switch ref to main; remove telemetry

Author: sdgilley

.openpublishing.publish.config.json

@@ -105,15 +105,21 @@
       "branch_mapping": {}
     },
     {
-      "path_to_root": "azureai-samples-nov2024",
+      "path_to_root": "azureai-samples-main",
       "url": "https://github.com/Azure-Samples/azureai-samples",
       "branch": "main",
       "branch_mapping": {}
     },
+    {
+      "path_to_root": "azureai-samples-nov2024",
+      "url": "https://github.com/Azure-Samples/azureai-samples",
+      "branch": "dantaylo/nov2024",
+      "branch_mapping": {}
+    },
     {
       "path_to_root": "azureai-samples-csharp",
       "url": "https://github.com/Azure-Samples/azureai-samples",
-      "branch": "main",
+      "branch": "dantaylo/csharp",
       "branch_mapping": {}
     },
     {

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

@@ -42,7 +42,7 @@ If you already have a search index with data, you can skip to [Get product docum
 
 Create an **assets** directory and add this example data to a **products.csv** file:
 
-:::code language="csv" source="~/azureai-samples-nov2024/scenarios/rag/custom-rag-app/assets/products.csv":::
+:::code language="csv" source="~/azureai-samples-main/scenarios/rag/custom-rag-app/assets/products.csv":::
 
 ## Create a search index
 
@@ -52,19 +52,19 @@ The search index is used to store vectorized data from the embeddings model. The
 1. Copy and paste the following code into your **create_search_index.py** file.
 1. Add the code to import the required libraries, create a project client, and configure some settings: 
 
-    :::code language="python" source="~/azureai-samples-nov2024/scenarios/rag/custom-rag-app/create_search_index.py" id="imports_and_config":::
+    :::code language="python" source="~/azureai-samples-main/scenarios/rag/custom-rag-app/create_search_index.py" id="imports_and_config":::
 
 1. Now add the function to define a search index:
 
-    :::code language="python" source="~/azureai-samples-nov2024/scenarios/rag/custom-rag-app/create_search_index.py" id="create_search_index":::
+    :::code language="python" source="~/azureai-samples-main/scenarios/rag/custom-rag-app/create_search_index.py" id="create_search_index":::
 
 1. Create the function to add a csv file to the index:
 
-    :::code language="python" source="~/azureai-samples-nov2024/scenarios/rag/custom-rag-app/create_search_index.py" id="add_csv_to_index":::
+    :::code language="python" source="~/azureai-samples-main/scenarios/rag/custom-rag-app/create_search_index.py" id="add_csv_to_index":::
 
 1. Finally, run the functions to build the index and register it to the cloud project:
 
-    :::code language="python" source="~/azureai-samples-nov2024/scenarios/rag/custom-rag-app/create_search_index.py" id="test_create_index":::
+    :::code language="python" source="~/azureai-samples-main/scenarios/rag/custom-rag-app/create_search_index.py" id="test_create_index":::
 
 1. From your console, log in to your Azure account and follow instructions for authenticating your account:
 
@@ -95,23 +95,23 @@ When the chat gets a request, it searches through your data to find relevant inf
 
 1. Start with code to import the required libraries, create a project client, and configure settings: 
 
-    :::code language="python" source="~/azureai-samples-nov2024/scenarios/rag/custom-rag-app/get_product_documents.py" id="imports_and_config":::
+    :::code language="python" source="~/azureai-samples-main/scenarios/rag/custom-rag-app/get_product_documents.py" id="imports_and_config":::
 
 1. Add the function to get product documents:
 
-    :::code language="python" source="~/azureai-samples-nov2024/scenarios/rag/custom-rag-app/get_product_documents.py" id="get_product_documents":::
+    :::code language="python" source="~/azureai-samples-main/scenarios/rag/custom-rag-app/get_product_documents.py" id="get_product_documents":::
 
 1. Finally, add code to test the function when you run the script directly:
 
-    :::code language="python" source="~/azureai-samples-nov2024/scenarios/rag/custom-rag-app/get_product_documents.py" id="test_get_documents":::
+    :::code language="python" source="~/azureai-samples-main/scenarios/rag/custom-rag-app/get_product_documents.py" id="test_get_documents":::
 
 ### Create prompt template for intent mapping
 
 The **get_product_documents.py** script uses a prompt template to convert the conversation to a search query. The template instructs how to extract the user's intent from the conversation.  
 
 Before you run the script, create the prompt template. Add the file **intent_mapping.prompty** to your **assets** folder:
 
-:::code language="prompty" source="~/azureai-samples-nov2024/scenarios/rag/custom-rag-app/assets/intent_mapping.prompty":::
+:::code language="prompty" source="~/azureai-samples-main/scenarios/rag/custom-rag-app/assets/intent_mapping.prompty":::
 
 ### Test the product document retrieval script
 
@@ -130,23 +130,23 @@ Next you create custom code to add retrieval augmented generation (RAG) capabili
 1. In your main folder, create a new file called **chat_with_products.py**. This script retrieves product documents and generates a response to a user's question.
 1. Add the code to import the required libraries, create a project client, and configure settings: 
 
-    :::code language="python" source="~/azureai-samples-nov2024/scenarios/rag/custom-rag-app/chat_with_products.py" id="imports_and_config":::
+    :::code language="python" source="~/azureai-samples-main/scenarios/rag/custom-rag-app/chat_with_products.py" id="imports_and_config":::
 
 1. Create the chat function that uses the RAG capabilities:
 
-    :::code language="python" source="~/azureai-samples-nov2024/scenarios/rag/custom-rag-app/chat_with_products.py" id="chat_function":::
+    :::code language="python" source="~/azureai-samples-main/scenarios/rag/custom-rag-app/chat_with_products.py" id="chat_function":::
 
 1. Finally, add the code to run the chat function:
 
-    :::code language="python" source="~/azureai-samples-nov2024/scenarios/rag/custom-rag-app/chat_with_products.py" id="test_function":::
+    :::code language="python" source="~/azureai-samples-main/scenarios/rag/custom-rag-app/chat_with_products.py" id="test_function":::
 
 ### Create a grounded chat prompt template
 
 The **chat_with_products.py** script calls a prompt template to generate a response to the user's question. The template instructs how to generate a response based on the user's question and the retrieved documents.  Create this template now.
 
 In your **assets** folder, add the file **grounded_chat.prompty**:
 
-:::code language="prompty" source="~/azureai-samples-nov2024/scenarios/rag/custom-rag-app/assets/grounded_chat.prompty":::
+:::code language="prompty" source="~/azureai-samples-main/scenarios/rag/custom-rag-app/assets/grounded_chat.prompty":::
 
 ### Run the chat script with RAG capabilities
 
@@ -156,7 +156,7 @@ Now that you have both the script and the template, run the script to test your
 python chat_with_products.py --query "I need a new tent for 4 people, what would you recommend?"
 ```
 
-To enable logging of telemetry to your project:
+<!-- To enable logging of telemetry to your project:
 
 1. Install `azure-monitor-opentelemetry`:
 
@@ -167,7 +167,7 @@ To enable logging of telemetry to your project:
 1. Add the `--enable-telemetry` flag when you use the `chat_with_products.py` script:
 
    ```bash
-   python chat_with_products.py --query "I need a new tent for 4 people, what would you recommend?" --enable-telemetry
+   python chat_with_products.py --query "I need a new tent for 4 people, what would you recommend?" --enable-telemetry -->
    ```
 
 ## Clean up resources

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

@@ -127,7 +127,7 @@ Install `azure-ai-projects`(preview) and `azure-ai-inference` (preview), along w
 
 1. First, create a file named **requirements.txt** in your project folder. Add the following packages to the file:
 
-    :::code language="txt" source="~/azureai-samples-nov2024/scenarios/rag/custom-rag-app/requirements.txt":::
+    :::code language="txt" source="~/azureai-samples-main/scenarios/rag/custom-rag-app/requirements.txt":::
 
 1. Install the required packages:
 
@@ -139,7 +139,7 @@ Install `azure-ai-projects`(preview) and `azure-ai-inference` (preview), along w
 
 Create a folder for your work. Create a file called **config.py** in this folder. This helper script is used in the next two parts of the tutorial series. Add the following code:
 
-:::code language="python" source="~/azureai-samples-nov2024/scenarios/rag/custom-rag-app/config.py":::
+:::code language="python" source="~/azureai-samples-main/scenarios/rag/custom-rag-app/config.py":::
 
 
 ## Configure environment variables

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

@@ -46,7 +46,7 @@ Use the following evaluation dataset, which contains example questions and expec
 1. Create a file called **chat_eval_data.jsonl** in your **assets** folder.
 1. Paste this dataset into the file:
 
-    :::code language="jsonl" source="~/azureai-samples-nov2024/scenarios/rag/custom-rag-app/assets/chat_eval_data.jsonl":::
+    :::code language="jsonl" source="~/azureai-samples-main/scenarios/rag/custom-rag-app/assets/chat_eval_data.jsonl":::
 
 ## Evaluate with Azure AI evaluators
 
@@ -65,15 +65,15 @@ The script also logs the evaluation results to the cloud project so that you can
 1. Create a file called **evaluate.py** in your main folder.
 1. Add the following code to import the required libraries, create a project client, and configure some settings: 
 
-    :::code language="python" source="~/azureai-samples-nov2024/scenarios/rag/custom-rag-app/evaluate.py" id="imports_and_config":::
+    :::code language="python" source="~/azureai-samples-main/scenarios/rag/custom-rag-app/evaluate.py" id="imports_and_config":::
 
 1. Add code to create a wrapper function that implements the evaluation interface for query and response evaluation:
 
-    :::code language="python" source="~/azureai-samples-nov2024/scenarios/rag/custom-rag-app/evaluate.py" id="evaluate_wrapper":::
+    :::code language="python" source="~/azureai-samples-main/scenarios/rag/custom-rag-app/evaluate.py" id="evaluate_wrapper":::
 
 1. Finally, add code to run the evaluation, view the results locally, and gives you a link to the evaluation results in AI Foundry portal:
 
-    :::code language="python" source="~/azureai-samples-nov2024/scenarios/rag/custom-rag-app/evaluate.py" id="run_evaluation":::
+    :::code language="python" source="~/azureai-samples-main/scenarios/rag/custom-rag-app/evaluate.py" id="run_evaluation":::
 
 ### Configure the evaluation model