Merge pull request #3028 from aahill/assistants-fixes

bing grounding section

Author: prmerger-automator[bot]

articles/ai-services/agents/how-to/tools/bing-grounding.md

@@ -28,6 +28,13 @@ Developers and end users don't have access to raw content returned from Groundin
 > 1. By creating and using a Grounding with Bing Search resource through code-first experience, such as Azure CLI, or deploying through deployment template, you agree to be bound by and comply with the terms available at https://www.microsoft.com/en-us/bing/apis/grounding-legal, which may be updated from time to time.
 > 1. When you use Grounding with Bing Search, your customer data is transferred outside of the Azure compliance boundary to the Grounding with Bing Search service. Grounding with Bing Search is not subject to the same data processing terms (including location of processing) and does not have the same compliance standards and certifications as the Azure AI Agent Service, as described in the [Grounding with Bing Search Terms of Use](https://www.microsoft.com/en-us/bing/apis/grounding-legal). It is your responsibility to assess whether use of Grounding with Bing Search in your agent meets your needs and requirements.
 
+## How Grounding with Bing Search works
+
+The user query is the message that an end user sends to an agent, such as *"should I take an umbrella with me today? I'm in Seattle."* Instructions are the system message a developer can provide to share context and provide instructions to the AI model on how to use various tools or behave. 
+
+When a user sends a query, the customer's AI model deployment first processes it (using the provided instructions) to later perform a Bing search query (which is [visible to developers](#how-to-display-grounding-with-bing-search-results)). 
+Grounding with Bing returns relevant search results to the customer's model deployment, which then generates the final output. When using Grounding with Bing Search, only the Bing search query and your resource key are sent to Bing, and no end user-specific information is included. Your resource key is sent to Bing solely for billing and rate limiting purposes. Any Bing search query that is generated and sent to Bing for the purposes of grounding is transferred, along with the resource key, outside of the Azure compliance boundary to the Grounding with Bing Search service. Grounding with Bing Search is subject to Bing's terms and do not have the same compliance standards and certifications as the Azure AI Agent Service, as described in the [Grounding with Bing Search Terms of Use](https://www.microsoft.com/bing/apis/grounding-legal). It is your responsibility to assess whether the use of Grounding with Bing Search in your agent meets your needs and requirements.
+
 ## Usage support
 
 |Azure AI foundry support  | Python SDK |	C# SDK | JavaScript SDK | REST API |Basic agent setup | Standard agent setup |

articles/ai-services/openai/concepts/use-your-data.md

@@ -82,6 +82,8 @@ For some data sources such as uploading files from your local machine (preview)
 |URL/Web address (preview)        | Web content from the URLs is stored in Azure Blob Storage.         |
 |Azure Blob Storage (preview) | Upload files from Azure Blob Storage to be ingested into an Azure AI Search index.         |
 
+If you choose to upload files or connect Azure Blob Storage, your data should be unstructured text for best results. If you have non-textual semi-structured or structured data consider converting it to text. If your files have special formatting, such as tables and columns, or bullet points, prepare your data with the data preparation script available on [GitHub](https://github.com/microsoft/sample-app-aoai-chatGPT/tree/main/scripts#optional-crack-pdfs-to-text).
+
 :::image type="content" source="../media/use-your-data/azure-databases-and-ai-search.png" lightbox="../media/use-your-data/azure-databases-and-ai-search.png" alt-text="Diagram of vector indexing services.":::
 
 # [Azure AI Search](#tab/ai-search)
@@ -93,7 +95,7 @@ You might want to consider using an Azure AI Search index when you either want t
 > [!NOTE]
 > * To use an existing index, it must have at least one searchable field.
 > * Set the CORS **Allow Origin Type** option to `all` and the **Allowed origins** option to `*`. 
-
+> * You cannot have complex fields in your search index. 
 
 ### Search types
 

articles/ai-services/openai/how-to/use-web-app.md

@@ -7,19 +7,21 @@ ms.service: azure-ai-openai
 ms.topic: how-to
 author: aahill
 ms.author: aahi
-ms.date: 01/08/2025
+ms.date: 02/19/2025
 recommendations: false
 ---
 
 
 # Use the Azure OpenAI web app
 
+> [!NOTE]
+> The web app and its [source code](https://github.com/microsoft/sample-app-aoai-chatGPT) are provided "as is" and as a sample only. Customers are responsible for all customization and implementation of their web apps. See the support section for the web app on [GitHub](https://github.com/microsoft/sample-app-aoai-chatGPT/blob/main/SUPPORT.md) for more information.
+
 Along with Azure AI Foundry portal, APIs, and SDKs, you can use the customizable standalone web app to interact with Azure OpenAI models by using a graphical user interface. Key features include:
 * Connectivity with multiple data sources to support rich querying and retrieval-augmented generation, including Azure AI Search, Prompt Flow, and more.
 * Conversation history and user feedback collection through Cosmos DB.
 * Authentication with role-based access control via Microsoft Entra ID.
 * Customization of the user interface, data sources, and features using environment variables (no-code via Azure portal).
-* Sample source code for the web app is available on [GitHub](https://github.com/microsoft/sample-app-aoai-chatGPT). Source code is provided "as is" and as a sample only. Customers are responsible for all customization and implementation of their web apps.
 
 You can deploy the app via the [Azure AI Foundry portal](/azure/ai-studio/tutorials/deploy-chat-web-app), the [Azure portal](https://portal.azure.com), or the Azure Developer CLI via your local machine [(instructions available at the repository here)](https://github.com/microsoft/sample-app-aoai-chatGPT). Depending on your deployment channel, you can preload a data source to chat with via the web application, but this can be changed after deployment.