generation in prompt flow. The tool automatically detects the indices in the workspace and allows the selection of the index to be used in the flow.
2223

24+
## Prerequisites
25+
26+
[!INCLUDE [hub-only-prereq](../../includes/hub-only-prereq.md)]
27+
2328
## Build with the Index Lookup tool
2429

2530
1. Create or open a flow in [Azure AI Foundry](https://ai.azure.com/?cid=learnDocs). For more information, see [Create a flow](../flow-develop.md).

articles/ai-foundry/how-to/prompt-flow-tools/llm-tool.md

Lines changed: 4 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -6,6 +6,7 @@ ms.service: azure-ai-foundry
66
ms.custom:
77
- ignite-2023
88
- build-2024
9+
- hub-only
910
ms.topic: reference
1011
ms.date: 6/30/2025
1112
ms.reviewer: none
@@ -21,11 +22,13 @@ ms.update-cycle: 180-days
2122

2223
To use large language models (LLMs) for natural language processing, you use the prompt flow LLM tool.
2324

24-
> [!NOTE]
25+
> [!TIP]
2526
> For embeddings to convert text into dense vector representations for various natural language processing tasks, see [Embedding tool](embedding-tool.md).
2627
2728
## Prerequisites
2829

30+
[!INCLUDE [hub-only-prereq](../../includes/hub-only-prereq.md)]
31+
2932
Prepare a prompt as described in the [Prompt tool](prompt-tool.md#prerequisites) documentation. The LLM tool and Prompt tool both support [Jinja](https://jinja.palletsprojects.com/en/stable/) templates. For more information and best practices, see [Prompt engineering techniques](../../openai/concepts/advanced-prompt-engineering.md).
3033

3134
## Build with the LLM tool

0 commit comments

Comments
 (0)