Merge pull request #265547 from eric-urban/eur/ai-studio-refresh

ai studio refresh docs

Author: JamesJBarnett

articles/ai-studio/how-to/costs-plan-manage.md

@@ -87,7 +87,7 @@ When you use cost analysis, you view Azure AI hub resource costs in graphs and t
 
 ### Monitor Azure AI Studio project costs
 
-You can get to cost analysis from the [Azure portal](https://portal.azure.com). You can also get to cost analysis from the [Azure AI Studio portal](https://ai.azure.com).
+You can get to cost analysis from the [Azure portal](https://portal.azure.com). You can also get to cost analysis from the [Azure AI Studio](https://ai.azure.com).
 
 > [!IMPORTANT]
 > Your Azure AI project costs are only a subset of your overall application or solution costs. You need to monitor costs for all Azure resources used in your application or solution. See [Azure AI hub resources](../concepts/ai-resources.md) for more information.
@@ -96,14 +96,14 @@ For the examples in this section, assume that all Azure AI Studio resources are
 
 Here's an example of how to monitor costs for an Azure AI Studio project. The costs are used as an example only. Your costs will vary depending on the services that you use and the amount of usage.
 
-1. Sign in to [Azure AI Studio portal](https://ai.azure.com).
+1. Sign in to [Azure AI Studio](https://ai.azure.com).
 1. Select your project and then select **Settings** from the left navigation menu.
 
     :::image type="content" source="../media/cost-management/project-costs/project-settings-go-view-costs.png" alt-text="Screenshot of the Azure AI Studio portal showing how to see project settings." lightbox="../media/cost-management/project-costs/project-settings-go-view-costs.png":::
 
-1. Select **See project cost on Azure portal**. The Azure portal opens to the cost analysis page for your project. 
+1. Select **View cost for resources**. The [Azure portal](https://portal.azure.com) opens to the cost analysis page for your project. 
 
-1. Expand the **Resource** column to see the costs for each service that's underlying your [Azure AI project](../concepts/ai-resources.md#organize-work-in-projects-for-customization). But this view doesn't include costs for all resources that you use in an Azure AI Studio project.
+1. Expand the **Resource** column to see the costs for each service that's underlying your [Azure AI project](../concepts/ai-resources.md#organize-work-in-projects-for-customization). But this view doesn't include costs for all resources that you use in an Azure AI project.
 
     :::image type="content" source="../media/cost-management/project-costs/costs-per-project-resource.png" alt-text="Screenshot of the Azure portal cost analysis with the Azure AI project and associated resources." lightbox="../media/cost-management/project-costs/costs-per-project-resource.png":::
 
@@ -125,7 +125,7 @@ Here's an example of how to monitor costs for an Azure AI Studio project. The co
 
     :::image type="content" source="../media/cost-management/project-costs/costs-per-project-resource-details.png" alt-text="Screenshot of the Azure portal cost analysis with Azure AI project expanded." lightbox="../media/cost-management/project-costs/costs-per-project-resource-details.png":::
 
-1. Expand **contoso_ai_resource** to see the costs for services underlying the [Azure AI](../concepts/ai-resources.md#azure-ai-hub-resources) resource. You can also apply a filter to focus on other costs in your resource group. 
+1. Expand **contoso_ai_resource** to see the costs for services underlying the [Azure AI hub](../concepts/ai-resources.md#azure-ai-hub-resources) resource. You can also apply a filter to focus on other costs in your resource group. 
 
 You can also view resource group costs directly from the Azure portal. To do so:
 1. Sign in to [Azure portal](https://portal.azure.com).

articles/ai-studio/how-to/generate-data-qa.md

@@ -7,7 +7,7 @@ ms.service: azure-ai-studio
 ms.custom:
   - ignite-2023
 ms.topic: how-to
-ms.date: 11/15/2023
+ms.date: 2/6/2024
 ms.reviewer: eur
 ms.author: eur
 author: eric-urban
@@ -124,7 +124,7 @@ print(f"Tokens used: {result['token_usage']}")
 
 ## Using the generated data in prompt flow
 
-One of the features of prompt flow is the ability to test and evaluate your flows on batch of inputs. This approach is useful for checking the quality and performance of your flows before deploying them. To use this feature, you need to provide the data in a specific (.jsonl) format that prompt flow can understand. We prepare this data from the questions and answers that we have generated in [Generate data from text](#generate-data-from-text) step. We use this data for batch run and flow evaluation.
+One of the features of [prompt flow](./prompt-flow.md) is the ability to test and [evaluate your flows](./evaluate-flow-results.md) with a batch of inputs. This approach is useful for checking the quality and performance of your flows before deploying them. To use this feature, you need to provide the data in a specific (.jsonl) format that prompt flow can understand. Now prepare this data from the questions and answers that we generated in [Generate data from text](#generate-data-from-text) step. We use this data for batch run and flow evaluation.
 
 ### Format and save the generated data
 
@@ -156,7 +156,7 @@ data_df.to_json(output_file, lines=True, orient="records")
 
 ### Use the data for evaluation
 
-To use the "generated_qa.jsonl" file for evaluation, you need to add this file as data to your evaluation flow. Go to a flow in Azure AI Studio and select **Evaluate**.
+To use the `generated_qa.jsonl` file for evaluation, you need to add this file as data to your evaluation flow. Go to a flow in Azure AI Studio and select **Evaluate**.
 
 1. Enter details in **Basic Settings**
 2. Select **Add new data** from **Batch run settings**.

articles/ai-studio/how-to/index-add.md

@@ -116,9 +116,9 @@ If the Azure AI hub resource the project uses was created through Azure portal:
 
 ## Use an index in prompt flow
 
-1. Open your AI Studio project
-1. In Flows, create a new Flow or open an existing flow 
-1. On the top menu of the flow designer, select **More tools**, and then select ***Index Lookup***
+1. Open your AI Studio project.
+1. In **Flows**, create a new flow or open an existing flow.
+1. On the top menu of the flow designer, select **More tools**, and then select ***Index Lookup***.
 
     :::image type="content" source="../media/index-retrieve/index-lookup-tool.png" alt-text="Screenshot of Vector index Lookup from More Tools." lightbox="../media/index-retrieve/index-lookup-tool.png":::
 

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

@@ -42,7 +42,7 @@ The following are available input parameters:
 
 ## Outputs
 
-The following JSON format response is an example returned by the tool that includes the top-k scored entities. The entity follows a generic schema of vector search result provided by promptflow-vectordb SDK. For the Faiss Index Search, the following fields are populated:
+The following JSON format response is an example returned by the tool that includes the top-k scored entities. The entity follows a generic schema of vector search result provided by the `promptflow-vectordb` SDK. For the Faiss Index Search, the following fields are populated:
 
 | Field Name | Type | Description |
 | ---- | ---- | ----------- |

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

@@ -34,12 +34,13 @@ The following are available input parameters:
 
 | Name | Type | Description | Required |
 | ---- | ---- | ----------- | -------- |
-| mlindex_content | string | Type of Index to be used. Input depends on Index type. Example of an Azure Cog Search Index JSON can be seen below the table* | Yes |
-| queries | string, Union[string, List[String]] | The text to be queried.| Yes |
-|query_type | string | The type of query to be performed. Options include Keyword, Semantic, Hybrid, etc.  | Yes |
+| mlindex_content | string | Type of index to be used. Input depends on the index type. An example of an Azure AI Search index JSON can be seen below the table. | Yes |
+| queries | string, `Union[string, List[String]]` | The text to be queried.| Yes |
+|query_type | string | The type of query to be performed. Options include Keyword, Semantic, Hybrid, and others.  | Yes |
 | top_k | integer | The count of top-scored entities to return. Default value is 3. | No |
 
-\**ACS JSON Example:*
+Here's an example of an Azure AI Search index input.
+
 ```json
 embeddings:
   api_base: <api_base>
@@ -68,14 +69,11 @@ index:
   index: <index_name>
   kind: acs
   semantic_configuration_name: azureml-default
-
-
-
 ```
 
 ## Outputs
 
-The following JSON format response is an example returned by the tool that includes the top-k scored entities. The entity follows a generic schema of vector search result provided by promptflow-vectordb SDK. For the Vector Index Search, the following fields are populated:
+The following JSON format response is an example returned by the tool that includes the top-k scored entities. The entity follows a generic schema of vector search result provided by the `promptflow-vectordb` SDK. For the Vector Index Search, the following fields are populated:
 
 | Field Name | Type | Description |
 | ---- | ---- | ----------- |

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

@@ -5,7 +5,7 @@ description: Learn about prompt flow tools that are available in Azure AI Studio
 manager: nitinme
 ms.service: azure-ai-studio
 ms.topic: overview
-ms.date: 12/6/2023
+ms.date: 2/6/2024
 ms.reviewer: keli19
 ms.author: lagayhar
 author: lgayhardt
@@ -35,7 +35,7 @@ To discover more custom tools developed by the open-source community, see [More
 ## Remarks
 - If existing tools don't meet your requirements, you can [develop your own custom tool and make a tool package](https://microsoft.github.io/promptflow/how-to-guides/develop-a-tool/create-and-use-tool-package.html).
 - To install the custom tools, if you are using the automatic runtime, you can readily install the package by adding the custom tool package name into the `requirements.txt` file in the flow folder. Then select the **Save and install** button to start installation. After completion, you can see the custom tools displayed in the tool list. To learn more, see [How to create and manage a runtime](../create-manage-runtime.md).
-:::image type="content" source="./media/prompt-flow-tools-overview/install-package-on-automatic-runtime.png" alt-text="Screenshot of how to install packages on automatic runtime."lightbox = "./media/prompt-flow-tools-overview/install-package-on-automatic-runtime.png":::
+:::image type="content" source="../../media/prompt-flow/install-package-on-automatic-runtime.png" alt-text="Screenshot of how to install packages on automatic runtime."lightbox = "../../media/prompt-flow/install-package-on-automatic-runtime.png":::
 
 ## Next steps
 

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

@@ -6,7 +6,7 @@ manager: nitinme
 ms.service: azure-ai-studio
 ms.custom: ignite-2023, devx-track-python
 ms.topic: how-to
-ms.date: 11/15/2023
+ms.date: 2/6/2024
 ms.reviewer: keli19
 ms.author: lagayhar
 author: lgayhardt
@@ -112,19 +112,19 @@ If you're developing a python tool that requires calling external services with
 Create a custom connection that stores all your LLM API KEY or other required credentials.
 
 1. Go to Prompt flow in your workspace, then go to **connections** tab.
-2. Select **Create** and select **Custom**.
-3. In the right panel, you can define your connection name, and you can add multiple *Key-value pairs* to store your credentials and keys by selecting **Add key-value pairs**.
-4. Besides your key value pairs, please also add following extra meta data to the connection:
-    - azureml.flow.connection_type: Custom
-    - azureml.flow.module: promptflow.connections
-    
-    :::image type="content" source="./media/python-tool/custom-connection-meta.png" alt-text="Screenshot that shows add extra meta to custom connection in AI Studio." lightbox = "./media/python-tool/custom-connection-meta.png"::: 
+1. Select **Create** and select **Custom**.
+1. In the right panel, you can define your connection name, and you can add multiple *Key-value pairs* to store your credentials and keys by selecting **Add key-value pairs**. 
+
+    > [!NOTE]
+    > Make sure at least one key-value pair is set as secret, otherwise the connection will not be created successfully. You can set one Key-Value pair as secret by **is secret** checked, which will be encrypted and stored in your key value.
 
+1. Add the following custom keys to the connection:
+    - `azureml.flow.connection_type`: `Custom`
+    - `azureml.flow.module`: `promptflow.connections`
 
-> [!NOTE]
-> - You can set one Key-Value pair as secret by **is secret** checked, which will be encrypted and stored in your key value.
-> - Make sure at least one key-value pair is set as secret, otherwise the connection will not be created successfully.
+    :::image type="content" source="../../media/prompt-flow/custom-connection-keys.png" alt-text="Screenshot that shows add extra meta to custom connection in AI Studio." lightbox = "../../media/prompt-flow/custom-connection-keys.png"::: 
 
+   
 
 ### Consume custom connection in Python
 

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

@@ -7,7 +7,7 @@ ms.service: azure-ai-studio
 ms.custom:
   - ignite-2023
 ms.topic: how-to
-ms.date: 11/15/2023
+ms.date: 2/6/2024
 ms.reviewer: keli19
 ms.author: lagayhar
 author: lgayhardt
@@ -29,12 +29,12 @@ Create a Serp connection:
 1. Sign in to [Azure AI Studio](https://studio.azureml.net/).
 1. Go to **Settings** > **Connections**.
 1. Select **+ New connection**.
-1. Create a custom connection with the following details:
-    - azureml.flow.connection_type: Serp
-    - azureml.flow.module: promptflow.connections
-    - api_key: Your_Serp_API_key, please mark it as a secret.
+1. Add the following custom keys to the connection:
+    - `azureml.flow.connection_type`: `Custom`
+    - `azureml.flow.module`: `promptflow.connections`
+    - `api_key`: Your_Serp_API_key. You must check the **is secret** checkbox to keep the API key secure.
 
-    :::image type="content" source="./media/serp-api-tool/serp-connection-meta.png" alt-text="Screenshot that shows add extra meta to custom connection in AI Studio." lightbox = "./media/serp-api-tool/serp-connection-meta.png"::: 
+    :::image type="content" source="../../media/prompt-flow/serp-custom-connection-keys.png" alt-text="Screenshot that shows add extra meta to custom connection in AI Studio." lightbox = "../../media/prompt-flow/serp-custom-connection-keys.png"::: 
 
 The connection is the model used to establish connections with Serp API. Get your API key from the SerpAPI account dashboard. 
 

articles/ai-studio/how-to/prompt-flow-tools/vector-db-lookup-tool.md

@@ -7,7 +7,7 @@ ms.service: azure-ai-studio
 ms.custom:
   - ignite-2023
 ms.topic: how-to
-ms.date: 11/15/2023
+ms.date: 2/6/2024
 ms.reviewer: keli19
 ms.author: lagayhar
 author: lgayhardt
@@ -50,23 +50,22 @@ The tool searches data from a third-party vector database. To use it, you should
     :::image type="content" source="../../media/prompt-flow/vector-db-lookup-tool.png" alt-text="Screenshot of the Vector DB Lookup tool added to a flow in Azure AI Studio." lightbox="../../media/prompt-flow/embedding-tool.png":::
 
 1. Select the connection to one of your provisioned resources. For example, select **CognitiveSearchConnection**.
-1. Enter values for the Vector DB Lookup tool input parameters described [here](#inputs-and-outputs).
+1. Enter values for the Vector DB Lookup tool input parameters described [here](#inputs).
 1. Add more tools to your flow as needed, or select **Run** to run the flow.
-1. The outputs are described [here](#inputs-and-outputs).
+1. The outputs are described [here](#outputs).
 
 
-## Inputs and outputs
+## Inputs
 
 The tool accepts the following inputs:
 - [Azure AI Search](#azure-ai-search)
 - [Qdrant](#qdrant)
 - [Weaviate](#weaviate)
 
-The JSON output includes the top-k scored entities. The entity follows a generic schema of vector search result provided by promptflow-vectordb SDK. 
 
 ## Outputs
 
-The following JSON format response is an example returned by the tool that includes the top-k scored entities. The entity follows a generic schema of vector search result provided by promptflow-vectordb SDK. 
+The JSON output includes the top-k scored entities. The entity follows a generic schema of vector search result provided by the promptflow-vectordb SDK. 
 
 
 ### Azure AI Search

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

@@ -43,7 +43,7 @@ The following are available input parameters:
 
 ## Outputs
 
-The following JSON format response is an example returned by the tool that includes the top-k scored entities. The entity follows a generic schema of vector search result provided by promptflow-vectordb SDK. For the Vector Index Search, the following fields are populated:
+The following JSON format response is an example returned by the tool that includes the top-k scored entities. The entity follows a generic schema of vector search result provided by the `promptflow-vectordb` SDK. For the Vector Index Search, the following fields are populated:
 
 | Field Name | Type | Description |
 | ---- | ---- | ----------- |