Skip to content

Commit 1f3d621

Browse files
authored
Merge pull request #271617 from MicrosoftDocs/main
4/9/2024 AM Publish
2 parents 363d4bd + 3763fc2 commit 1f3d621

File tree

129 files changed

+255
-554
lines changed

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

129 files changed

+255
-554
lines changed
Lines changed: 23 additions & 22 deletions
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,7 @@
11
---
22
title: Azure OpenAI GPT-4 Turbo with Vision tool in Azure AI Studio
33
titleSuffix: Azure AI Studio
4-
description: This article introduces the Azure OpenAI GPT-4 Turbo with Vision tool for flows in Azure AI Studio.
4+
description: This article introduces you to the Azure OpenAI GPT-4 Turbo with Vision tool for flows in Azure AI Studio.
55
manager: scottpolly
66
ms.service: azure-ai-studio
77
ms.topic: how-to
@@ -15,26 +15,26 @@ author: lgayhardt
1515

1616
[!INCLUDE [Azure AI Studio preview](../../includes/preview-ai-studio.md)]
1717

18-
The prompt flow *Azure OpenAI GPT-4 Turbo with Vision* tool enables you to use your Azure OpenAI GPT-4 Turbo with Vision model deployment to analyze images and provide textual responses to questions about them.
18+
The prompt flow Azure OpenAI GPT-4 Turbo with Vision tool enables you to use your Azure OpenAI GPT-4 Turbo with Vision model deployment to analyze images and provide textual responses to questions about them.
1919

2020
## Prerequisites
2121

22-
- An Azure subscription - <a href="https://azure.microsoft.com/free/cognitive-services" target="_blank">Create one for free</a>.
22+
- An Azure subscription. <a href="https://azure.microsoft.com/free/cognitive-services" target="_blank">You can create one for free</a>.
2323
- Access granted to Azure OpenAI in the desired Azure subscription.
2424

25-
Currently, access to this service is granted only by application. You can apply for access to Azure OpenAI by completing the form at <a href="https://aka.ms/oai/access" target="_blank">https://aka.ms/oai/access</a>. Open an issue on this repo to contact us if you have an issue.
25+
Currently, you must apply for access to this service. To apply for access to Azure OpenAI, complete the form at <a href="https://aka.ms/oai/access" target="_blank">https://aka.ms/oai/access</a>. Open an issue on this repo to contact us if you have an issue.
2626

27-
- An [Azure AI hub resource](../../how-to/create-azure-ai-resource.md) with a GPT-4 Turbo with Vision model deployed in [one of the regions that support GPT-4 Turbo with Vision](../../../ai-services/openai/concepts/models.md#model-summary-table-and-region-availability). When you deploy from your project's **Deployments** page, select: `gpt-4` as the model name and `vision-preview` as the model version.
27+
- An [Azure AI hub resource](../../how-to/create-azure-ai-resource.md) with a GPT-4 Turbo with Vision model deployed in [one of the regions that support GPT-4 Turbo with Vision](../../../ai-services/openai/concepts/models.md#model-summary-table-and-region-availability). When you deploy from your project's **Deployments** page, select `gpt-4` as the model name and `vision-preview` as the model version.
2828

2929
## Build with the Azure OpenAI GPT-4 Turbo with Vision tool
3030

3131
1. Create or open a flow in [Azure AI Studio](https://ai.azure.com). For more information, see [Create a flow](../flow-develop.md).
3232
1. Select **+ More tools** > **Azure OpenAI GPT-4 Turbo with Vision** to add the Azure OpenAI GPT-4 Turbo with Vision tool to your flow.
3333

34-
:::image type="content" source="../../media/prompt-flow/azure-openai-gpt-4-vision-tool.png" alt-text="Screenshot of the Azure OpenAI GPT-4 Turbo with Vision tool added to a flow in Azure AI Studio." lightbox="../../media/prompt-flow/azure-openai-gpt-4-vision-tool.png":::
34+
:::image type="content" source="../../media/prompt-flow/azure-openai-gpt-4-vision-tool.png" alt-text="Screenshot that shows the Azure OpenAI GPT-4 Turbo with Vision tool added to a flow in Azure AI Studio." lightbox="../../media/prompt-flow/azure-openai-gpt-4-vision-tool.png":::
3535

3636
1. Select the connection to your Azure OpenAI Service. For example, you can select the **Default_AzureOpenAI** connection. For more information, see [Prerequisites](#prerequisites).
37-
1. Enter values for the Azure OpenAI GPT-4 Turbo with Vision tool input parameters described [here](#inputs). For example, you can use this example prompt:
37+
1. Enter values for the Azure OpenAI GPT-4 Turbo with Vision tool input parameters described in the [Inputs table](#inputs). For example, you can use this example prompt:
3838

3939
```jinja
4040
# system:
@@ -47,9 +47,10 @@ The prompt flow *Azure OpenAI GPT-4 Turbo with Vision* tool enables you to use y
4747
```
4848
4949
1. Select **Validate and parse input** to validate the tool inputs.
50-
1. Specify an image to analyze in the `image_input` input parameter. For example, you can upload an image or enter the URL of an image to analyze. Otherwise you can paste or drag and drop an image into the tool.
51-
1. Add more tools to your flow as needed, or select **Run** to run the flow.
52-
1. The outputs are described [here](#outputs).
50+
1. Specify an image to analyze in the `image_input` input parameter. For example, you can upload an image or enter the URL of an image to analyze. Otherwise, you can paste or drag and drop an image into the tool.
51+
1. Add more tools to your flow, as needed. Or select **Run** to run the flow.
52+
53+
The outputs are described in the [Outputs table](#outputs).
5354
5455
Here's an example output response:
5556
@@ -67,29 +68,29 @@ Here's an example output response:
6768

6869
## Inputs
6970

70-
The following are available input parameters:
71+
The following input parameters are available.
7172

7273
| Name | Type | Description | Required |
7374
| ---- | ---- | ----------- | -------- |
7475
| connection | AzureOpenAI | The Azure OpenAI connection to be used in the tool. | Yes |
7576
| deployment\_name | string | The language model to use. | Yes |
76-
| prompt | string | Text prompt that the language model uses to generate its response. The Jinja template for composing prompts in this tool follows a similar structure to the chat API in the LLM tool. To represent an image input within your prompt, you can use the syntax `![image]({{INPUT NAME}})`. Image input can be passed in the `user`, `system` and `assistant` messages. | Yes |
77-
| max\_tokens | integer | Maximum number of tokens to generate in the response. Default is 512. | No |
78-
| temperature | float | Randomness of the generated text. Default is 1. | No |
79-
| stop | list | Stopping sequence for the generated text. Default is null. | No |
80-
| top_p | float | Probability of using the top choice from the generated tokens. Default is 1. | No |
81-
| presence\_penalty | float | Value that controls the model's behavior regarding repeating phrases. Default is 0. | No |
82-
| frequency\_penalty | float | Value that controls the model's behavior regarding generating rare phrases. Default is 0. | No |
77+
| prompt | string | The text prompt that the language model uses to generate its response. The Jinja template for composing prompts in this tool follows a similar structure to the chat API in the large language model (LLM) tool. To represent an image input within your prompt, you can use the syntax `![image]({{INPUT NAME}})`. Image input can be passed in the `user`, `system`, and `assistant` messages. | Yes |
78+
| max\_tokens | integer | The maximum number of tokens to generate in the response. Default is 512. | No |
79+
| temperature | float | The randomness of the generated text. Default is 1. | No |
80+
| stop | list | The stopping sequence for the generated text. Default is null. | No |
81+
| top_p | float | The probability of using the top choice from the generated tokens. Default is 1. | No |
82+
| presence\_penalty | float | The value that controls the model's behavior regarding repeating phrases. Default is 0. | No |
83+
| frequency\_penalty | float | The value that controls the model's behavior regarding generating rare phrases. Default is 0. | No |
8384

8485
## Outputs
8586

86-
The following are available output parameters:
87+
The following output parameters are available.
8788

88-
| Return Type | Description |
89+
| Return type | Description |
8990
|-------------|------------------------------------------|
9091
| string | The text of one response of conversation |
9192

92-
## Next step
93+
## Next steps
9394

9495
- Learn more about [how to process images in prompt flow](../flow-process-image.md).
95-
- [Learn more about how to create a flow](../flow-develop.md).
96+
- Learn more about [how to create a flow](../flow-develop.md).

articles/ai-studio/how-to/prompt-flow-tools/content-safety-tool.md

Lines changed: 17 additions & 16 deletions
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,7 @@
11
---
22
title: Content Safety tool for flows in Azure AI Studio
33
titleSuffix: Azure AI Studio
4-
description: This article introduces the Content Safety tool for flows in Azure AI Studio.
4+
description: This article introduces you to the Content Safety tool for flows in Azure AI Studio.
55
manager: scottpolly
66
ms.service: azure-ai-studio
77
ms.custom:
@@ -17,41 +17,42 @@ author: lgayhardt
1717

1818
[!INCLUDE [Azure AI Studio preview](../../includes/preview-ai-studio.md)]
1919

20-
The prompt flow *Content Safety* tool enables you to use Azure AI Content Safety in Azure AI Studio.
20+
The prompt flow Content Safety tool enables you to use Azure AI Content Safety in Azure AI Studio.
2121

2222
Azure AI Content Safety is a content moderation service that helps detect harmful content from different modalities and languages. For more information, see [Azure AI Content Safety](/azure/ai-services/content-safety/).
2323

2424
## Prerequisites
2525

26-
Create an Azure Content Safety connection:
26+
To create an Azure Content Safety connection:
27+
2728
1. Sign in to [Azure AI Studio](https://studio.azureml.net/).
2829
1. Go to **AI project settings** > **Connections**.
2930
1. Select **+ New connection**.
30-
1. Complete all steps in the **Create a new connection** dialog box. You can use an Azure AI hub resource or Azure AI Content Safety resource. An Azure AI hub resource that supports multiple Azure AI services is recommended.
31+
1. Complete all steps in the **Create a new connection** dialog. You can use an Azure AI hub resource or Azure AI Content Safety resource. We recommend that you use an Azure AI hub resource that supports multiple Azure AI services.
3132

3233
## Build with the Content Safety tool
3334

3435
1. Create or open a flow in [Azure AI Studio](https://ai.azure.com). For more information, see [Create a flow](../flow-develop.md).
3536
1. Select **+ More tools** > **Content Safety (Text)** to add the Content Safety tool to your flow.
3637

37-
:::image type="content" source="../../media/prompt-flow/content-safety-tool.png" alt-text="Screenshot of the Content Safety tool added to a flow in Azure AI Studio." lightbox="../../media/prompt-flow/content-safety-tool.png":::
38+
:::image type="content" source="../../media/prompt-flow/content-safety-tool.png" alt-text="Screenshot that shows the Content Safety tool added to a flow in Azure AI Studio." lightbox="../../media/prompt-flow/content-safety-tool.png":::
3839

3940
1. Select the connection to one of your provisioned resources. For example, select **AzureAIContentSafetyConnection** if you created a connection with that name. For more information, see [Prerequisites](#prerequisites).
40-
1. Enter values for the Content Safety tool input parameters described [here](#inputs).
41-
1. Add more tools to your flow as needed, or select **Run** to run the flow.
42-
1. The outputs are described [here](#outputs).
41+
1. Enter values for the Content Safety tool input parameters described in the [Inputs table](#inputs).
42+
1. Add more tools to your flow, as needed. Or select **Run** to run the flow.
43+
1. The outputs are described in the [Outputs table](#outputs).
4344

4445
## Inputs
4546

46-
The following are available input parameters:
47+
The following input parameters are available.
4748

4849
| Name | Type | Description | Required |
4950
| ---- | ---- | ----------- | -------- |
5051
| text | string | The text that needs to be moderated. | Yes |
51-
| hate_category | string | The moderation sensitivity for Hate category. You can choose from four options: *disable*, *low_sensitivity*, *medium_sensitivity*, or *high_sensitivity*. The *disable* option means no moderation for hate category. The other three options mean different degrees of strictness in filtering out hate content. The default option is *medium_sensitivity*. | Yes |
52-
| sexual_category | string | The moderation sensitivity for Sexual category. You can choose from four options: *disable*, *low_sensitivity*, *medium_sensitivity*, or *high_sensitivity*. The *disable* option means no moderation for sexual category. The other three options mean different degrees of strictness in filtering out sexual content. The default option is *medium_sensitivity*. | Yes |
53-
| self_harm_category | string | The moderation sensitivity for Self-harm category. You can choose from four options: *disable*, *low_sensitivity*, *medium_sensitivity*, or *high_sensitivity*. The *disable* option means no moderation for self-harm category. The other three options mean different degrees of strictness in filtering out self_harm content. The default option is *medium_sensitivity*. | Yes |
54-
| violence_category | string | The moderation sensitivity for Violence category. You can choose from four options: *disable*, *low_sensitivity*, *medium_sensitivity*, or *high_sensitivity*. The *disable* option means no moderation for violence category. The other three options mean different degrees of strictness in filtering out violence content. The default option is *medium_sensitivity*. | Yes |
52+
| hate_category | string | The moderation sensitivity for the Hate category. You can choose from four options: `disable`, `low_sensitivity`, `medium_sensitivity`, or `high_sensitivity`. The `disable` option means no moderation for the Hate category. The other three options mean different degrees of strictness in filtering out hate content. The default option is `medium_sensitivity`. | Yes |
53+
| sexual_category | string | The moderation sensitivity for the Sexual category. You can choose from four options: `disable`, `low_sensitivity`, `medium_sensitivity`, or `high_sensitivity`. The `disable` option means no moderation for the Sexual category. The other three options mean different degrees of strictness in filtering out sexual content. The default option is `medium_sensitivity`. | Yes |
54+
| self_harm_category | string | The moderation sensitivity for the Self-harm category. You can choose from four options: `disable`, `low_sensitivity`, `medium_sensitivity`, or `high_sensitivity`. The `disable` option means no moderation for the Self-harm category. The other three options mean different degrees of strictness in filtering out self-harm content. The default option is `medium_sensitivity`. | Yes |
55+
| violence_category | string | The moderation sensitivity for the Violence category. You can choose from four options: `disable`, `low_sensitivity`, `medium_sensitivity`, or `high_sensitivity`. The `disable` option means no moderation for the Violence category. The other three options mean different degrees of strictness in filtering out violence content. The default option is `medium_sensitivity`. | Yes |
5556

5657
## Outputs
5758

@@ -69,12 +70,12 @@ The following JSON format response is an example returned by the tool:
6970
}
7071
```
7172

72-
You can use the following parameters as inputs for this tool:
73+
You can use the following parameters as inputs for this tool.
7374

7475
| Name | Type | Description |
7576
| ---- | ---- | ----------- |
76-
| action_by_category | string | A binary value for each category: *Accept* or *Reject*. This value shows if the text meets the sensitivity level that you set in the request parameters for that category. |
77-
| suggested_action | string | An overall recommendation based on the four categories. If any category has a *Reject* value, the `suggested_action` is *Reject* as well. |
77+
| action_by_category | string | A binary value for each category: `Accept` or `Reject`. This value shows if the text meets the sensitivity level that you set in the request parameters for that category. |
78+
| suggested_action | string | An overall recommendation based on the four categories. If any category has a `Reject` value, `suggested_action` is also `Reject`. |
7879

7980
## Next steps
8081

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

Lines changed: 11 additions & 13 deletions
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,7 @@
11
---
22
title: Embedding tool for flows in Azure AI Studio
33
titleSuffix: Azure AI Studio
4-
description: This article introduces the Embedding tool for flows in Azure AI Studio.
4+
description: This article introduces you to the Embedding tool for flows in Azure AI Studio.
55
manager: scottpolly
66
ms.service: azure-ai-studio
77
ms.custom:
@@ -17,32 +17,31 @@ author: lgayhardt
1717

1818
[!INCLUDE [Azure AI Studio preview](../../includes/preview-ai-studio.md)]
1919

20-
The prompt flow *Embedding* tool enables you to convert text into dense vector representations for various natural language processing tasks
20+
The prompt flow Embedding tool enables you to convert text into dense vector representations for various natural language processing tasks.
2121

2222
> [!NOTE]
23-
> For chat and completion tools, check out the [LLM tool](llm-tool.md).
23+
> For chat and completion tools, learn more about the large language model [(LLM) tool](llm-tool.md).
2424
2525
## Build with the Embedding tool
2626

2727
1. Create or open a flow in [Azure AI Studio](https://ai.azure.com). For more information, see [Create a flow](../flow-develop.md).
2828
1. Select **+ More tools** > **Embedding** to add the Embedding tool to your flow.
2929

30-
:::image type="content" source="../../media/prompt-flow/embedding-tool.png" alt-text="Screenshot of the Embedding tool added to a flow in Azure AI Studio." lightbox="../../media/prompt-flow/embedding-tool.png":::
30+
:::image type="content" source="../../media/prompt-flow/embedding-tool.png" alt-text="Screenshot that shows the Embedding tool added to a flow in Azure AI Studio." lightbox="../../media/prompt-flow/embedding-tool.png":::
3131

3232
1. Select the connection to one of your provisioned resources. For example, select **Default_AzureOpenAI**.
33-
1. Enter values for the Embedding tool input parameters described [here](#inputs).
34-
1. Add more tools to your flow as needed, or select **Run** to run the flow.
35-
1. The outputs are described [here](#outputs).
36-
33+
1. Enter values for the Embedding tool input parameters described in the [Inputs table](#inputs).
34+
1. Add more tools to your flow, as needed. Or select **Run** to run the flow.
35+
1. The outputs are described in the [Outputs table](#outputs).
3736

3837
## Inputs
3938

40-
The following are available input parameters:
39+
The following input parameters are available.
4140

4241
| Name | Type | Description | Required |
4342
|------------------------|-------------|-----------------------------------------------------------------------------------------|----------|
44-
| input | string | the input text to embed | Yes |
45-
| model, deployment_name | string | instance of the text-embedding engine to use | Yes |
43+
| input | string | The input text to embed. | Yes |
44+
| model, deployment_name | string | The instance of the text-embedding engine to use. | Yes |
4645

4746
## Outputs
4847

@@ -58,5 +57,4 @@ The output is a list of vector representations for the input text. For example:
5857

5958
## Next steps
6059

61-
- [Learn more about how to create a flow](../flow-develop.md)
62-
60+
- [Learn more about how to create a flow](../flow-develop.md)

0 commit comments

Comments
 (0)