freshness update

Author: sdgilley

articles/ai-studio/tutorials/copilot-sdk-build-rag.md

@@ -5,7 +5,7 @@ description:  Learn how to build a RAG-based chat app using the Azure AI Foundry
 manager: scottpolly
 ms.service: azure-ai-foundry
 ms.topic: tutorial
-ms.date: 12/18/2024
+ms.date: 02/12/2025
 ms.reviewer: lebaro
 ms.author: sgilley
 author: sdgilley
@@ -78,11 +78,6 @@ The search index is used to store vectorized data from the embeddings model. The
     python create_search_index.py
     ```
 
-1. Once the script is run, you can view your newly created index in the **Data + indexes** page of your Azure AI Foundry project. For more information, see [How to build and consume vector indexes in Azure AI Foundry portal](../how-to/index-add.md).
-
-1. If you run the script again with the same index name, it creates a new version of the same index.
-
-
 ## <a name="get-documents"></a> Get product documents
 
 Next, you create a script to get product documents from the search index. The script queries the search index for documents that match a user's question.
@@ -176,6 +171,7 @@ To enable logging of telemetry to your project:
    python chat_with_products.py --query "I need a new tent for 4 people, what would you recommend?" --enable-telemetry 
    ```
 
+Follow the link in the console output to see the telemetry data in your Application Insights resource. If it doesn't appear right away, wait a few minutes and select **Refresh** in the toolbar.
 
 ## Clean up resources
 

articles/ai-studio/tutorials/copilot-sdk-create-resources.md

@@ -7,7 +7,7 @@ ms.service: azure-ai-foundry
 ms.custom:
   - ignite-2024
 ms.topic: tutorial
-ms.date: 12/18/2024
+ms.date: 02/12/2025
 ms.reviewer: lebaro
 ms.author: sgilley
 author: sdgilley

articles/ai-studio/tutorials/copilot-sdk-evaluate.md

@@ -85,7 +85,7 @@ In Part 1 of this tutorial series, you created an **.env** file that specifies t
 1. In your project in Azure AI Foundry portal, select **Models + endpoints**.
 1. Select **gpt-4o-mini**.  
 1. Select **Edit**.
-1. If you have quota to increase the **Tokens per Minute Rate Limit**, try increasing it to 30. 
+1. If you have quota to increase the **Tokens per Minute Rate Limit**, try increasing it to 30 or above. 
 1. Select **Save and close**.
 
 ### Run the evaluation script
@@ -108,6 +108,8 @@ In Part 1 of this tutorial series, you created an **.env** file that specifies t
     python evaluate.py
     ```
 
+Expect the evaluation to take a few minutes to complete.
+
 ### Interpret the evaluation output
 
 In the console output, you see an answer for each question, followed by a table with summarized metrics. (You might see different columns in your output.)
@@ -160,7 +162,7 @@ For more information about evaluation results in Azure AI Foundry portal, see [H
 
 Notice that the responses are not well grounded. In many cases, the model replies with a question rather than an answer. This is a result of the prompt template instructions. 
  
-* In your **assets/grounded_chat.prompty** file, find the sentence "If the question is related to outdoor/camping gear and clothing but vague, ask for clarifying questions instead of referencing documents."
+* In your **assets/grounded_chat.prompty** file, find the sentence "If the question is not related to outdoor/camping gear and clothing, just say 'Sorry, I only can answer queries related to outdoor/camping gear and clothing. So, how can I help?'"
 * Change the sentence to "If the question is related to outdoor/camping gear and clothing but vague, try to answer based on the reference documents, then ask for clarifying questions."  
 * Save the file and re-run the evaluation script.